{"meta":{"computed_at":"2026-04-08T04:13:33.892Z","model_count":178,"response_count":3095,"challenge_count":43,"feature_count":32,"total_pairs":15753,"clone_threshold":0.9,"near_clone_threshold":0.8,"min_responses":3},"global_stats":{"avg_similarity":0,"similarity_stddev":0.2748,"clone_pair_count":12,"near_clone_pair_count":45,"similarity_distribution":[{"range":"-0.75 to -0.70","count":7,"pct":0.04},{"range":"-0.70 to -0.65","count":21,"pct":0.13},{"range":"-0.65 to -0.60","count":22,"pct":0.14},{"range":"-0.60 to -0.55","count":69,"pct":0.44},{"range":"-0.55 to -0.50","count":161,"pct":1.02},{"range":"-0.50 to -0.45","count":230,"pct":1.46},{"range":"-0.45 to -0.40","count":383,"pct":2.43},{"range":"-0.40 to -0.35","count":493,"pct":3.13},{"range":"-0.35 to -0.30","count":660,"pct":4.19},{"range":"-0.30 to -0.25","count":873,"pct":5.54},{"range":"-0.25 to -0.20","count":934,"pct":5.93},{"range":"-0.20 to -0.15","count":1055,"pct":6.7},{"range":"-0.15 to -0.10","count":1238,"pct":7.86},{"range":"-0.10 to -0.05","count":1172,"pct":7.44},{"range":"-0.05 to 0.00","count":1102,"pct":7},{"range":"0.00 to 0.05","count":1097,"pct":6.96},{"range":"0.05 to 0.10","count":1014,"pct":6.44},{"range":"0.10 to 0.15","count":873,"pct":5.54},{"range":"0.15 to 0.20","count":787,"pct":5},{"range":"0.20 to 0.25","count":698,"pct":4.43},{"range":"0.25 to 0.30","count":603,"pct":3.83},{"range":"0.30 to 0.35","count":517,"pct":3.28},{"range":"0.35 to 0.40","count":400,"pct":2.54},{"range":"0.40 to 0.45","count":302,"pct":1.92},{"range":"0.45 to 0.50","count":275,"pct":1.75},{"range":"0.50 to 0.55","count":193,"pct":1.23},{"range":"0.55 to 0.60","count":173,"pct":1.1},{"range":"0.60 to 0.65","count":119,"pct":0.76},{"range":"0.65 to 0.70","count":80,"pct":0.51},{"range":"0.70 to 0.75","count":87,"pct":0.55},{"range":"0.75 to 0.80","count":58,"pct":0.37},{"range":"0.80 to 0.85","count":29,"pct":0.18},{"range":"0.85 to 0.90","count":16,"pct":0.1},{"range":"0.90 to 0.95","count":10,"pct":0.06},{"range":"0.95 to 1.00","count":2,"pct":0.01}]},"top_similar_pairs":[{"model_a":"devstral-medium","model_b":"devstral-small","name_a":"Mistral Devstral Medium","name_b":"Mistral Devstral Small 1.1","provider_a":"mistral","provider_b":"mistral","similarity":0.9568},{"model_a":"qwen3-coder","model_b":"qwen3-coder-flash","name_a":"Qwen3 Coder","name_b":"Qwen3 Coder Flash","provider_a":"qwen","provider_b":"qwen","similarity":0.9556},{"model_a":"mistral-large-2512","model_b":"mistral-small-creative","name_a":"Mistral Large 3 2512","name_b":"Mistral Small Creative","provider_a":"mistral","provider_b":"mistral","similarity":0.9459},{"model_a":"gpt-5.4","model_b":"gpt-5.4-mini","name_a":"GPT-5.4","name_b":"GPT-5.4 Mini","provider_a":"openai","provider_b":"openai","similarity":0.9328},{"model_a":"mercury-2","model_b":"solar-pro-3-free","name_a":"Inception: Mercury 2","name_b":"Solar Pro 3","provider_a":"inception","provider_b":"upstage","similarity":0.9261},{"model_a":"llama-4-maverick","model_b":"llama-4-scout","name_a":"Llama 4 Maverick","name_b":"Llama 4 Scout","provider_a":"meta","provider_b":"meta","similarity":0.919},{"model_a":"gpt-5","model_b":"gpt-5-nano","name_a":"GPT-5","name_b":"GPT-5 Nano","provider_a":"openai","provider_b":"openai","similarity":0.9116},{"model_a":"qwen3.5-27b","model_b":"qwen3.5-35b-a3b","name_a":"Qwen: Qwen3.5 27B","name_b":"Qwen: Qwen3.5 35B A3B","provider_a":"qwen","provider_b":"qwen","similarity":0.911},{"model_a":"mistral-medium-3.1","model_b":"mistral-small-creative","name_a":"Mistral Medium 3.1","name_b":"Mistral Small Creative","provider_a":"mistral","provider_b":"mistral","similarity":0.9081},{"model_a":"aurora-alpha","model_b":"solar-pro-3-free","name_a":"Aurora Alpha","name_b":"Solar Pro 3","provider_a":"openrouter","provider_b":"upstage","similarity":0.907},{"model_a":"mistral-large-2512","model_b":"mistral-small-2603","name_a":"Mistral Large 3 2512","name_b":"Mistral Small 4","provider_a":"mistral","provider_b":"mistral","similarity":0.9016},{"model_a":"gpt-5-mini","model_b":"horizon-beta","name_a":"GPT-5 Mini","name_b":"Horizon Beta","provider_a":"openai","provider_b":"openrouter","similarity":0.9005},{"model_a":"mistral-medium-3.1","model_b":"mistral-small-2603","name_a":"Mistral Medium 3.1","name_b":"Mistral Small 4","provider_a":"mistral","provider_b":"mistral","similarity":0.8998},{"model_a":"mistral-large-2","model_b":"mistral-large-2512","name_a":"Mistral Large 2","name_b":"Mistral Large 3 2512","provider_a":"mistral","provider_b":"mistral","similarity":0.8929},{"model_a":"claude-opus-4.1","model_b":"claude-sonnet-4","name_a":"Claude Opus 4.1","name_b":"Claude Sonnet 4","provider_a":"anthropic","provider_b":"anthropic","similarity":0.8922},{"model_a":"mistral-large-2512","model_b":"mistral-medium-3.1","name_a":"Mistral Large 3 2512","name_b":"Mistral Medium 3.1","provider_a":"mistral","provider_b":"mistral","similarity":0.8906},{"model_a":"aurora-alpha","model_b":"mercury-2","name_a":"Aurora Alpha","name_b":"Inception: Mercury 2","provider_a":"openrouter","provider_b":"inception","similarity":0.8895},{"model_a":"mistral-small-2603","model_b":"mistral-small-creative","name_a":"Mistral Small 4","name_b":"Mistral Small Creative","provider_a":"mistral","provider_b":"mistral","similarity":0.8744},{"model_a":"gemma-3n-e4b-it","model_b":"glm-4.5-air","name_a":"Gemma 3n 4B","name_b":"Z.AI: GLM 4.5 Air","provider_a":"google","provider_b":"zhipu","similarity":0.8728},{"model_a":"gpt-oss-120b","model_b":"solar-pro-3-free","name_a":"GPT OSS 120B","name_b":"Solar Pro 3","provider_a":"openai","provider_b":"upstage","similarity":0.8727},{"model_a":"llama-4-scout","model_b":"mistral-nemo","name_a":"Llama 4 Scout","name_b":"Mistral Nemo","provider_a":"meta","provider_b":"mistral","similarity":0.872},{"model_a":"gpt-oss-120b","model_b":"mercury-2","name_a":"GPT OSS 120B","name_b":"Inception: Mercury 2","provider_a":"openai","provider_b":"inception","similarity":0.8682},{"model_a":"horizon-alpha","model_b":"horizon-beta","name_a":"Horizon Alpha","name_b":"Horizon Beta","provider_a":"openrouter","provider_b":"openrouter","similarity":0.868},{"model_a":"llama-4-maverick","model_b":"mistral-nemo","name_a":"Llama 4 Maverick","name_b":"Mistral Nemo","provider_a":"meta","provider_b":"mistral","similarity":0.8637},{"model_a":"qwen3-coder","model_b":"qwen3-coder-plus","name_a":"Qwen3 Coder","name_b":"Qwen3 Coder Plus","provider_a":"qwen","provider_b":"qwen","similarity":0.861},{"model_a":"gpt-5-pro","model_b":"horizon-alpha","name_a":"GPT-5 Pro","name_b":"Horizon Alpha","provider_a":"openai","provider_b":"openrouter","similarity":0.8592},{"model_a":"gpt-5.2","model_b":"gpt-5.2-chat","name_a":"GPT-5.2","name_b":"GPT-5.2 Chat","provider_a":"openai","provider_b":"openai","similarity":0.8516},{"model_a":"aurora-alpha","model_b":"gpt-oss-20b","name_a":"Aurora Alpha","name_b":"GPT OSS 20B","provider_a":"openrouter","provider_b":"openai","similarity":0.8511},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-9b","name_a":"Qwen: Qwen3.5 122B A10B","name_b":"Qwen3.5 9B","provider_a":"qwen","provider_b":"qwen","similarity":0.8466},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-flash-02-23","name_a":"Qwen: Qwen3.5 122B A10B","name_b":"Qwen: Qwen3.5 Flash","provider_a":"qwen","provider_b":"qwen","similarity":0.8451},{"model_a":"qwen3.5-9b","model_b":"qwen3.5-flash-02-23","name_a":"Qwen3.5 9B","name_b":"Qwen: Qwen3.5 Flash","provider_a":"qwen","provider_b":"qwen","similarity":0.838},{"model_a":"gemma-3n-e4b-it","model_b":"llama-4-scout","name_a":"Gemma 3n 4B","name_b":"Llama 4 Scout","provider_a":"google","provider_b":"meta","similarity":0.8367},{"model_a":"gemma-3n-e4b-it","model_b":"llama-4-maverick","name_a":"Gemma 3n 4B","name_b":"Llama 4 Maverick","provider_a":"google","provider_b":"meta","similarity":0.8365},{"model_a":"claude-4.5-sonnet","model_b":"claude-sonnet-4","name_a":"Claude Sonnet 4.5","name_b":"Claude Sonnet 4","provider_a":"anthropic","provider_b":"anthropic","similarity":0.8345},{"model_a":"qwen3.5-35b-a3b","model_b":"qwen3.5-flash-02-23","name_a":"Qwen: Qwen3.5 35B A3B","name_b":"Qwen: Qwen3.5 Flash","provider_a":"qwen","provider_b":"qwen","similarity":0.8322},{"model_a":"sherlock-dash-alpha","model_b":"sherlock-think-alpha","name_a":"Sherlock Dash Alpha","name_b":"Sherlock Think Alpha","provider_a":"openrouter","provider_b":"openrouter","similarity":0.8275},{"model_a":"qwen3.5-27b","model_b":"qwen3.5-flash-02-23","name_a":"Qwen: Qwen3.5 27B","name_b":"Qwen: Qwen3.5 Flash","provider_a":"qwen","provider_b":"qwen","similarity":0.8265},{"model_a":"qwen3.5-397b-a17b","model_b":"qwen3.5-flash-02-23","name_a":"Qwen: Qwen3.5 397B A17B","name_b":"Qwen: Qwen3.5 Flash","provider_a":"qwen","provider_b":"qwen","similarity":0.8265},{"model_a":"qwen-plus-2025-07-28","model_b":"qwen3-30b-a3b-instruct-2507","name_a":"Qwen Plus 0728","name_b":"Qwen: Qwen3 30B A3B Instruct 2507","provider_a":"qwen","provider_b":"qwen","similarity":0.8258},{"model_a":"mistral-large-2","model_b":"mistral-small-2603","name_a":"Mistral Large 2","name_b":"Mistral Small 4","provider_a":"mistral","provider_b":"mistral","similarity":0.8224},{"model_a":"cypher-alpha-free","model_b":"gpt-3.5-turbo","name_a":"Cypher Alpha (free)","name_b":"GPT-3.5 Turbo","provider_a":"openrouter","provider_b":"openai","similarity":0.8218},{"model_a":"aurora-alpha","model_b":"gpt-oss-120b","name_a":"Aurora Alpha","name_b":"GPT OSS 120B","provider_a":"openrouter","provider_b":"openai","similarity":0.8213},{"model_a":"claude-4.5-sonnet","model_b":"claude-opus-4.1","name_a":"Claude Sonnet 4.5","name_b":"Claude Opus 4.1","provider_a":"anthropic","provider_b":"anthropic","similarity":0.82},{"model_a":"mercury","model_b":"mercury-2","name_a":"Inception: Mercury","name_b":"Inception: Mercury 2","provider_a":"inception","provider_b":"inception","similarity":0.8183},{"model_a":"gemini-2.5-flash-lite-preview-06-17","model_b":"gemini-2.5-flash-preview-05-20-thinking","name_a":"Gemini 2.5 Flash Lite Preview 06-17","name_b":"Gemini 2.5 Flash Preview 05-20 (thinking)","provider_a":"google","provider_b":"google","similarity":0.8173},{"model_a":"gemini-2.0-flash-thinking-exp","model_b":"gemma-3-27b-it","name_a":"Gemini 2.0 Flash Thinking","name_b":"Gemma 3 27B","provider_a":"google","provider_b":"google","similarity":0.8172},{"model_a":"glm-5","model_b":"qwen3.5-flash-02-23","name_a":"Z.ai: GLM 5","name_b":"Qwen: Qwen3.5 Flash","provider_a":"zhipu","provider_b":"qwen","similarity":0.8141},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-35b-a3b","name_a":"Qwen: Qwen3.5 122B A10B","name_b":"Qwen: Qwen3.5 35B A3B","provider_a":"qwen","provider_b":"qwen","similarity":0.8136},{"model_a":"gemini-3-flash-preview","model_b":"glm-4.7","name_a":"Gemini 3 Flash Preview","name_b":"Z.AI: GLM 4.7","provider_a":"google","provider_b":"openrouter","similarity":0.8101},{"model_a":"gpt-5","model_b":"gpt-5-mini","name_a":"GPT-5","name_b":"GPT-5 Mini","provider_a":"openai","provider_b":"openai","similarity":0.8093},{"model_a":"gpt-5.1-codex-max","model_b":"o4-mini","name_a":"GPT-5.1 Codex Max","name_b":"OpenAI o4-mini","provider_a":"openai","provider_b":"openai","similarity":0.8093},{"model_a":"gpt-5.4","model_b":"gpt-5.4-pro","name_a":"GPT-5.4","name_b":"GPT-5.4 Pro","provider_a":"openai","provider_b":"openai","similarity":0.8092},{"model_a":"gemini-3-flash-preview","model_b":"qwen3.5-35b-a3b","name_a":"Gemini 3 Flash Preview","name_b":"Qwen: Qwen3.5 35B A3B","provider_a":"google","provider_b":"qwen","similarity":0.8049},{"model_a":"nova-2-lite-v1-free","model_b":"qwen3-30b-a3b-thinking-2507","name_a":"Amazon Nova 2 Lite","name_b":"Qwen3 30B A3B Thinking 2507","provider_a":"amazon","provider_b":"qwen","similarity":0.8046},{"model_a":"nova-2-lite-v1-free","model_b":"qwen3-coder-next","name_a":"Amazon Nova 2 Lite","name_b":"Qwen3 Coder Next","provider_a":"amazon","provider_b":"qwen","similarity":0.8028},{"model_a":"claude-sonnet-4","model_b":"qwen3-coder-plus","name_a":"Claude Sonnet 4","name_b":"Qwen3 Coder Plus","provider_a":"anthropic","provider_b":"qwen","similarity":0.8019},{"model_a":"deepseek-v3-03-24","model_b":"mistral-medium-3","name_a":"DeepSeek V3 (March 2024)","name_b":"Mistral Medium 3","provider_a":"deepseek","provider_b":"mistral","similarity":0.8004},{"model_a":"claude-opus-4.1","model_b":"qwen3-coder-plus","name_a":"Claude Opus 4.1","name_b":"Qwen3 Coder Plus","provider_a":"anthropic","provider_b":"qwen","similarity":0.7998},{"model_a":"claude-3.7-sonnet-thinking","model_b":"qwen3-coder","name_a":"Claude 3.7 Thinking Sonnet","name_b":"Qwen3 Coder","provider_a":"anthropic","provider_b":"qwen","similarity":0.799},{"model_a":"bert-nebulon-alpha","model_b":"nova-2-lite-v1-free","name_a":"Bert-Nebulon Alpha","name_b":"Amazon Nova 2 Lite","provider_a":"openrouter","provider_b":"amazon","similarity":0.7987},{"model_a":"gemini-2.0-flash-thinking-exp","model_b":"gemini-2.0-pro-exp","name_a":"Gemini 2.0 Flash Thinking","name_b":"Gemini 2.0 Pro Experimental","provider_a":"google","provider_b":"google","similarity":0.7969},{"model_a":"mistral-large-2","model_b":"mistral-small-creative","name_a":"Mistral Large 2","name_b":"Mistral Small Creative","provider_a":"mistral","provider_b":"mistral","similarity":0.7969},{"model_a":"pony-alpha","model_b":"qwen3.5-122b-a10b","name_a":"Pony Alpha","name_b":"Qwen: Qwen3.5 122B A10B","provider_a":"openrouter","provider_b":"qwen","similarity":0.7967},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-27b","name_a":"Qwen: Qwen3.5 122B A10B","name_b":"Qwen: Qwen3.5 27B","provider_a":"qwen","provider_b":"qwen","similarity":0.796},{"model_a":"qwen3-235b-a22b-thinking-2507","model_b":"qwen3-30b-a3b-thinking-2507","name_a":"Qwen: Qwen3 235B A22B Thinking 2507","name_b":"Qwen3 30B A3B Thinking 2507","provider_a":"qwen","provider_b":"qwen","similarity":0.7919},{"model_a":"gpt-5-mini","model_b":"horizon-alpha","name_a":"GPT-5 Mini","name_b":"Horizon Alpha","provider_a":"openai","provider_b":"openrouter","similarity":0.7917},{"model_a":"gpt-5-mini","model_b":"gpt-5-nano","name_a":"GPT-5 Mini","name_b":"GPT-5 Nano","provider_a":"openai","provider_b":"openai","similarity":0.7895},{"model_a":"cypher-alpha-free","model_b":"horizon-alpha","name_a":"Cypher Alpha (free)","name_b":"Horizon Alpha","provider_a":"openrouter","provider_b":"openrouter","similarity":0.7872},{"model_a":"qwen3.5-35b-a3b","model_b":"qwen3.5-9b","name_a":"Qwen: Qwen3.5 35B A3B","name_b":"Qwen3.5 9B","provider_a":"qwen","provider_b":"qwen","similarity":0.7872},{"model_a":"claude-sonnet-4","model_b":"qwen3-coder","name_a":"Claude Sonnet 4","name_b":"Qwen3 Coder","provider_a":"anthropic","provider_b":"qwen","similarity":0.7869},{"model_a":"qwen-plus-2025-07-28-thinking","model_b":"qwen3-30b-a3b-thinking-2507","name_a":"Qwen Plus 0728 (thinking)","name_b":"Qwen3 30B A3B Thinking 2507","provider_a":"qwen","provider_b":"qwen","similarity":0.7851},{"model_a":"minimax-m1","model_b":"mistral-large","name_a":"MiniMax M1","name_b":"Mistral Large","provider_a":"minimax","provider_b":"mistral","similarity":0.7838},{"model_a":"claude-opus-4.6","model_b":"claude-sonnet-4.6","name_a":"Claude Opus 4.6","name_b":"Claude Sonnet 4.6","provider_a":"anthropic","provider_b":"anthropic","similarity":0.783},{"model_a":"devstral-small","model_b":"gemma-3n-e2b-it-free","name_a":"Mistral Devstral Small 1.1","name_b":"Google: Gemma 3n 2B","provider_a":"mistral","provider_b":"google","similarity":0.7829},{"model_a":"qwen-plus-2025-07-28-thinking","model_b":"qwen3-next-80b-a3b-thinking","name_a":"Qwen Plus 0728 (thinking)","name_b":"Qwen3 Next 80B A3B Thinking","provider_a":"qwen","provider_b":"qwen","similarity":0.7829},{"model_a":"gpt-5.4-mini","model_b":"gpt-5.4-pro","name_a":"GPT-5.4 Mini","name_b":"GPT-5.4 Pro","provider_a":"openai","provider_b":"openai","similarity":0.7826},{"model_a":"claude-3-opus","model_b":"gemini-2.5-flash-lite-preview-06-17","name_a":"Claude 3 Opus","name_b":"Gemini 2.5 Flash Lite Preview 06-17","provider_a":"anthropic","provider_b":"google","similarity":0.7818},{"model_a":"glm-4.7","model_b":"glm-5","name_a":"Z.AI: GLM 4.7","name_b":"Z.ai: GLM 5","provider_a":"openrouter","provider_b":"zhipu","similarity":0.7818},{"model_a":"bert-nebulon-alpha","model_b":"qwen3-30b-a3b-thinking-2507","name_a":"Bert-Nebulon Alpha","name_b":"Qwen3 30B A3B Thinking 2507","provider_a":"openrouter","provider_b":"qwen","similarity":0.7814},{"model_a":"bert-nebulon-alpha","model_b":"devstral-2512-free","name_a":"Bert-Nebulon Alpha","name_b":"Mistral: Devstral 2 2512","provider_a":"openrouter","provider_b":"mistral","similarity":0.7812},{"model_a":"pony-alpha","model_b":"qwen3.5-35b-a3b","name_a":"Pony Alpha","name_b":"Qwen: Qwen3.5 35B A3B","provider_a":"openrouter","provider_b":"qwen","similarity":0.7799},{"model_a":"claude-opus-4.1","model_b":"qwen3-coder","name_a":"Claude Opus 4.1","name_b":"Qwen3 Coder","provider_a":"anthropic","provider_b":"qwen","similarity":0.7793},{"model_a":"grok-3","model_b":"grok-4","name_a":"Grok 3","name_b":"xAI: Grok 4","provider_a":"xai","provider_b":"xai","similarity":0.778},{"model_a":"gemini-2.5-flash-preview","model_b":"gemini-2.5-flash-preview-thinking","name_a":"Gemini 2.5 Flash Preview","name_b":"Gemini 2.5 Flash Preview (thinking)","provider_a":"google","provider_b":"google","similarity":0.7777},{"model_a":"mimo-v2-flash","model_b":"pony-alpha","name_a":"MiMo-V2-Flash","name_b":"Pony Alpha","provider_a":"xiaomi","provider_b":"openrouter","similarity":0.777},{"model_a":"pony-alpha","model_b":"qwen3.5-flash-02-23","name_a":"Pony Alpha","name_b":"Qwen: Qwen3.5 Flash","provider_a":"openrouter","provider_b":"qwen","similarity":0.7769},{"model_a":"glm-4.5-air","model_b":"llama-4-maverick","name_a":"Z.AI: GLM 4.5 Air","name_b":"Llama 4 Maverick","provider_a":"zhipu","provider_b":"meta","similarity":0.7763},{"model_a":"mistral-large","model_b":"mistral-large-2","name_a":"Mistral Large","name_b":"Mistral Large 2","provider_a":"mistral","provider_b":"mistral","similarity":0.7742},{"model_a":"qwen-plus-2025-07-28-thinking","model_b":"qwen3-235b-a22b-thinking-2507","name_a":"Qwen Plus 0728 (thinking)","name_b":"Qwen: Qwen3 235B A22B Thinking 2507","provider_a":"qwen","provider_b":"qwen","similarity":0.774},{"model_a":"glm-4.7","model_b":"qwen3.5-flash-02-23","name_a":"Z.AI: GLM 4.7","name_b":"Qwen: Qwen3.5 Flash","provider_a":"openrouter","provider_b":"qwen","similarity":0.7734},{"model_a":"glm-5","model_b":"qwen3.5-35b-a3b","name_a":"Z.ai: GLM 5","name_b":"Qwen: Qwen3.5 35B A3B","provider_a":"zhipu","provider_b":"qwen","similarity":0.7734},{"model_a":"kimi-k2-0905","model_b":"o3","name_a":"MoonshotAI: Kimi K2 0905","name_b":"OpenAI o3","provider_a":"moonshotai","provider_b":"openai","similarity":0.7728},{"model_a":"qwen3-30b-a3b-thinking-2507","model_b":"qwen3-coder-next","name_a":"Qwen3 30B A3B Thinking 2507","name_b":"Qwen3 Coder Next","provider_a":"qwen","provider_b":"qwen","similarity":0.7717},{"model_a":"claude-3.7-sonnet-thinking","model_b":"qwen3-coder-plus","name_a":"Claude 3.7 Thinking Sonnet","name_b":"Qwen3 Coder Plus","provider_a":"anthropic","provider_b":"qwen","similarity":0.7705},{"model_a":"gemini-2.5-pro-preview-06-05","model_b":"glm-4.6","name_a":"Gemini 2.5 Pro Preview 06-05","name_b":"Z.AI: GLM 4.6","provider_a":"google","provider_b":"zhipu","similarity":0.7689},{"model_a":"gemini-3-flash-preview","model_b":"qwen3.5-397b-a17b","name_a":"Gemini 3 Flash Preview","name_b":"Qwen: Qwen3.5 397B A17B","provider_a":"google","provider_b":"qwen","similarity":0.7689},{"model_a":"nova-2-lite-v1-free","model_b":"qwen3-30b-a3b-instruct-2507","name_a":"Amazon Nova 2 Lite","name_b":"Qwen: Qwen3 30B A3B Instruct 2507","provider_a":"amazon","provider_b":"qwen","similarity":0.7662},{"model_a":"gpt-5-mini","model_b":"gpt-5-pro","name_a":"GPT-5 Mini","name_b":"GPT-5 Pro","provider_a":"openai","provider_b":"openai","similarity":0.7641},{"model_a":"gemini-3-flash-preview","model_b":"qwen3.5-flash-02-23","name_a":"Gemini 3 Flash Preview","name_b":"Qwen: Qwen3.5 Flash","provider_a":"google","provider_b":"qwen","similarity":0.7608},{"model_a":"qwen3-coder-flash","model_b":"qwen3-coder-plus","name_a":"Qwen3 Coder Flash","name_b":"Qwen3 Coder Plus","provider_a":"qwen","provider_b":"qwen","similarity":0.7593}],"top_different_pairs":[{"model_a":"cypher-alpha-free","model_b":"mistral-small-2603","name_a":"Cypher Alpha (free)","name_b":"Mistral Small 4","provider_a":"openrouter","provider_b":"mistral","similarity":-0.7327},{"model_a":"gpt-5.4-nano","model_b":"trinity-large-preview-free","name_a":"GPT-5.4 Nano","name_b":"Trinity Large Preview","provider_a":"openai","provider_b":"arcee-ai","similarity":-0.724},{"model_a":"devstral-medium","model_b":"mimo-v2-pro","name_a":"Mistral Devstral Medium","name_b":"MiMo-V2-Pro","provider_a":"mistral","provider_b":"xiaomi","similarity":-0.719},{"model_a":"gpt-3.5-turbo","model_b":"minimax-m1","name_a":"GPT-3.5 Turbo","name_b":"MiniMax M1","provider_a":"openai","provider_b":"minimax","similarity":-0.7127},{"model_a":"gpt-5-pro","model_b":"mistral-small-2603","name_a":"GPT-5 Pro","name_b":"Mistral Small 4","provider_a":"openai","provider_b":"mistral","similarity":-0.7104},{"model_a":"gpt-3.5-turbo","model_b":"mistral-small-2603","name_a":"GPT-3.5 Turbo","name_b":"Mistral Small 4","provider_a":"openai","provider_b":"mistral","similarity":-0.71},{"model_a":"horizon-alpha","model_b":"mistral-small-2603","name_a":"Horizon Alpha","name_b":"Mistral Small 4","provider_a":"openrouter","provider_b":"mistral","similarity":-0.7072},{"model_a":"mistral-small-2603","model_b":"o4-mini","name_a":"Mistral Small 4","name_b":"OpenAI o4-mini","provider_a":"mistral","provider_b":"openai","similarity":-0.6991},{"model_a":"gpt-5-pro","model_b":"mistral-medium-3","name_a":"GPT-5 Pro","name_b":"Mistral Medium 3","provider_a":"openai","provider_b":"mistral","similarity":-0.6937},{"model_a":"cypher-alpha-free","model_b":"deepseek-v3-03-24","name_a":"Cypher Alpha (free)","name_b":"DeepSeek V3 (March 2024)","provider_a":"openrouter","provider_b":"deepseek","similarity":-0.6886},{"model_a":"devstral-small","model_b":"mimo-v2-pro","name_a":"Mistral Devstral Small 1.1","name_b":"MiMo-V2-Pro","provider_a":"mistral","provider_b":"xiaomi","similarity":-0.6877},{"model_a":"minimax-m1","model_b":"trinity-large-preview-free","name_a":"MiniMax M1","name_b":"Trinity Large Preview","provider_a":"minimax","provider_b":"arcee-ai","similarity":-0.6873},{"model_a":"cypher-alpha-free","model_b":"mistral-medium-3.1","name_a":"Cypher Alpha (free)","name_b":"Mistral Medium 3.1","provider_a":"openrouter","provider_b":"mistral","similarity":-0.687},{"model_a":"cypher-alpha-free","model_b":"mistral-large-2","name_a":"Cypher Alpha (free)","name_b":"Mistral Large 2","provider_a":"openrouter","provider_b":"mistral","similarity":-0.6857},{"model_a":"mistral-large-2","model_b":"trinity-large-preview-free","name_a":"Mistral Large 2","name_b":"Trinity Large Preview","provider_a":"mistral","provider_b":"arcee-ai","similarity":-0.6835},{"model_a":"gpt-3.5-turbo","model_b":"mistral-large-2","name_a":"GPT-3.5 Turbo","name_b":"Mistral Large 2","provider_a":"openai","provider_b":"mistral","similarity":-0.6828},{"model_a":"cypher-alpha-free","model_b":"mistral-small-creative","name_a":"Cypher Alpha (free)","name_b":"Mistral Small Creative","provider_a":"openrouter","provider_b":"mistral","similarity":-0.6752},{"model_a":"glm-4.5-air","model_b":"gpt-5.1-chat","name_a":"Z.AI: GLM 4.5 Air","name_b":"GPT-5.1 Chat","provider_a":"zhipu","provider_b":"openai","similarity":-0.675},{"model_a":"gpt-5-pro","model_b":"mistral-medium-3.1","name_a":"GPT-5 Pro","name_b":"Mistral Medium 3.1","provider_a":"openai","provider_b":"mistral","similarity":-0.673},{"model_a":"gpt-5.1-codex-max","model_b":"intellect-3","name_a":"GPT-5.1 Codex Max","name_b":"INTELLECT-3","provider_a":"openai","provider_b":"openrouter","similarity":-0.6707},{"model_a":"mistral-large-2","model_b":"o4-mini","name_a":"Mistral Large 2","name_b":"OpenAI o4-mini","provider_a":"mistral","provider_b":"openai","similarity":-0.6686},{"model_a":"minimax-m2.1","model_b":"qwq-32b","name_a":"MiniMax: MiniMax M2.1","name_b":"QwQ 32B","provider_a":"minimax","provider_b":"qwen","similarity":-0.6642},{"model_a":"gpt-3.5-turbo","model_b":"mistral-small-creative","name_a":"GPT-3.5 Turbo","name_b":"Mistral Small Creative","provider_a":"openai","provider_b":"mistral","similarity":-0.6641},{"model_a":"deepseek-v3-03-24","model_b":"gpt-3.5-turbo","name_a":"DeepSeek V3 (March 2024)","name_b":"GPT-3.5 Turbo","provider_a":"deepseek","provider_b":"openai","similarity":-0.6627},{"model_a":"claude-3-sonnet","model_b":"gpt-5.3-codex","name_a":"Claude 3 Sonnet","name_b":"GPT-5.3-Codex","provider_a":"anthropic","provider_b":"openai","similarity":-0.6598},{"model_a":"nemotron-nano-9b-v2","model_b":"o4-mini","name_a":"NVIDIA Nemotron Nano 9B V2","name_b":"OpenAI o4-mini","provider_a":"nvidia","provider_b":"openai","similarity":-0.6597},{"model_a":"gpt-3.5-turbo","model_b":"mistral-large-2512","name_a":"GPT-3.5 Turbo","name_b":"Mistral Large 3 2512","provider_a":"openai","provider_b":"mistral","similarity":-0.6591},{"model_a":"gemini-2.5-flash-preview","model_b":"gpt-5.2-pro","name_a":"Gemini 2.5 Flash Preview","name_b":"GPT-5.2 Pro","provider_a":"google","provider_b":"openai","similarity":-0.6532},{"model_a":"cypher-alpha-free","model_b":"mistral-large-2512","name_a":"Cypher Alpha (free)","name_b":"Mistral Large 3 2512","provider_a":"openrouter","provider_b":"mistral","similarity":-0.6491},{"model_a":"cypher-alpha-free","model_b":"qwen-plus-2025-07-28-thinking","name_a":"Cypher Alpha (free)","name_b":"Qwen Plus 0728 (thinking)","provider_a":"openrouter","provider_b":"qwen","similarity":-0.6472},{"model_a":"deepseek-chat-v3.1","model_b":"mimo-v2-pro","name_a":"DeepSeek V3.1","name_b":"MiMo-V2-Pro","provider_a":"deepseek","provider_b":"xiaomi","similarity":-0.6462},{"model_a":"gpt-3.5-turbo","model_b":"mistral-medium-3.1","name_a":"GPT-3.5 Turbo","name_b":"Mistral Medium 3.1","provider_a":"openai","provider_b":"mistral","similarity":-0.6377},{"model_a":"cypher-alpha-free","model_b":"mistral-medium-3","name_a":"Cypher Alpha (free)","name_b":"Mistral Medium 3","provider_a":"openrouter","provider_b":"mistral","similarity":-0.6316},{"model_a":"mistral-large-2","model_b":"palm-2-chat-bison","name_a":"Mistral Large 2","name_b":"PaLM 2 Chat","provider_a":"mistral","provider_b":"google","similarity":-0.6298},{"model_a":"claude-opus-4.5","model_b":"gemini-3.1-pro-preview","name_a":"Claude Opus 4.5","name_b":"Gemini 3.1 Pro Preview","provider_a":"anthropic","provider_b":"google","similarity":-0.6296},{"model_a":"claude-3.7-sonnet","model_b":"mistral-small-creative","name_a":"Claude 3.7 Sonnet","name_b":"Mistral Small Creative","provider_a":"anthropic","provider_b":"mistral","similarity":-0.6208},{"model_a":"mistral-small-2603","model_b":"o4-mini-high","name_a":"Mistral Small 4","name_b":"OpenAI o4 Mini High","provider_a":"mistral","provider_b":"openai","similarity":-0.6171},{"model_a":"horizon-alpha","model_b":"mistral-medium-3.1","name_a":"Horizon Alpha","name_b":"Mistral Medium 3.1","provider_a":"openrouter","provider_b":"mistral","similarity":-0.615},{"model_a":"mistral-small-2603","model_b":"trinity-large-preview-free","name_a":"Mistral Small 4","name_b":"Trinity Large Preview","provider_a":"mistral","provider_b":"arcee-ai","similarity":-0.6138},{"model_a":"glm-5-turbo","model_b":"tng-r1t-chimera-free","name_a":"GLM 5 Turbo","name_b":"TNG R1T Chimera","provider_a":"z-ai","provider_b":"openrouter","similarity":-0.6098},{"model_a":"intellect-3","model_b":"kimi-linear-48b-a3b-instruct","name_a":"INTELLECT-3","name_b":"Kimi Linear 48B A3B Instruct","provider_a":"openrouter","provider_b":"moonshotai","similarity":-0.6093},{"model_a":"claude-3-haiku","model_b":"gpt-5.2","name_a":"Claude 3 Haiku","name_b":"GPT-5.2","provider_a":"anthropic","provider_b":"openai","similarity":-0.6088},{"model_a":"deepseek-v3.2","model_b":"o4-mini","name_a":"DeepSeek V3.2","name_b":"OpenAI o4-mini","provider_a":"deepseek","provider_b":"openai","similarity":-0.6088},{"model_a":"cypher-alpha-free","model_b":"minimax-m1","name_a":"Cypher Alpha (free)","name_b":"MiniMax M1","provider_a":"openrouter","provider_b":"minimax","similarity":-0.608},{"model_a":"golden-gate-claude","model_b":"minimax-m1","name_a":"Golden Gate Claude","name_b":"MiniMax M1","provider_a":"anthropic","provider_b":"minimax","similarity":-0.6078},{"model_a":"deepseek-v3-03-24","model_b":"horizon-alpha","name_a":"DeepSeek V3 (March 2024)","name_b":"Horizon Alpha","provider_a":"deepseek","provider_b":"openrouter","similarity":-0.6076},{"model_a":"gemma-3n-e2b-it-free","model_b":"gpt-5.1-chat","name_a":"Google: Gemma 3n 2B","name_b":"GPT-5.1 Chat","provider_a":"google","provider_b":"openai","similarity":-0.6047},{"model_a":"claude-3.7-sonnet","model_b":"nemotron-3-super-120b-a12b-free","name_a":"Claude 3.7 Sonnet","name_b":"NVIDIA Nemotron 3 Super (free)","provider_a":"anthropic","provider_b":"nvidia","similarity":-0.6022},{"model_a":"glm-4.7","model_b":"gpt-4.1-nano","name_a":"Z.AI: GLM 4.7","name_b":"GPT-4.1 Nano","provider_a":"openrouter","provider_b":"openai","similarity":-0.6018},{"model_a":"claude-3-sonnet","model_b":"tng-r1t-chimera-free","name_a":"Claude 3 Sonnet","name_b":"TNG R1T Chimera","provider_a":"anthropic","provider_b":"openrouter","similarity":-0.6002}],"clone_clusters":[{"models":[{"id":"mistral-large-2512","name":"Mistral Large 3 2512","provider":"mistral","inputPrice":null,"outputPrice":null,"family":null,"size":"xlarge"},{"id":"mistral-medium-3.1","name":"Mistral Medium 3.1","provider":"mistral","inputPrice":0.4,"outputPrice":2,"family":"Mistral","size":"large"},{"id":"mistral-small-2603","name":"Mistral Small 4","provider":"mistral","inputPrice":0.15,"outputPrice":0.6,"family":null,"size":"small"},{"id":"mistral-small-creative","name":"Mistral Small Creative","provider":"mistral","inputPrice":0.1,"outputPrice":0.3,"family":null,"size":"small"}],"avg_similarity":0.9034,"size":4},{"models":[{"id":"aurora-alpha","name":"Aurora Alpha","provider":"openrouter","inputPrice":0,"outputPrice":0,"family":null,"size":"large"},{"id":"mercury-2","name":"Inception: Mercury 2","provider":"inception","inputPrice":0.25,"outputPrice":0.75,"family":"Mercury","size":"medium"},{"id":"solar-pro-3-free","name":"Solar Pro 3","provider":"upstage","inputPrice":0,"outputPrice":0,"family":null,"size":"large"}],"avg_similarity":0.9076,"size":3},{"models":[{"id":"devstral-medium","name":"Mistral Devstral Medium","provider":"mistral","inputPrice":0.4,"outputPrice":2,"family":null,"size":"medium"},{"id":"devstral-small","name":"Mistral Devstral Small 1.1","provider":"mistral","inputPrice":0.1,"outputPrice":0.3,"family":null,"size":"small"}],"avg_similarity":0.9568,"size":2},{"models":[{"id":"gpt-5","name":"GPT-5","provider":"openai","inputPrice":1.25,"outputPrice":10,"family":"GPT","size":"xlarge"},{"id":"gpt-5-nano","name":"GPT-5 Nano","provider":"openai","inputPrice":null,"outputPrice":null,"family":null,"size":"small"}],"avg_similarity":0.9116,"size":2},{"models":[{"id":"gpt-5-mini","name":"GPT-5 Mini","provider":"openai","inputPrice":0.25,"outputPrice":2,"family":null,"size":"medium"},{"id":"horizon-beta","name":"Horizon Beta","provider":"openrouter","inputPrice":0,"outputPrice":0,"family":null,"size":"large"}],"avg_similarity":0.9005,"size":2},{"models":[{"id":"gpt-5.4","name":"GPT-5.4","provider":"openai","inputPrice":2.5,"outputPrice":15,"family":"GPT-5","size":"xlarge"},{"id":"gpt-5.4-mini","name":"GPT-5.4 Mini","provider":"openai","inputPrice":0.75,"outputPrice":4.5,"family":"GPT-5","size":"medium"}],"avg_similarity":0.9328,"size":2},{"models":[{"id":"llama-4-maverick","name":"Llama 4 Maverick","provider":"meta","inputPrice":1.5,"outputPrice":2.5,"family":"Llama","size":"xlarge"},{"id":"llama-4-scout","name":"Llama 4 Scout","provider":"meta","inputPrice":0.25,"outputPrice":0.5,"family":"Llama","size":"medium"}],"avg_similarity":0.919,"size":2},{"models":[{"id":"qwen3-coder","name":"Qwen3 Coder","provider":"qwen","inputPrice":0.22,"outputPrice":0.95,"family":"Qwen","size":"xlarge"},{"id":"qwen3-coder-flash","name":"Qwen3 Coder Flash","provider":"qwen","inputPrice":0.3,"outputPrice":1.5,"family":null,"size":"medium"}],"avg_similarity":0.9556,"size":2},{"models":[{"id":"qwen3.5-27b","name":"Qwen: Qwen3.5 27B","provider":"qwen","inputPrice":0.3,"outputPrice":2.4,"family":"Qwen","size":"medium"},{"id":"qwen3.5-35b-a3b","name":"Qwen: Qwen3.5 35B A3B","provider":"qwen","inputPrice":0.25,"outputPrice":2,"family":"Qwen","size":"medium"}],"avg_similarity":0.911,"size":2}],"cross_provider_twins":[{"model_a":"mercury-2","model_b":"solar-pro-3-free","similarity":0.9261,"provider_a":"inception","provider_b":"upstage","name_a":"Inception: Mercury 2","name_b":"Solar Pro 3"},{"model_a":"aurora-alpha","model_b":"solar-pro-3-free","similarity":0.907,"provider_a":"openrouter","provider_b":"upstage","name_a":"Aurora Alpha","name_b":"Solar Pro 3"},{"model_a":"gpt-5-mini","model_b":"horizon-beta","similarity":0.9005,"provider_a":"openai","provider_b":"openrouter","name_a":"GPT-5 Mini","name_b":"Horizon Beta"},{"model_a":"aurora-alpha","model_b":"mercury-2","similarity":0.8895,"provider_a":"openrouter","provider_b":"inception","name_a":"Aurora Alpha","name_b":"Inception: Mercury 2"},{"model_a":"gemma-3n-e4b-it","model_b":"glm-4.5-air","similarity":0.8728,"provider_a":"google","provider_b":"zhipu","name_a":"Gemma 3n 4B","name_b":"Z.AI: GLM 4.5 Air"},{"model_a":"gpt-oss-120b","model_b":"solar-pro-3-free","similarity":0.8727,"provider_a":"openai","provider_b":"upstage","name_a":"GPT OSS 120B","name_b":"Solar Pro 3"},{"model_a":"llama-4-scout","model_b":"mistral-nemo","similarity":0.872,"provider_a":"meta","provider_b":"mistral","name_a":"Llama 4 Scout","name_b":"Mistral Nemo"},{"model_a":"gpt-oss-120b","model_b":"mercury-2","similarity":0.8682,"provider_a":"openai","provider_b":"inception","name_a":"GPT OSS 120B","name_b":"Inception: Mercury 2"},{"model_a":"llama-4-maverick","model_b":"mistral-nemo","similarity":0.8637,"provider_a":"meta","provider_b":"mistral","name_a":"Llama 4 Maverick","name_b":"Mistral Nemo"},{"model_a":"gpt-5-pro","model_b":"horizon-alpha","similarity":0.8592,"provider_a":"openai","provider_b":"openrouter","name_a":"GPT-5 Pro","name_b":"Horizon Alpha"},{"model_a":"aurora-alpha","model_b":"gpt-oss-20b","similarity":0.8511,"provider_a":"openrouter","provider_b":"openai","name_a":"Aurora Alpha","name_b":"GPT OSS 20B"},{"model_a":"gemma-3n-e4b-it","model_b":"llama-4-scout","similarity":0.8367,"provider_a":"google","provider_b":"meta","name_a":"Gemma 3n 4B","name_b":"Llama 4 Scout"},{"model_a":"gemma-3n-e4b-it","model_b":"llama-4-maverick","similarity":0.8365,"provider_a":"google","provider_b":"meta","name_a":"Gemma 3n 4B","name_b":"Llama 4 Maverick"},{"model_a":"cypher-alpha-free","model_b":"gpt-3.5-turbo","similarity":0.8218,"provider_a":"openrouter","provider_b":"openai","name_a":"Cypher Alpha (free)","name_b":"GPT-3.5 Turbo"},{"model_a":"aurora-alpha","model_b":"gpt-oss-120b","similarity":0.8213,"provider_a":"openrouter","provider_b":"openai","name_a":"Aurora Alpha","name_b":"GPT OSS 120B"},{"model_a":"glm-5","model_b":"qwen3.5-flash-02-23","similarity":0.8141,"provider_a":"zhipu","provider_b":"qwen","name_a":"Z.ai: GLM 5","name_b":"Qwen: Qwen3.5 Flash"},{"model_a":"gemini-3-flash-preview","model_b":"glm-4.7","similarity":0.8101,"provider_a":"google","provider_b":"openrouter","name_a":"Gemini 3 Flash Preview","name_b":"Z.AI: GLM 4.7"},{"model_a":"gemini-3-flash-preview","model_b":"qwen3.5-35b-a3b","similarity":0.8049,"provider_a":"google","provider_b":"qwen","name_a":"Gemini 3 Flash Preview","name_b":"Qwen: Qwen3.5 35B A3B"},{"model_a":"nova-2-lite-v1-free","model_b":"qwen3-30b-a3b-thinking-2507","similarity":0.8046,"provider_a":"amazon","provider_b":"qwen","name_a":"Amazon Nova 2 Lite","name_b":"Qwen3 30B A3B Thinking 2507"},{"model_a":"nova-2-lite-v1-free","model_b":"qwen3-coder-next","similarity":0.8028,"provider_a":"amazon","provider_b":"qwen","name_a":"Amazon Nova 2 Lite","name_b":"Qwen3 Coder Next"},{"model_a":"claude-sonnet-4","model_b":"qwen3-coder-plus","similarity":0.8019,"provider_a":"anthropic","provider_b":"qwen","name_a":"Claude Sonnet 4","name_b":"Qwen3 Coder Plus"},{"model_a":"deepseek-v3-03-24","model_b":"mistral-medium-3","similarity":0.8004,"provider_a":"deepseek","provider_b":"mistral","name_a":"DeepSeek V3 (March 2024)","name_b":"Mistral Medium 3"},{"model_a":"claude-opus-4.1","model_b":"qwen3-coder-plus","similarity":0.7998,"provider_a":"anthropic","provider_b":"qwen","name_a":"Claude Opus 4.1","name_b":"Qwen3 Coder Plus"},{"model_a":"claude-3.7-sonnet-thinking","model_b":"qwen3-coder","similarity":0.799,"provider_a":"anthropic","provider_b":"qwen","name_a":"Claude 3.7 Thinking Sonnet","name_b":"Qwen3 Coder"},{"model_a":"bert-nebulon-alpha","model_b":"nova-2-lite-v1-free","similarity":0.7987,"provider_a":"openrouter","provider_b":"amazon","name_a":"Bert-Nebulon Alpha","name_b":"Amazon Nova 2 Lite"},{"model_a":"pony-alpha","model_b":"qwen3.5-122b-a10b","similarity":0.7967,"provider_a":"openrouter","provider_b":"qwen","name_a":"Pony Alpha","name_b":"Qwen: Qwen3.5 122B A10B"},{"model_a":"gpt-5-mini","model_b":"horizon-alpha","similarity":0.7917,"provider_a":"openai","provider_b":"openrouter","name_a":"GPT-5 Mini","name_b":"Horizon Alpha"},{"model_a":"claude-sonnet-4","model_b":"qwen3-coder","similarity":0.7869,"provider_a":"anthropic","provider_b":"qwen","name_a":"Claude Sonnet 4","name_b":"Qwen3 Coder"},{"model_a":"minimax-m1","model_b":"mistral-large","similarity":0.7838,"provider_a":"minimax","provider_b":"mistral","name_a":"MiniMax M1","name_b":"Mistral Large"},{"model_a":"devstral-small","model_b":"gemma-3n-e2b-it-free","similarity":0.7829,"provider_a":"mistral","provider_b":"google","name_a":"Mistral Devstral Small 1.1","name_b":"Google: Gemma 3n 2B"}],"price_arbitrage":[{"similarity":0.7818,"cheap_model":{"id":"gemini-2.5-flash-lite-preview-06-17","name":"Gemini 2.5 Flash Lite Preview 06-17","provider":"google","input_price":0.1,"output_price":0.4},"expensive_model":{"id":"claude-3-opus","name":"Claude 3 Opus","provider":"anthropic","input_price":15,"output_price":75},"price_ratio":184.62,"savings_pct":99},{"similarity":0.7969,"cheap_model":{"id":"mistral-small-creative","name":"Mistral Small Creative","provider":"mistral","input_price":0.1,"output_price":0.3},"expensive_model":{"id":"mistral-large-2","name":"Mistral Large 2","provider":"mistral","input_price":8,"output_price":24},"price_ratio":80,"savings_pct":99},{"similarity":0.7793,"cheap_model":{"id":"qwen3-coder","name":"Qwen3 Coder","provider":"qwen","input_price":0.22,"output_price":0.95},"expensive_model":{"id":"claude-opus-4.1","name":"Claude Opus 4.1","provider":"anthropic","input_price":15,"output_price":75},"price_ratio":78.18,"savings_pct":99},{"similarity":0.7641,"cheap_model":{"id":"gpt-5-mini","name":"GPT-5 Mini","provider":"openai","input_price":0.25,"output_price":2},"expensive_model":{"id":"gpt-5-pro","name":"GPT-5 Pro","provider":"openai","input_price":15,"output_price":120},"price_ratio":60,"savings_pct":98},{"similarity":0.8224,"cheap_model":{"id":"mistral-small-2603","name":"Mistral Small 4","provider":"mistral","input_price":0.15,"output_price":0.6},"expensive_model":{"id":"mistral-large-2","name":"Mistral Large 2","provider":"mistral","input_price":8,"output_price":24},"price_ratio":41.03,"savings_pct":98},{"similarity":0.7826,"cheap_model":{"id":"gpt-5.4-mini","name":"GPT-5.4 Mini","provider":"openai","input_price":0.75,"output_price":4.5},"expensive_model":{"id":"gpt-5.4-pro","name":"GPT-5.4 Pro","provider":"openai","input_price":30,"output_price":180},"price_ratio":40,"savings_pct":98},{"similarity":0.8637,"cheap_model":{"id":"mistral-nemo","name":"Mistral Nemo","provider":"mistral","input_price":0.03,"output_price":0.07},"expensive_model":{"id":"llama-4-maverick","name":"Llama 4 Maverick","provider":"meta","input_price":1.5,"output_price":2.5},"price_ratio":37.5,"savings_pct":97},{"similarity":0.799,"cheap_model":{"id":"qwen3-coder","name":"Qwen3 Coder","provider":"qwen","input_price":0.22,"output_price":0.95},"expensive_model":{"id":"claude-3.7-sonnet-thinking","name":"Claude 3.7 Thinking Sonnet","provider":"anthropic","input_price":6,"output_price":30},"price_ratio":31.27,"savings_pct":97},{"similarity":0.7515,"cheap_model":{"id":"gemini-2.5-flash-preview-thinking","name":"Gemini 2.5 Flash Preview (thinking)","provider":"google","input_price":0.175,"output_price":3.5},"expensive_model":{"id":"claude-3-opus","name":"Claude 3 Opus","provider":"anthropic","input_price":15,"output_price":75},"price_ratio":22.48,"savings_pct":96},{"similarity":0.8466,"cheap_model":{"id":"qwen3.5-9b","name":"Qwen3.5 9B","provider":"qwen","input_price":0.1,"output_price":0.15},"expensive_model":{"id":"qwen3.5-122b-a10b","name":"Qwen: Qwen3.5 122B A10B","provider":"qwen","input_price":0.4,"output_price":3.2},"price_ratio":18.18,"savings_pct":95},{"similarity":0.7728,"cheap_model":{"id":"kimi-k2-0905","name":"MoonshotAI: Kimi K2 0905","provider":"moonshotai","input_price":0.6,"output_price":2.5},"expensive_model":{"id":"o3","name":"OpenAI o3","provider":"openai","input_price":10,"output_price":40},"price_ratio":16.05,"savings_pct":94},{"similarity":0.8183,"cheap_model":{"id":"mercury-2","name":"Inception: Mercury 2","provider":"inception","input_price":0.25,"output_price":0.75},"expensive_model":{"id":"mercury","name":"Inception: Mercury","provider":"inception","input_price":10,"output_price":10},"price_ratio":16,"savings_pct":94},{"similarity":0.7869,"cheap_model":{"id":"qwen3-coder","name":"Qwen3 Coder","provider":"qwen","input_price":0.22,"output_price":0.95},"expensive_model":{"id":"claude-sonnet-4","name":"Claude Sonnet 4","provider":"anthropic","input_price":3,"output_price":15},"price_ratio":15.64,"savings_pct":94},{"similarity":0.7838,"cheap_model":{"id":"minimax-m1","name":"MiniMax M1","provider":"minimax","input_price":0.3,"output_price":1.65},"expensive_model":{"id":"mistral-large","name":"Mistral Large","provider":"mistral","input_price":8,"output_price":24},"price_ratio":15.24,"savings_pct":93},{"similarity":0.7998,"cheap_model":{"id":"qwen3-coder-plus","name":"Qwen3 Coder Plus","provider":"qwen","input_price":1,"output_price":5},"expensive_model":{"id":"claude-opus-4.1","name":"Claude Opus 4.1","provider":"anthropic","input_price":15,"output_price":75},"price_ratio":15,"savings_pct":93},{"similarity":0.7851,"cheap_model":{"id":"qwen3-30b-a3b-thinking-2507","name":"Qwen3 30B A3B Thinking 2507","provider":"qwen","input_price":0.071,"output_price":0.285},"expensive_model":{"id":"qwen-plus-2025-07-28-thinking","name":"Qwen Plus 0728 (thinking)","provider":"qwen","input_price":0.4,"output_price":4},"price_ratio":13.39,"savings_pct":93},{"similarity":0.7592,"cheap_model":{"id":"mistral-medium-3.1","name":"Mistral Medium 3.1","provider":"mistral","input_price":0.4,"output_price":2},"expensive_model":{"id":"mistral-large-2","name":"Mistral Large 2","provider":"mistral","input_price":8,"output_price":24},"price_ratio":12.5,"savings_pct":92},{"similarity":0.8092,"cheap_model":{"id":"gpt-5.4","name":"GPT-5.4","provider":"openai","input_price":2.5,"output_price":15},"expensive_model":{"id":"gpt-5.4-pro","name":"GPT-5.4 Pro","provider":"openai","input_price":30,"output_price":180},"price_ratio":12,"savings_pct":92},{"similarity":0.7872,"cheap_model":{"id":"qwen3.5-9b","name":"Qwen3.5 9B","provider":"qwen","input_price":0.1,"output_price":0.15},"expensive_model":{"id":"qwen3.5-35b-a3b","name":"Qwen: Qwen3.5 35B A3B","provider":"qwen","input_price":0.25,"output_price":2},"price_ratio":11.36,"savings_pct":91},{"similarity":0.8265,"cheap_model":{"id":"qwen3.5-flash-02-23","name":"Qwen: Qwen3.5 Flash","provider":"qwen","input_price":0.1,"output_price":0.4},"expensive_model":{"id":"qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","provider":"qwen","input_price":0.6,"output_price":3.6},"price_ratio":8.77,"savings_pct":89},{"similarity":0.8173,"cheap_model":{"id":"gemini-2.5-flash-lite-preview-06-17","name":"Gemini 2.5 Flash Lite Preview 06-17","provider":"google","input_price":0.1,"output_price":0.4},"expensive_model":{"id":"gemini-2.5-flash-preview-05-20-thinking","name":"Gemini 2.5 Flash Preview 05-20 (thinking)","provider":"google","input_price":0.15,"output_price":3.5},"price_ratio":8.19,"savings_pct":88},{"similarity":0.8451,"cheap_model":{"id":"qwen3.5-flash-02-23","name":"Qwen: Qwen3.5 Flash","provider":"qwen","input_price":0.1,"output_price":0.4},"expensive_model":{"id":"qwen3.5-122b-a10b","name":"Qwen: Qwen3.5 122B A10B","provider":"qwen","input_price":0.4,"output_price":3.2},"price_ratio":7.69,"savings_pct":87},{"similarity":0.7608,"cheap_model":{"id":"qwen3.5-flash-02-23","name":"Qwen: Qwen3.5 Flash","provider":"qwen","input_price":0.1,"output_price":0.4},"expensive_model":{"id":"gemini-3-flash-preview","name":"Gemini 3 Flash Preview","provider":"google","input_price":0.5,"output_price":3},"price_ratio":7.31,"savings_pct":86},{"similarity":0.872,"cheap_model":{"id":"mistral-nemo","name":"Mistral Nemo","provider":"mistral","input_price":0.03,"output_price":0.07},"expensive_model":{"id":"llama-4-scout","name":"Llama 4 Scout","provider":"meta","input_price":0.25,"output_price":0.5},"price_ratio":7.29,"savings_pct":86},{"similarity":0.8004,"cheap_model":{"id":"deepseek-v3-03-24","name":"DeepSeek V3 (March 2024)","provider":"deepseek","input_price":0.14,"output_price":0.28},"expensive_model":{"id":"mistral-medium-3","name":"Mistral Medium 3","provider":"mistral","input_price":0.4,"output_price":2},"price_ratio":6.53,"savings_pct":85},{"similarity":0.8141,"cheap_model":{"id":"qwen3.5-flash-02-23","name":"Qwen: Qwen3.5 Flash","provider":"qwen","input_price":0.1,"output_price":0.4},"expensive_model":{"id":"glm-5","name":"Z.ai: GLM 5","provider":"zhipu","input_price":0.8,"output_price":2.56},"price_ratio":6.52,"savings_pct":85},{"similarity":0.774,"cheap_model":{"id":"qwen3-235b-a22b-thinking-2507","name":"Qwen: Qwen3 235B A22B Thinking 2507","provider":"qwen","input_price":0.11,"output_price":0.6},"expensive_model":{"id":"qwen-plus-2025-07-28-thinking","name":"Qwen Plus 0728 (thinking)","provider":"qwen","input_price":0.4,"output_price":4},"price_ratio":6.49,"savings_pct":85},{"similarity":0.9568,"cheap_model":{"id":"devstral-small","name":"Mistral Devstral Small 1.1","provider":"mistral","input_price":0.1,"output_price":0.3},"expensive_model":{"id":"devstral-medium","name":"Mistral Devstral Medium","provider":"mistral","input_price":0.4,"output_price":2},"price_ratio":6.4,"savings_pct":84},{"similarity":0.9081,"cheap_model":{"id":"mistral-small-creative","name":"Mistral Small Creative","provider":"mistral","input_price":0.1,"output_price":0.3},"expensive_model":{"id":"mistral-medium-3.1","name":"Mistral Medium 3.1","provider":"mistral","input_price":0.4,"output_price":2},"price_ratio":6.4,"savings_pct":84},{"similarity":0.7705,"cheap_model":{"id":"qwen3-coder-plus","name":"Qwen3 Coder Plus","provider":"qwen","input_price":1,"output_price":5},"expensive_model":{"id":"claude-3.7-sonnet-thinking","name":"Claude 3.7 Thinking Sonnet","provider":"anthropic","input_price":6,"output_price":30},"price_ratio":6,"savings_pct":83},{"similarity":0.8265,"cheap_model":{"id":"qwen3.5-flash-02-23","name":"Qwen: Qwen3.5 Flash","provider":"qwen","input_price":0.1,"output_price":0.4},"expensive_model":{"id":"qwen3.5-27b","name":"Qwen: Qwen3.5 27B","provider":"qwen","input_price":0.3,"output_price":2.4},"price_ratio":5.77,"savings_pct":83},{"similarity":0.7689,"cheap_model":{"id":"glm-4.6","name":"Z.AI: GLM 4.6","provider":"zhipu","input_price":0.4,"output_price":1.75},"expensive_model":{"id":"gemini-2.5-pro-preview-06-05","name":"Gemini 2.5 Pro Preview 06-05","provider":"google","input_price":1.25,"output_price":10},"price_ratio":5.53,"savings_pct":82},{"similarity":0.7777,"cheap_model":{"id":"gemini-2.5-flash-preview","name":"Gemini 2.5 Flash Preview","provider":"google","input_price":0.15,"output_price":0.6},"expensive_model":{"id":"gemini-2.5-flash-preview-thinking","name":"Gemini 2.5 Flash Preview (thinking)","provider":"google","input_price":0.175,"output_price":3.5},"price_ratio":5.47,"savings_pct":82},{"similarity":0.8046,"cheap_model":{"id":"qwen3-30b-a3b-thinking-2507","name":"Qwen3 30B A3B Thinking 2507","provider":"qwen","input_price":0.071,"output_price":0.285},"expensive_model":{"id":"nova-2-lite-v1-free","name":"Amazon Nova 2 Lite","provider":"amazon","input_price":0.5,"output_price":1.5},"price_ratio":5.4,"savings_pct":81},{"similarity":0.861,"cheap_model":{"id":"qwen3-coder","name":"Qwen3 Coder","provider":"qwen","input_price":0.22,"output_price":0.95},"expensive_model":{"id":"qwen3-coder-plus","name":"Qwen3 Coder Plus","provider":"qwen","input_price":1,"output_price":5},"price_ratio":5.21,"savings_pct":81},{"similarity":0.919,"cheap_model":{"id":"llama-4-scout","name":"Llama 4 Scout","provider":"meta","input_price":0.25,"output_price":0.5},"expensive_model":{"id":"llama-4-maverick","name":"Llama 4 Maverick","provider":"meta","input_price":1.5,"output_price":2.5},"price_ratio":5.14,"savings_pct":81},{"similarity":0.7717,"cheap_model":{"id":"qwen3-30b-a3b-thinking-2507","name":"Qwen3 30B A3B Thinking 2507","provider":"qwen","input_price":0.071,"output_price":0.285},"expensive_model":{"id":"qwen3-coder-next","name":"Qwen3 Coder Next","provider":"qwen","input_price":0.2,"output_price":1.5},"price_ratio":5.08,"savings_pct":80},{"similarity":0.8922,"cheap_model":{"id":"claude-sonnet-4","name":"Claude Sonnet 4","provider":"anthropic","input_price":3,"output_price":15},"expensive_model":{"id":"claude-opus-4.1","name":"Claude Opus 4.1","provider":"anthropic","input_price":15,"output_price":75},"price_ratio":5,"savings_pct":80},{"similarity":0.82,"cheap_model":{"id":"claude-4.5-sonnet","name":"Claude Sonnet 4.5","provider":"anthropic","input_price":3,"output_price":15},"expensive_model":{"id":"claude-opus-4.1","name":"Claude Opus 4.1","provider":"anthropic","input_price":15,"output_price":75},"price_ratio":5,"savings_pct":80},{"similarity":0.8093,"cheap_model":{"id":"gpt-5-mini","name":"GPT-5 Mini","provider":"openai","input_price":0.25,"output_price":2},"expensive_model":{"id":"gpt-5","name":"GPT-5","provider":"openai","input_price":1.25,"output_price":10},"price_ratio":5,"savings_pct":80},{"similarity":0.8322,"cheap_model":{"id":"qwen3.5-flash-02-23","name":"Qwen: Qwen3.5 Flash","provider":"qwen","input_price":0.1,"output_price":0.4},"expensive_model":{"id":"qwen3.5-35b-a3b","name":"Qwen: Qwen3.5 35B A3B","provider":"qwen","input_price":0.25,"output_price":2},"price_ratio":4.81,"savings_pct":79},{"similarity":0.757,"cheap_model":{"id":"mistral-small-creative","name":"Mistral Small Creative","provider":"mistral","input_price":0.1,"output_price":0.3},"expensive_model":{"id":"qwen3-next-80b-a3b-thinking","name":"Qwen3 Next 80B A3B Thinking","provider":"qwen","input_price":0.15,"output_price":1.5},"price_ratio":4.65,"savings_pct":78},{"similarity":0.9328,"cheap_model":{"id":"gpt-5.4-mini","name":"GPT-5.4 Mini","provider":"openai","input_price":0.75,"output_price":4.5},"expensive_model":{"id":"gpt-5.4","name":"GPT-5.4","provider":"openai","input_price":2.5,"output_price":15},"price_ratio":3.33,"savings_pct":70},{"similarity":0.7593,"cheap_model":{"id":"qwen3-coder-flash","name":"Qwen3 Coder Flash","provider":"qwen","input_price":0.3,"output_price":1.5},"expensive_model":{"id":"qwen3-coder-plus","name":"Qwen3 Coder Plus","provider":"qwen","input_price":1,"output_price":5},"price_ratio":3.33,"savings_pct":70},{"similarity":0.8998,"cheap_model":{"id":"mistral-small-2603","name":"Mistral Small 4","provider":"mistral","input_price":0.15,"output_price":0.6},"expensive_model":{"id":"mistral-medium-3.1","name":"Mistral Medium 3.1","provider":"mistral","input_price":0.4,"output_price":2},"price_ratio":3.28,"savings_pct":70},{"similarity":0.7538,"cheap_model":{"id":"gpt-5-mini","name":"GPT-5 Mini","provider":"openai","input_price":0.25,"output_price":2},"expensive_model":{"id":"grok-4.20-multi-agent-beta","name":"Grok 4.20 Multi-Agent Beta","provider":"xai","input_price":2,"output_price":6},"price_ratio":3.2,"savings_pct":69},{"similarity":0.8019,"cheap_model":{"id":"qwen3-coder-plus","name":"Qwen3 Coder Plus","provider":"qwen","input_price":1,"output_price":5},"expensive_model":{"id":"claude-sonnet-4","name":"Claude Sonnet 4","provider":"anthropic","input_price":3,"output_price":15},"price_ratio":3,"savings_pct":67},{"similarity":0.8172,"cheap_model":{"id":"gemma-3-27b-it","name":"Gemma 3 27B","provider":"google","input_price":0.09,"output_price":0.17},"expensive_model":{"id":"gemini-2.0-flash-thinking-exp","name":"Gemini 2.0 Flash Thinking","provider":"google","input_price":0.25,"output_price":0.5},"price_ratio":2.92,"savings_pct":66},{"similarity":0.7829,"cheap_model":{"id":"qwen3-next-80b-a3b-thinking","name":"Qwen3 Next 80B A3B Thinking","provider":"qwen","input_price":0.15,"output_price":1.5},"expensive_model":{"id":"qwen-plus-2025-07-28-thinking","name":"Qwen Plus 0728 (thinking)","provider":"qwen","input_price":0.4,"output_price":4},"price_ratio":2.67,"savings_pct":63},{"similarity":0.7763,"cheap_model":{"id":"glm-4.5-air","name":"Z.AI: GLM 4.5 Air","provider":"zhipu","input_price":0.2,"output_price":1.1},"expensive_model":{"id":"llama-4-maverick","name":"Llama 4 Maverick","provider":"meta","input_price":1.5,"output_price":2.5},"price_ratio":2.57,"savings_pct":61}],"provider_convergence":[{"provider":"meta","model_count":4,"intra_similarity":0.4225,"inter_similarity":0.0113,"distinctiveness":37.544,"models":["llama-3.1-405b","llama-3.1-70b","llama-4-maverick","llama-4-scout"]},{"provider":"zhipu","model_count":6,"intra_similarity":0.1559,"inter_similarity":0.0127,"distinctiveness":12.269,"models":["glm-4-32b","glm-4.5","glm-4.5-air","glm-4.6","glm-4.7-flash","glm-5"]},{"provider":"deepseek","model_count":7,"intra_similarity":0.0486,"inter_similarity":0.0079,"distinctiveness":6.148,"models":["deepseek-chat-v3.1","deepseek-r1","deepseek-r1-0528","deepseek-v3-03-24","deepseek-v3.2","deepseek-v3.2-exp","deepseek-v3.2-speciale"]},{"provider":"minimax","model_count":6,"intra_similarity":0.0349,"inter_similarity":0.0085,"distinctiveness":4.086,"models":["minimax-m1","minimax-m2-free","minimax-m2-her","minimax-m2.1","minimax-m2.5","minimax-m2.7"]},{"provider":"openrouter","model_count":18,"intra_similarity":-0.0048,"inter_similarity":-0.0072,"distinctiveness":0,"models":["andromeda-alpha","aurora-alpha","bert-nebulon-alpha","cypher-alpha-free","glm-4.7","healer-alpha","horizon-alpha","horizon-beta","hunter-alpha","intellect-3","optimus-alpha","polaris-alpha","pony-alpha","sherlock-dash-alpha","sherlock-think-alpha","sonoma-dusk-alpha","sonoma-sky-alpha","tng-r1t-chimera-free"]},{"provider":"openai","model_count":37,"intra_similarity":0.0861,"inter_similarity":-0.0273,"distinctiveness":0,"models":["chatgpt-4o-03-25","gpt-2","gpt-3.5-turbo","gpt-4","gpt-4.1","gpt-4.1-mini","gpt-4.1-nano","gpt-4.5","gpt-4o","gpt-4o-mini","gpt-5","gpt-5-codex","gpt-5-mini","gpt-5-nano","gpt-5-pro","gpt-5.1","gpt-5.1-chat","gpt-5.1-codex","gpt-5.1-codex-max","gpt-5.1-codex-mini","gpt-5.2","gpt-5.2-chat","gpt-5.2-pro","gpt-5.3-chat","gpt-5.3-codex","gpt-5.4","gpt-5.4-mini","gpt-5.4-nano","gpt-5.4-pro","gpt-oss-120b","gpt-oss-20b","o1","o3","o3-mini","o4-mini","o4-mini-high","openai-gpt"]},{"provider":"anthropic","model_count":15,"intra_similarity":0.1988,"inter_similarity":-0.0408,"distinctiveness":0,"models":["claude-3-haiku","claude-3-opus","claude-3-sonnet","claude-3.5-sonnet","claude-3.7-sonnet","claude-3.7-sonnet-thinking","claude-4.5-sonnet","claude-haiku-4.5","claude-opus-4","claude-opus-4.1","claude-opus-4.5","claude-opus-4.6","claude-sonnet-4","claude-sonnet-4.6","golden-gate-claude"]},{"provider":"mistral","model_count":11,"intra_similarity":0.3867,"inter_similarity":-0.0034,"distinctiveness":0,"models":["devstral-2512-free","devstral-medium","devstral-small","mistral-large","mistral-large-2","mistral-large-2512","mistral-medium-3","mistral-medium-3.1","mistral-nemo","mistral-small-2603","mistral-small-creative"]},{"provider":"google","model_count":22,"intra_similarity":0.1587,"inter_similarity":-0.0172,"distinctiveness":0,"models":["gemini-1.5-pro","gemini-2.0-flash-thinking-exp","gemini-2.0-pro-exp","gemini-2.5-flash-lite-preview-06-17","gemini-2.5-flash-lite-preview-09-2025","gemini-2.5-flash-preview","gemini-2.5-flash-preview-05-20-thinking","gemini-2.5-flash-preview-09-2025","gemini-2.5-flash-preview-thinking","gemini-2.5-pro-exp","gemini-2.5-pro-preview-05-06","gemini-2.5-pro-preview-06-05","gemini-3-flash-preview","gemini-3-pro-preview","gemini-3.1-flash-lite-preview","gemini-3.1-pro-preview","gemini-pro","gemma-3-12b-it","gemma-3-27b-it","gemma-3n-e2b-it-free","gemma-3n-e4b-it","palm-2-chat-bison"]},{"provider":"xai","model_count":9,"intra_similarity":0.245,"inter_similarity":-0.0072,"distinctiveness":0,"models":["grok-3","grok-3-beta","grok-3-thinking","grok-4","grok-4-fast-free","grok-4.1-fast","grok-4.20-beta","grok-4.20-multi-agent-beta","grok-code-fast-1"]},{"provider":"moonshotai","model_count":5,"intra_similarity":0.1084,"inter_similarity":-0.0082,"distinctiveness":0,"models":["kimi-k2","kimi-k2-0905","kimi-k2-thinking","kimi-k2.5","kimi-linear-48b-a3b-instruct"]},{"provider":"xiaomi","model_count":3,"intra_similarity":-0.0585,"inter_similarity":-0.002,"distinctiveness":0,"models":["mimo-v2-flash","mimo-v2-omni","mimo-v2-pro"]},{"provider":"qwen","model_count":24,"intra_similarity":0.1247,"inter_similarity":-0.0213,"distinctiveness":0,"models":["qwen-plus-2025-07-28","qwen-plus-2025-07-28-thinking","qwen3-0.6b-04-28","qwen3-235b-a22b-07-25","qwen3-235b-a22b-thinking-2507","qwen3-30b-a3b","qwen3-30b-a3b-instruct-2507","qwen3-30b-a3b-thinking-2507","qwen3-coder","qwen3-coder-flash","qwen3-coder-next","qwen3-coder-plus","qwen3-max","qwen3-max-thinking","qwen3-next-80b-a3b-instruct","qwen3-next-80b-a3b-thinking","qwen3.5-122b-a10b","qwen3.5-27b","qwen3.5-35b-a3b","qwen3.5-397b-a17b","qwen3.5-9b","qwen3.5-flash-02-23","qwen3.5-plus-02-15","qwq-32b"]}],"family_analysis":[{"family":"GPT-5","model_count":4,"avg_similarity":0.7144,"models":[{"id":"gpt-5.4","name":"GPT-5.4","size":"xlarge"},{"id":"gpt-5.4-mini","name":"GPT-5.4 Mini","size":"medium"},{"id":"gpt-5.4-nano","name":"GPT-5.4 Nano","size":"small"},{"id":"gpt-5.4-pro","name":"GPT-5.4 Pro","size":"xlarge"}],"pairs":[{"model_a":"gpt-5.4","model_b":"gpt-5.4-mini","similarity":0.9328},{"model_a":"gpt-5.4","model_b":"gpt-5.4-pro","similarity":0.8092},{"model_a":"gpt-5.4-mini","model_b":"gpt-5.4-pro","similarity":0.7826},{"model_a":"gpt-5.4-nano","model_b":"gpt-5.4-pro","similarity":0.6521},{"model_a":"gpt-5.4-mini","model_b":"gpt-5.4-nano","similarity":0.6003},{"model_a":"gpt-5.4","model_b":"gpt-5.4-nano","similarity":0.5096}]},{"family":"Mistral","model_count":5,"avg_similarity":0.4768,"models":[{"id":"mistral-large","name":"Mistral Large","size":"large"},{"id":"mistral-large-2","name":"Mistral Large 2","size":"large"},{"id":"mistral-medium-3","name":"Mistral Medium 3","size":"large"},{"id":"mistral-medium-3.1","name":"Mistral Medium 3.1","size":"large"},{"id":"mistral-nemo","name":"Mistral Nemo","size":"large"}],"pairs":[{"model_a":"mistral-large","model_b":"mistral-large-2","similarity":0.7742},{"model_a":"mistral-large-2","model_b":"mistral-medium-3.1","similarity":0.7592},{"model_a":"mistral-large","model_b":"mistral-medium-3.1","similarity":0.6388},{"model_a":"mistral-medium-3","model_b":"mistral-medium-3.1","similarity":0.6128},{"model_a":"mistral-large-2","model_b":"mistral-medium-3","similarity":0.4978},{"model_a":"mistral-large","model_b":"mistral-medium-3","similarity":0.436},{"model_a":"mistral-large","model_b":"mistral-nemo","similarity":0.3768},{"model_a":"mistral-medium-3","model_b":"mistral-nemo","similarity":0.3733},{"model_a":"mistral-large-2","model_b":"mistral-nemo","similarity":0.2194},{"model_a":"mistral-medium-3.1","model_b":"mistral-nemo","similarity":0.0792}]},{"family":"Llama","model_count":4,"avg_similarity":0.4225,"models":[{"id":"llama-3.1-405b","name":"Llama 3.1 405B","size":"xlarge"},{"id":"llama-3.1-70b","name":"Llama 3.1 70B (Instruct)","size":"large"},{"id":"llama-4-maverick","name":"Llama 4 Maverick","size":"xlarge"},{"id":"llama-4-scout","name":"Llama 4 Scout","size":"medium"}],"pairs":[{"model_a":"llama-4-maverick","model_b":"llama-4-scout","similarity":0.919},{"model_a":"llama-3.1-70b","model_b":"llama-4-scout","similarity":0.709},{"model_a":"llama-3.1-70b","model_b":"llama-4-maverick","similarity":0.7058},{"model_a":"llama-3.1-405b","model_b":"llama-3.1-70b","similarity":0.1146},{"model_a":"llama-3.1-405b","model_b":"llama-4-maverick","similarity":0.0719},{"model_a":"llama-3.1-405b","model_b":"llama-4-scout","similarity":0.015}]},{"family":"MiniMax","model_count":3,"avg_similarity":0.4112,"models":[{"id":"minimax-m1","name":"MiniMax M1","size":"xlarge"},{"id":"minimax-m2.5","name":"MiniMax M2.5","size":"large"},{"id":"minimax-m2.7","name":"MiniMax M2.7","size":"large"}],"pairs":[{"model_a":"minimax-m2.5","model_b":"minimax-m2.7","similarity":0.6595},{"model_a":"minimax-m1","model_b":"minimax-m2.7","similarity":0.319},{"model_a":"minimax-m1","model_b":"minimax-m2.5","similarity":0.2552}]},{"family":"o-series","model_count":5,"avg_similarity":0.3383,"models":[{"id":"o1","name":"o1","size":"medium"},{"id":"o3","name":"OpenAI o3","size":"xlarge"},{"id":"o3-mini","name":"o3 Mini","size":"small"},{"id":"o4-mini","name":"OpenAI o4-mini","size":"medium"},{"id":"o4-mini-high","name":"OpenAI o4 Mini High","size":"medium"}],"pairs":[{"model_a":"o4-mini","model_b":"o4-mini-high","similarity":0.6409},{"model_a":"o1","model_b":"o4-mini","similarity":0.4645},{"model_a":"o1","model_b":"o3-mini","similarity":0.4633},{"model_a":"o3","model_b":"o4-mini","similarity":0.4168},{"model_a":"o3","model_b":"o4-mini-high","similarity":0.3448},{"model_a":"o3-mini","model_b":"o4-mini-high","similarity":0.3036},{"model_a":"o1","model_b":"o4-mini-high","similarity":0.2533},{"model_a":"o3-mini","model_b":"o4-mini","similarity":0.2443},{"model_a":"o1","model_b":"o3","similarity":0.1267},{"model_a":"o3","model_b":"o3-mini","similarity":0.1244}]},{"family":"Grok","model_count":8,"avg_similarity":0.3118,"models":[{"id":"grok-3","name":"Grok 3","size":"xlarge"},{"id":"grok-3-beta","name":"Grok 3 Beta","size":"xlarge"},{"id":"grok-3-thinking","name":"Grok 3 Thinking","size":"xlarge"},{"id":"grok-4","name":"xAI: Grok 4","size":"large"},{"id":"grok-4-fast-free","name":"xAI: Grok 4 Fast (free)","size":"large"},{"id":"grok-4.20-beta","name":"Grok 4.20 Beta","size":"xlarge"},{"id":"grok-4.20-multi-agent-beta","name":"Grok 4.20 Multi-Agent Beta","size":"xlarge"},{"id":"grok-code-fast-1","name":"Grok Code Fast 1","size":"medium"}],"pairs":[{"model_a":"grok-3","model_b":"grok-4","similarity":0.778},{"model_a":"grok-3","model_b":"grok-code-fast-1","similarity":0.6967},{"model_a":"grok-3","model_b":"grok-3-beta","similarity":0.675},{"model_a":"grok-4","model_b":"grok-code-fast-1","similarity":0.648},{"model_a":"grok-4.20-beta","model_b":"grok-4.20-multi-agent-beta","similarity":0.6292},{"model_a":"grok-3-beta","model_b":"grok-3-thinking","similarity":0.6186},{"model_a":"grok-3","model_b":"grok-3-thinking","similarity":0.6079},{"model_a":"grok-4-fast-free","model_b":"grok-code-fast-1","similarity":0.5321},{"model_a":"grok-4","model_b":"grok-4.20-multi-agent-beta","similarity":0.4892},{"model_a":"grok-4.20-multi-agent-beta","model_b":"grok-code-fast-1","similarity":0.4581},{"model_a":"grok-3","model_b":"grok-4.20-multi-agent-beta","similarity":0.4437},{"model_a":"grok-3-beta","model_b":"grok-4","similarity":0.4016},{"model_a":"grok-3-thinking","model_b":"grok-code-fast-1","similarity":0.3859},{"model_a":"grok-3-beta","model_b":"grok-code-fast-1","similarity":0.3003},{"model_a":"grok-4","model_b":"grok-4-fast-free","similarity":0.2522},{"model_a":"grok-3-thinking","model_b":"grok-4","similarity":0.2275},{"model_a":"grok-3","model_b":"grok-4-fast-free","similarity":0.1698},{"model_a":"grok-3-beta","model_b":"grok-4-fast-free","similarity":0.1698},{"model_a":"grok-4-fast-free","model_b":"grok-4.20-multi-agent-beta","similarity":0.1679},{"model_a":"grok-3","model_b":"grok-4.20-beta","similarity":0.0814},{"model_a":"grok-3-beta","model_b":"grok-4.20-beta","similarity":0.0657},{"model_a":"grok-3-thinking","model_b":"grok-4-fast-free","similarity":0.0359},{"model_a":"grok-3-beta","model_b":"grok-4.20-multi-agent-beta","similarity":0.033},{"model_a":"grok-3-thinking","model_b":"grok-4.20-beta","similarity":0.0277},{"model_a":"grok-4.20-beta","model_b":"grok-code-fast-1","similarity":0.012},{"model_a":"grok-4-fast-free","model_b":"grok-4.20-beta","similarity":-0.0169},{"model_a":"grok-3-thinking","model_b":"grok-4.20-multi-agent-beta","similarity":-0.0356},{"model_a":"grok-4","model_b":"grok-4.20-beta","similarity":-0.1239}]},{"family":"Gemini","model_count":12,"avg_similarity":0.2646,"models":[{"id":"gemini-1.5-pro","name":"Gemini 1.5 Pro","size":"large"},{"id":"gemini-2.0-flash-thinking-exp","name":"Gemini 2.0 Flash Thinking","size":"large"},{"id":"gemini-2.0-pro-exp","name":"Gemini 2.0 Pro Experimental","size":"xlarge"},{"id":"gemini-2.5-flash-lite-preview-06-17","name":"Gemini 2.5 Flash Lite Preview 06-17","size":"small"},{"id":"gemini-2.5-flash-preview","name":"Gemini 2.5 Flash Preview","size":"medium"},{"id":"gemini-2.5-flash-preview-05-20-thinking","name":"Gemini 2.5 Flash Preview 05-20 (thinking)","size":"medium"},{"id":"gemini-2.5-flash-preview-thinking","name":"Gemini 2.5 Flash Preview (thinking)","size":"medium"},{"id":"gemini-2.5-pro-exp","name":"Gemini 2.5 Pro Experimental","size":"xlarge"},{"id":"gemini-2.5-pro-preview-06-05","name":"Gemini 2.5 Pro Preview 06-05","size":"xlarge"},{"id":"gemini-3.1-flash-lite-preview","name":"Google: Gemini 3.1 Flash Lite Preview","size":"small"},{"id":"gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","size":"xlarge"},{"id":"gemini-pro","name":"Gemini Pro 1.0","size":"large"}],"pairs":[{"model_a":"gemini-2.5-flash-lite-preview-06-17","model_b":"gemini-2.5-flash-preview-05-20-thinking","similarity":0.8173},{"model_a":"gemini-2.0-flash-thinking-exp","model_b":"gemini-2.0-pro-exp","similarity":0.7969},{"model_a":"gemini-2.5-flash-preview","model_b":"gemini-2.5-flash-preview-thinking","similarity":0.7777},{"model_a":"gemini-2.5-flash-lite-preview-06-17","model_b":"gemini-2.5-flash-preview-thinking","similarity":0.7484},{"model_a":"gemini-2.0-flash-thinking-exp","model_b":"gemini-2.5-flash-preview","similarity":0.7053},{"model_a":"gemini-1.5-pro","model_b":"gemini-2.0-flash-thinking-exp","similarity":0.6123},{"model_a":"gemini-2.0-pro-exp","model_b":"gemini-2.5-flash-preview","similarity":0.599},{"model_a":"gemini-2.5-flash-preview-05-20-thinking","model_b":"gemini-2.5-flash-preview-thinking","similarity":0.5636},{"model_a":"gemini-3.1-flash-lite-preview","model_b":"gemini-3.1-pro-preview","similarity":0.5431},{"model_a":"gemini-2.0-flash-thinking-exp","model_b":"gemini-2.5-flash-preview-thinking","similarity":0.5329},{"model_a":"gemini-2.5-flash-lite-preview-06-17","model_b":"gemini-2.5-flash-preview","similarity":0.5211},{"model_a":"gemini-2.0-pro-exp","model_b":"gemini-2.5-flash-preview-thinking","similarity":0.5168},{"model_a":"gemini-1.5-pro","model_b":"gemini-2.0-pro-exp","similarity":0.4909},{"model_a":"gemini-1.5-pro","model_b":"gemini-2.5-flash-preview","similarity":0.4343},{"model_a":"gemini-2.5-flash-preview-thinking","model_b":"gemini-3.1-pro-preview","similarity":0.4332},{"model_a":"gemini-2.0-pro-exp","model_b":"gemini-2.5-pro-exp","similarity":0.4073},{"model_a":"gemini-2.0-pro-exp","model_b":"gemini-2.5-flash-lite-preview-06-17","similarity":0.3938},{"model_a":"gemini-2.0-flash-thinking-exp","model_b":"gemini-2.5-pro-exp","similarity":0.3812},{"model_a":"gemini-2.5-pro-exp","model_b":"gemini-3.1-flash-lite-preview","similarity":0.3771},{"model_a":"gemini-2.5-pro-preview-06-05","model_b":"gemini-3.1-flash-lite-preview","similarity":0.3716},{"model_a":"gemini-2.0-pro-exp","model_b":"gemini-2.5-flash-preview-05-20-thinking","similarity":0.3671},{"model_a":"gemini-2.5-pro-exp","model_b":"gemini-2.5-pro-preview-06-05","similarity":0.363},{"model_a":"gemini-2.5-pro-preview-06-05","model_b":"gemini-3.1-pro-preview","similarity":0.363},{"model_a":"gemini-2.5-flash-preview-05-20-thinking","model_b":"gemini-pro","similarity":0.3459},{"model_a":"gemini-2.0-pro-exp","model_b":"gemini-pro","similarity":0.3238},{"model_a":"gemini-2.5-flash-preview-thinking","model_b":"gemini-pro","similarity":0.3218},{"model_a":"gemini-2.5-pro-exp","model_b":"gemini-3.1-pro-preview","similarity":0.3159},{"model_a":"gemini-2.0-flash-thinking-exp","model_b":"gemini-2.5-flash-lite-preview-06-17","similarity":0.297},{"model_a":"gemini-1.5-pro","model_b":"gemini-3.1-pro-preview","similarity":0.2878},{"model_a":"gemini-2.5-flash-preview","model_b":"gemini-2.5-pro-exp","similarity":0.2825},{"model_a":"gemini-2.5-pro-exp","model_b":"gemini-pro","similarity":0.2788},{"model_a":"gemini-2.5-flash-preview","model_b":"gemini-3.1-pro-preview","similarity":0.2677},{"model_a":"gemini-1.5-pro","model_b":"gemini-2.5-flash-preview-thinking","similarity":0.2658},{"model_a":"gemini-1.5-pro","model_b":"gemini-2.5-pro-exp","similarity":0.2617},{"model_a":"gemini-2.5-flash-preview","model_b":"gemini-2.5-flash-preview-05-20-thinking","similarity":0.261},{"model_a":"gemini-3.1-pro-preview","model_b":"gemini-pro","similarity":0.256},{"model_a":"gemini-2.0-flash-thinking-exp","model_b":"gemini-2.5-pro-preview-06-05","similarity":0.2499},{"model_a":"gemini-2.5-flash-preview-thinking","model_b":"gemini-2.5-pro-exp","similarity":0.2486},{"model_a":"gemini-2.0-flash-thinking-exp","model_b":"gemini-pro","similarity":0.2459},{"model_a":"gemini-1.5-pro","model_b":"gemini-pro","similarity":0.242},{"model_a":"gemini-2.5-flash-lite-preview-06-17","model_b":"gemini-pro","similarity":0.2338},{"model_a":"gemini-1.5-pro","model_b":"gemini-2.5-pro-preview-06-05","similarity":0.1808},{"model_a":"gemini-2.5-flash-lite-preview-06-17","model_b":"gemini-3.1-pro-preview","similarity":0.1491},{"model_a":"gemini-2.5-flash-preview","model_b":"gemini-pro","similarity":0.1351},{"model_a":"gemini-2.5-flash-preview-05-20-thinking","model_b":"gemini-3.1-pro-preview","similarity":0.1216},{"model_a":"gemini-2.5-flash-preview","model_b":"gemini-2.5-pro-preview-06-05","similarity":0.1202},{"model_a":"gemini-2.5-flash-lite-preview-06-17","model_b":"gemini-2.5-pro-exp","similarity":0.0978},{"model_a":"gemini-2.5-flash-preview-05-20-thinking","model_b":"gemini-2.5-pro-exp","similarity":0.0869},{"model_a":"gemini-2.0-flash-thinking-exp","model_b":"gemini-3.1-pro-preview","similarity":0.0827},{"model_a":"gemini-2.5-flash-preview-thinking","model_b":"gemini-2.5-pro-preview-06-05","similarity":0.0813},{"model_a":"gemini-2.0-flash-thinking-exp","model_b":"gemini-2.5-flash-preview-05-20-thinking","similarity":0.0789},{"model_a":"gemini-1.5-pro","model_b":"gemini-3.1-flash-lite-preview","similarity":0.0645},{"model_a":"gemini-2.5-pro-preview-06-05","model_b":"gemini-pro","similarity":0.0549},{"model_a":"gemini-2.0-pro-exp","model_b":"gemini-3.1-pro-preview","similarity":0.0456},{"model_a":"gemini-1.5-pro","model_b":"gemini-2.5-flash-lite-preview-06-17","similarity":0.0326},{"model_a":"gemini-2.5-flash-lite-preview-06-17","model_b":"gemini-2.5-pro-preview-06-05","similarity":0.0173},{"model_a":"gemini-3.1-flash-lite-preview","model_b":"gemini-pro","similarity":0.0067},{"model_a":"gemini-2.5-flash-lite-preview-06-17","model_b":"gemini-3.1-flash-lite-preview","similarity":-0.0253},{"model_a":"gemini-1.5-pro","model_b":"gemini-2.5-flash-preview-05-20-thinking","similarity":-0.0277},{"model_a":"gemini-2.0-pro-exp","model_b":"gemini-2.5-pro-preview-06-05","similarity":-0.0326},{"model_a":"gemini-2.5-flash-preview-05-20-thinking","model_b":"gemini-2.5-pro-preview-06-05","similarity":-0.0473},{"model_a":"gemini-2.5-flash-preview-thinking","model_b":"gemini-3.1-flash-lite-preview","similarity":-0.0596},{"model_a":"gemini-2.5-flash-preview-05-20-thinking","model_b":"gemini-3.1-flash-lite-preview","similarity":-0.094},{"model_a":"gemini-2.5-flash-preview","model_b":"gemini-3.1-flash-lite-preview","similarity":-0.1266},{"model_a":"gemini-2.0-flash-thinking-exp","model_b":"gemini-3.1-flash-lite-preview","similarity":-0.2385},{"model_a":"gemini-2.0-pro-exp","model_b":"gemini-3.1-flash-lite-preview","similarity":-0.3406}]},{"family":"Claude","model_count":11,"avg_similarity":0.1939,"models":[{"id":"claude-3-haiku","name":"Claude 3 Haiku","size":"medium"},{"id":"claude-3-opus","name":"Claude 3 Opus","size":"xlarge"},{"id":"claude-3-sonnet","name":"Claude 3 Sonnet","size":"large"},{"id":"claude-3.5-sonnet","name":"Claude Sonnet 3.6 (2022-10-22)","size":"large"},{"id":"claude-3.7-sonnet","name":"Claude 3.7 Sonnet","size":"large"},{"id":"claude-3.7-sonnet-thinking","name":"Claude 3.7 Thinking Sonnet","size":"large"},{"id":"claude-opus-4","name":"Claude Opus 4","size":"xlarge"},{"id":"claude-opus-4.1","name":"Claude Opus 4.1","size":"xlarge"},{"id":"claude-opus-4.6","name":"Claude Opus 4.6","size":"xlarge"},{"id":"claude-sonnet-4","name":"Claude Sonnet 4","size":"large"},{"id":"claude-sonnet-4.6","name":"Claude Sonnet 4.6","size":"large"}],"pairs":[{"model_a":"claude-opus-4.1","model_b":"claude-sonnet-4","similarity":0.8922},{"model_a":"claude-opus-4.6","model_b":"claude-sonnet-4.6","similarity":0.783},{"model_a":"claude-3.7-sonnet","model_b":"claude-3.7-sonnet-thinking","similarity":0.6623},{"model_a":"claude-3.5-sonnet","model_b":"claude-opus-4.1","similarity":0.6217},{"model_a":"claude-3-opus","model_b":"claude-3-sonnet","similarity":0.6172},{"model_a":"claude-3.7-sonnet-thinking","model_b":"claude-opus-4.1","similarity":0.5591},{"model_a":"claude-3.5-sonnet","model_b":"claude-3.7-sonnet-thinking","similarity":0.5386},{"model_a":"claude-3.7-sonnet-thinking","model_b":"claude-sonnet-4","similarity":0.5329},{"model_a":"claude-3.5-sonnet","model_b":"claude-sonnet-4","similarity":0.5294},{"model_a":"claude-opus-4.6","model_b":"claude-sonnet-4","similarity":0.4619},{"model_a":"claude-3.5-sonnet","model_b":"claude-3.7-sonnet","similarity":0.4579},{"model_a":"claude-3-haiku","model_b":"claude-3-sonnet","similarity":0.4562},{"model_a":"claude-3.7-sonnet-thinking","model_b":"claude-opus-4.6","similarity":0.4562},{"model_a":"claude-opus-4","model_b":"claude-sonnet-4","similarity":0.4335},{"model_a":"claude-opus-4","model_b":"claude-opus-4.1","similarity":0.4153},{"model_a":"claude-opus-4.1","model_b":"claude-opus-4.6","similarity":0.3721},{"model_a":"claude-3-haiku","model_b":"claude-3.5-sonnet","similarity":0.3362},{"model_a":"claude-sonnet-4","model_b":"claude-sonnet-4.6","similarity":0.3318},{"model_a":"claude-3.7-sonnet-thinking","model_b":"claude-sonnet-4.6","similarity":0.3053},{"model_a":"claude-3-opus","model_b":"claude-3.7-sonnet","similarity":0.2953},{"model_a":"claude-3.7-sonnet","model_b":"claude-opus-4.1","similarity":0.2832},{"model_a":"claude-3-haiku","model_b":"claude-3-opus","similarity":0.2723},{"model_a":"claude-3-haiku","model_b":"claude-3.7-sonnet","similarity":0.2699},{"model_a":"claude-3.7-sonnet","model_b":"claude-opus-4.6","similarity":0.2693},{"model_a":"claude-opus-4.1","model_b":"claude-sonnet-4.6","similarity":0.256},{"model_a":"claude-3.7-sonnet","model_b":"claude-sonnet-4","similarity":0.2416},{"model_a":"claude-3-sonnet","model_b":"claude-3.7-sonnet","similarity":0.2381},{"model_a":"claude-3-haiku","model_b":"claude-3.7-sonnet-thinking","similarity":0.2373},{"model_a":"claude-3.5-sonnet","model_b":"claude-opus-4","similarity":0.1811},{"model_a":"claude-3.7-sonnet","model_b":"claude-sonnet-4.6","similarity":0.162},{"model_a":"claude-3.5-sonnet","model_b":"claude-opus-4.6","similarity":0.1434},{"model_a":"claude-3-opus","model_b":"claude-opus-4.6","similarity":0.1298},{"model_a":"claude-3.7-sonnet-thinking","model_b":"claude-opus-4","similarity":0.0736},{"model_a":"claude-3.5-sonnet","model_b":"claude-sonnet-4.6","similarity":0.0717},{"model_a":"claude-3-opus","model_b":"claude-3.7-sonnet-thinking","similarity":0.0643},{"model_a":"claude-3-sonnet","model_b":"claude-3.7-sonnet-thinking","similarity":0.0339},{"model_a":"claude-3-haiku","model_b":"claude-opus-4.6","similarity":0.0188},{"model_a":"claude-opus-4","model_b":"claude-sonnet-4.6","similarity":0.0076},{"model_a":"claude-3-sonnet","model_b":"claude-3.5-sonnet","similarity":-0.0028},{"model_a":"claude-3-haiku","model_b":"claude-opus-4.1","similarity":-0.0468},{"model_a":"claude-3-opus","model_b":"claude-3.5-sonnet","similarity":-0.0585},{"model_a":"claude-3-opus","model_b":"claude-sonnet-4.6","similarity":-0.0604},{"model_a":"claude-opus-4","model_b":"claude-opus-4.6","similarity":-0.069},{"model_a":"claude-3.7-sonnet","model_b":"claude-opus-4","similarity":-0.0709},{"model_a":"claude-3-haiku","model_b":"claude-sonnet-4","similarity":-0.0829},{"model_a":"claude-3-sonnet","model_b":"claude-opus-4.6","similarity":-0.0976},{"model_a":"claude-3-sonnet","model_b":"claude-sonnet-4","similarity":-0.1148},{"model_a":"claude-3-haiku","model_b":"claude-opus-4","similarity":-0.1287},{"model_a":"claude-3-haiku","model_b":"claude-sonnet-4.6","similarity":-0.1379},{"model_a":"claude-3-sonnet","model_b":"claude-opus-4.1","similarity":-0.1903},{"model_a":"claude-3-sonnet","model_b":"claude-sonnet-4.6","similarity":-0.2007},{"model_a":"claude-3-opus","model_b":"claude-sonnet-4","similarity":-0.239},{"model_a":"claude-3-sonnet","model_b":"claude-opus-4","similarity":-0.2463},{"model_a":"claude-3-opus","model_b":"claude-opus-4.1","similarity":-0.2548},{"model_a":"claude-3-opus","model_b":"claude-opus-4","similarity":-0.3482}]},{"family":"Qwen","model_count":17,"avg_similarity":0.1274,"models":[{"id":"qwen3-0.6b-04-28","name":"Qwen3 0.6B","size":"small"},{"id":"qwen3-235b-a22b-07-25","name":"Qwen: Qwen3 235B A22B 2507","size":"xlarge"},{"id":"qwen3-235b-a22b-thinking-2507","name":"Qwen: Qwen3 235B A22B Thinking 2507","size":"xlarge"},{"id":"qwen3-30b-a3b","name":"Qwen3 30B A3B","size":"large"},{"id":"qwen3-30b-a3b-instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","size":"large"},{"id":"qwen3-30b-a3b-thinking-2507","name":"Qwen3 30B A3B Thinking 2507","size":"large"},{"id":"qwen3-coder","name":"Qwen3 Coder","size":"xlarge"},{"id":"qwen3-max","name":"Qwen: Qwen3 Max","size":"xlarge"},{"id":"qwen3-max-thinking","name":"Qwen: Qwen3 Max Thinking","size":"xlarge"},{"id":"qwen3.5-122b-a10b","name":"Qwen: Qwen3.5 122B A10B","size":"large"},{"id":"qwen3.5-27b","name":"Qwen: Qwen3.5 27B","size":"medium"},{"id":"qwen3.5-35b-a3b","name":"Qwen: Qwen3.5 35B A3B","size":"medium"},{"id":"qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","size":"xlarge"},{"id":"qwen3.5-9b","name":"Qwen3.5 9B","size":"small"},{"id":"qwen3.5-flash-02-23","name":"Qwen: Qwen3.5 Flash","size":"medium"},{"id":"qwen3.5-plus-02-15","name":"Qwen: Qwen3.5 Plus 2026-02-15","size":"xlarge"},{"id":"qwq-32b","name":"QwQ 32B","size":"large"}],"pairs":[{"model_a":"qwen3.5-27b","model_b":"qwen3.5-35b-a3b","similarity":0.911},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-9b","similarity":0.8466},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-flash-02-23","similarity":0.8451},{"model_a":"qwen3.5-9b","model_b":"qwen3.5-flash-02-23","similarity":0.838},{"model_a":"qwen3.5-35b-a3b","model_b":"qwen3.5-flash-02-23","similarity":0.8322},{"model_a":"qwen3.5-27b","model_b":"qwen3.5-flash-02-23","similarity":0.8265},{"model_a":"qwen3.5-397b-a17b","model_b":"qwen3.5-flash-02-23","similarity":0.8265},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-35b-a3b","similarity":0.8136},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-27b","similarity":0.796},{"model_a":"qwen3-235b-a22b-thinking-2507","model_b":"qwen3-30b-a3b-thinking-2507","similarity":0.7919},{"model_a":"qwen3.5-35b-a3b","model_b":"qwen3.5-9b","similarity":0.7872},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-397b-a17b","similarity":0.7491},{"model_a":"qwen3.5-27b","model_b":"qwen3.5-9b","similarity":0.7327},{"model_a":"qwen3.5-27b","model_b":"qwen3.5-397b-a17b","similarity":0.7318},{"model_a":"qwen3.5-35b-a3b","model_b":"qwen3.5-397b-a17b","similarity":0.73},{"model_a":"qwen3.5-397b-a17b","model_b":"qwen3.5-9b","similarity":0.6713},{"model_a":"qwen3-30b-a3b","model_b":"qwen3-30b-a3b-thinking-2507","similarity":0.6654},{"model_a":"qwen3.5-flash-02-23","model_b":"qwen3.5-plus-02-15","similarity":0.5987},{"model_a":"qwen3-235b-a22b-thinking-2507","model_b":"qwen3-30b-a3b","similarity":0.5763},{"model_a":"qwen3-30b-a3b-instruct-2507","model_b":"qwen3-max-thinking","similarity":0.5681},{"model_a":"qwen3.5-35b-a3b","model_b":"qwen3.5-plus-02-15","similarity":0.5637},{"model_a":"qwen3.5-9b","model_b":"qwen3.5-plus-02-15","similarity":0.5506},{"model_a":"qwen3-0.6b-04-28","model_b":"qwen3-30b-a3b","similarity":0.5428},{"model_a":"qwen3-235b-a22b-thinking-2507","model_b":"qwen3-30b-a3b-instruct-2507","similarity":0.5392},{"model_a":"qwen3-30b-a3b-instruct-2507","model_b":"qwen3-30b-a3b-thinking-2507","similarity":0.5253},{"model_a":"qwen3-235b-a22b-07-25","model_b":"qwen3-30b-a3b-instruct-2507","similarity":0.5191},{"model_a":"qwen3.5-397b-a17b","model_b":"qwen3.5-plus-02-15","similarity":0.515},{"model_a":"qwen3-235b-a22b-thinking-2507","model_b":"qwen3-max","similarity":0.5133},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-plus-02-15","similarity":0.501},{"model_a":"qwen3-30b-a3b-instruct-2507","model_b":"qwen3-max","similarity":0.4972},{"model_a":"qwen3-235b-a22b-07-25","model_b":"qwen3-max-thinking","similarity":0.4605},{"model_a":"qwen3.5-27b","model_b":"qwen3.5-plus-02-15","similarity":0.455},{"model_a":"qwen3-30b-a3b","model_b":"qwq-32b","similarity":0.3997},{"model_a":"qwen3-30b-a3b-thinking-2507","model_b":"qwen3-max","similarity":0.3664},{"model_a":"qwen3-30b-a3b-thinking-2507","model_b":"qwen3-max-thinking","similarity":0.3602},{"model_a":"qwen3-235b-a22b-07-25","model_b":"qwen3-max","similarity":0.3272},{"model_a":"qwen3-30b-a3b-thinking-2507","model_b":"qwen3.5-122b-a10b","similarity":0.3087},{"model_a":"qwen3-235b-a22b-thinking-2507","model_b":"qwen3-max-thinking","similarity":0.2994},{"model_a":"qwen3.5-397b-a17b","model_b":"qwq-32b","similarity":0.2968},{"model_a":"qwen3-30b-a3b","model_b":"qwen3-30b-a3b-instruct-2507","similarity":0.2929},{"model_a":"qwen3-0.6b-04-28","model_b":"qwq-32b","similarity":0.2592},{"model_a":"qwen3-235b-a22b-thinking-2507","model_b":"qwq-32b","similarity":0.259},{"model_a":"qwen3-max","model_b":"qwen3-max-thinking","similarity":0.2325},{"model_a":"qwen3-coder","model_b":"qwen3-max","similarity":0.2307},{"model_a":"qwen3-30b-a3b","model_b":"qwen3-max","similarity":0.2217},{"model_a":"qwen3.5-27b","model_b":"qwq-32b","similarity":0.1876},{"model_a":"qwen3-30b-a3b-thinking-2507","model_b":"qwq-32b","similarity":0.1777},{"model_a":"qwen3-max","model_b":"qwq-32b","similarity":0.1574},{"model_a":"qwen3.5-35b-a3b","model_b":"qwq-32b","similarity":0.156},{"model_a":"qwen3-30b-a3b-thinking-2507","model_b":"qwen3.5-397b-a17b","similarity":0.1539},{"model_a":"qwen3-0.6b-04-28","model_b":"qwen3.5-35b-a3b","similarity":0.1476},{"model_a":"qwen3-235b-a22b-07-25","model_b":"qwen3-30b-a3b-thinking-2507","similarity":0.1458},{"model_a":"qwen3-0.6b-04-28","model_b":"qwen3.5-397b-a17b","similarity":0.1424},{"model_a":"qwen3-235b-a22b-thinking-2507","model_b":"qwen3.5-122b-a10b","similarity":0.1311},{"model_a":"qwen3-235b-a22b-thinking-2507","model_b":"qwen3.5-397b-a17b","similarity":0.127},{"model_a":"qwen3-30b-a3b-instruct-2507","model_b":"qwen3.5-397b-a17b","similarity":0.1261},{"model_a":"qwen3-0.6b-04-28","model_b":"qwen3-30b-a3b-thinking-2507","similarity":0.1215},{"model_a":"qwen3-0.6b-04-28","model_b":"qwen3.5-9b","similarity":0.1198},{"model_a":"qwen3-0.6b-04-28","model_b":"qwen3.5-122b-a10b","similarity":0.1164},{"model_a":"qwen3-30b-a3b-thinking-2507","model_b":"qwen3.5-9b","similarity":0.115},{"model_a":"qwen3-0.6b-04-28","model_b":"qwen3-235b-a22b-thinking-2507","similarity":0.1117},{"model_a":"qwen3-max-thinking","model_b":"qwen3.5-27b","similarity":0.1061},{"model_a":"qwen3.5-flash-02-23","model_b":"qwq-32b","similarity":0.1031},{"model_a":"qwen3-0.6b-04-28","model_b":"qwen3.5-flash-02-23","similarity":0.103},{"model_a":"qwen3-0.6b-04-28","model_b":"qwen3.5-plus-02-15","similarity":0.1029},{"model_a":"qwen3.5-122b-a10b","model_b":"qwq-32b","similarity":0.0973},{"model_a":"qwen3-30b-a3b","model_b":"qwen3.5-122b-a10b","similarity":0.0888},{"model_a":"qwen3-235b-a22b-07-25","model_b":"qwen3-235b-a22b-thinking-2507","similarity":0.0782},{"model_a":"qwen3-max-thinking","model_b":"qwen3.5-397b-a17b","similarity":0.0552},{"model_a":"qwen3-30b-a3b-thinking-2507","model_b":"qwen3.5-35b-a3b","similarity":0.0474},{"model_a":"qwen3-0.6b-04-28","model_b":"qwen3.5-27b","similarity":0.0318},{"model_a":"qwen3.5-9b","model_b":"qwq-32b","similarity":0.0318},{"model_a":"qwen3-30b-a3b-thinking-2507","model_b":"qwen3.5-flash-02-23","similarity":0.0299},{"model_a":"qwen3-30b-a3b-instruct-2507","model_b":"qwq-32b","similarity":0.0274},{"model_a":"qwen3-30b-a3b-thinking-2507","model_b":"qwen3.5-27b","similarity":0.0152},{"model_a":"qwen3-235b-a22b-thinking-2507","model_b":"qwen3.5-9b","similarity":-0.0069},{"model_a":"qwen3-30b-a3b","model_b":"qwen3.5-35b-a3b","similarity":-0.0115},{"model_a":"qwen3-30b-a3b","model_b":"qwen3.5-9b","similarity":-0.0251},{"model_a":"qwen3-0.6b-04-28","model_b":"qwen3-max","similarity":-0.0273},{"model_a":"qwen3-235b-a22b-07-25","model_b":"qwq-32b","similarity":-0.0295},{"model_a":"qwen3-30b-a3b","model_b":"qwen3.5-397b-a17b","similarity":-0.0326},{"model_a":"qwen3-30b-a3b-thinking-2507","model_b":"qwen3.5-plus-02-15","similarity":-0.0327},{"model_a":"qwen3-30b-a3b-instruct-2507","model_b":"qwen3.5-122b-a10b","similarity":-0.0347},{"model_a":"qwen3-max-thinking","model_b":"qwen3.5-35b-a3b","similarity":-0.0656},{"model_a":"qwen3-30b-a3b","model_b":"qwen3-max-thinking","similarity":-0.0673},{"model_a":"qwen3-max-thinking","model_b":"qwen3.5-plus-02-15","similarity":-0.0688},{"model_a":"qwen3-coder","model_b":"qwen3.5-plus-02-15","similarity":-0.0713},{"model_a":"qwen3-235b-a22b-thinking-2507","model_b":"qwen3.5-flash-02-23","similarity":-0.0767},{"model_a":"qwen3-235b-a22b-thinking-2507","model_b":"qwen3.5-plus-02-15","similarity":-0.0829},{"model_a":"qwen3-max-thinking","model_b":"qwen3.5-122b-a10b","similarity":-0.0859},{"model_a":"qwen3-coder","model_b":"qwen3.5-27b","similarity":-0.0994},{"model_a":"qwen3-coder","model_b":"qwen3-max-thinking","similarity":-0.106},{"model_a":"qwen3-max-thinking","model_b":"qwen3.5-flash-02-23","similarity":-0.1089},{"model_a":"qwen3-235b-a22b-thinking-2507","model_b":"qwen3.5-27b","similarity":-0.1133},{"model_a":"qwen3-coder","model_b":"qwen3.5-35b-a3b","similarity":-0.1142},{"model_a":"qwen3-235b-a22b-thinking-2507","model_b":"qwen3.5-35b-a3b","similarity":-0.1179},{"model_a":"qwen3-0.6b-04-28","model_b":"qwen3-30b-a3b-instruct-2507","similarity":-0.1196},{"model_a":"qwen3-coder","model_b":"qwen3.5-122b-a10b","similarity":-0.125},{"model_a":"qwen3-30b-a3b-instruct-2507","model_b":"qwen3.5-plus-02-15","similarity":-0.1286},{"model_a":"qwen3-30b-a3b-instruct-2507","model_b":"qwen3.5-9b","similarity":-0.1294},{"model_a":"qwen3-coder","model_b":"qwen3.5-9b","similarity":-0.1387},{"model_a":"qwen3-30b-a3b-instruct-2507","model_b":"qwen3.5-flash-02-23","similarity":-0.1392},{"model_a":"qwen3-coder","model_b":"qwen3.5-397b-a17b","similarity":-0.1456},{"model_a":"qwen3-30b-a3b","model_b":"qwen3.5-27b","similarity":-0.1457},{"model_a":"qwen3-max-thinking","model_b":"qwq-32b","similarity":-0.15},{"model_a":"qwen3-0.6b-04-28","model_b":"qwen3-coder","similarity":-0.1544},{"model_a":"qwen3-coder","model_b":"qwen3.5-flash-02-23","similarity":-0.1617},{"model_a":"qwen3-30b-a3b-instruct-2507","model_b":"qwen3-coder","similarity":-0.1677},{"model_a":"qwen3-coder","model_b":"qwq-32b","similarity":-0.1725},{"model_a":"qwen3-max","model_b":"qwen3.5-397b-a17b","similarity":-0.1756},{"model_a":"qwen3-235b-a22b-thinking-2507","model_b":"qwen3-coder","similarity":-0.1763},{"model_a":"qwen3-30b-a3b-thinking-2507","model_b":"qwen3-coder","similarity":-0.1798},{"model_a":"qwen3-235b-a22b-07-25","model_b":"qwen3-coder","similarity":-0.1848},{"model_a":"qwen3-30b-a3b-instruct-2507","model_b":"qwen3.5-35b-a3b","similarity":-0.1864},{"model_a":"qwen3-max-thinking","model_b":"qwen3.5-9b","similarity":-0.1887},{"model_a":"qwen3-235b-a22b-07-25","model_b":"qwen3-30b-a3b","similarity":-0.2003},{"model_a":"qwen3-30b-a3b","model_b":"qwen3.5-flash-02-23","similarity":-0.2061},{"model_a":"qwen3-30b-a3b","model_b":"qwen3.5-plus-02-15","similarity":-0.2118},{"model_a":"qwen3-max","model_b":"qwen3.5-9b","similarity":-0.2176},{"model_a":"qwen3-235b-a22b-07-25","model_b":"qwen3.5-flash-02-23","similarity":-0.2201},{"model_a":"qwen3-30b-a3b-instruct-2507","model_b":"qwen3.5-27b","similarity":-0.2297},{"model_a":"qwen3-30b-a3b","model_b":"qwen3-coder","similarity":-0.2432},{"model_a":"qwen3-235b-a22b-07-25","model_b":"qwen3.5-397b-a17b","similarity":-0.2438},{"model_a":"qwen3-max","model_b":"qwen3.5-122b-a10b","similarity":-0.2737},{"model_a":"qwen3-0.6b-04-28","model_b":"qwen3-max-thinking","similarity":-0.2842},{"model_a":"qwen3-235b-a22b-07-25","model_b":"qwen3.5-9b","similarity":-0.2989},{"model_a":"qwen3-235b-a22b-07-25","model_b":"qwen3.5-27b","similarity":-0.3413},{"model_a":"qwen3-235b-a22b-07-25","model_b":"qwen3.5-plus-02-15","similarity":-0.348},{"model_a":"qwen3-235b-a22b-07-25","model_b":"qwen3.5-122b-a10b","similarity":-0.3529},{"model_a":"qwen3-max","model_b":"qwen3.5-flash-02-23","similarity":-0.353},{"model_a":"qwen3.5-plus-02-15","model_b":"qwq-32b","similarity":-0.3748},{"model_a":"qwen3-max","model_b":"qwen3.5-27b","similarity":-0.3981},{"model_a":"qwen3-235b-a22b-07-25","model_b":"qwen3.5-35b-a3b","similarity":-0.4439},{"model_a":"qwen3-max","model_b":"qwen3.5-plus-02-15","similarity":-0.4695},{"model_a":"qwen3-0.6b-04-28","model_b":"qwen3-235b-a22b-07-25","similarity":-0.4738},{"model_a":"qwen3-max","model_b":"qwen3.5-35b-a3b","similarity":-0.4758}]},{"family":"GPT","model_count":11,"avg_similarity":0.0319,"models":[{"id":"gpt-2","name":"GPT-2","size":"medium"},{"id":"gpt-3.5-turbo","name":"GPT-3.5 Turbo","size":"medium"},{"id":"gpt-4","name":"GPT-4","size":"xlarge"},{"id":"gpt-4.1","name":"GPT-4.1","size":"xlarge"},{"id":"gpt-4.1-mini","name":"GPT-4.1 Mini","size":"medium"},{"id":"gpt-4.1-nano","name":"GPT-4.1 Nano","size":"small"},{"id":"gpt-4.5","name":"GPT-4.5","size":"xlarge"},{"id":"gpt-4o","name":"GPT-4o (Omni)","size":"xlarge"},{"id":"gpt-4o-mini","name":"GPT-4o mini","size":"small"},{"id":"gpt-5","name":"GPT-5","size":"xlarge"},{"id":"gpt-5-pro","name":"GPT-5 Pro","size":"xlarge"}],"pairs":[{"model_a":"gpt-5","model_b":"gpt-5-pro","similarity":0.6933},{"model_a":"gpt-4.1-mini","model_b":"gpt-4.1-nano","similarity":0.6872},{"model_a":"gpt-4o","model_b":"gpt-4o-mini","similarity":0.6261},{"model_a":"gpt-3.5-turbo","model_b":"gpt-5-pro","similarity":0.535},{"model_a":"gpt-4.1-nano","model_b":"gpt-4.5","similarity":0.4511},{"model_a":"gpt-4.1","model_b":"gpt-4.1-mini","similarity":0.3896},{"model_a":"gpt-4.1-nano","model_b":"gpt-4o-mini","similarity":0.3841},{"model_a":"gpt-2","model_b":"gpt-3.5-turbo","similarity":0.3699},{"model_a":"gpt-4.1","model_b":"gpt-4.1-nano","similarity":0.3185},{"model_a":"gpt-4.5","model_b":"gpt-4o","similarity":0.3007},{"model_a":"gpt-3.5-turbo","model_b":"gpt-4","similarity":0.2915},{"model_a":"gpt-4","model_b":"gpt-4o-mini","similarity":0.2306},{"model_a":"gpt-4.1-nano","model_b":"gpt-4o","similarity":0.223},{"model_a":"gpt-4.5","model_b":"gpt-4o-mini","similarity":0.2073},{"model_a":"gpt-3.5-turbo","model_b":"gpt-4o-mini","similarity":0.1957},{"model_a":"gpt-3.5-turbo","model_b":"gpt-5","similarity":0.1731},{"model_a":"gpt-2","model_b":"gpt-4","similarity":0.1638},{"model_a":"gpt-3.5-turbo","model_b":"gpt-4.5","similarity":0.1548},{"model_a":"gpt-4.1-mini","model_b":"gpt-4o-mini","similarity":0.1144},{"model_a":"gpt-4.1-mini","model_b":"gpt-4o","similarity":0.1014},{"model_a":"gpt-4.1-mini","model_b":"gpt-4.5","similarity":0.089},{"model_a":"gpt-4","model_b":"gpt-4o","similarity":0.0868},{"model_a":"gpt-4.1","model_b":"gpt-4.5","similarity":0.0838},{"model_a":"gpt-4","model_b":"gpt-5-pro","similarity":0.0727},{"model_a":"gpt-2","model_b":"gpt-5-pro","similarity":0.0689},{"model_a":"gpt-2","model_b":"gpt-5","similarity":0.0448},{"model_a":"gpt-4","model_b":"gpt-4.5","similarity":0.0358},{"model_a":"gpt-4.5","model_b":"gpt-5","similarity":0.0199},{"model_a":"gpt-4.1","model_b":"gpt-4o","similarity":0.0035},{"model_a":"gpt-2","model_b":"gpt-4o-mini","similarity":-0.0351},{"model_a":"gpt-4.1","model_b":"gpt-5","similarity":-0.037},{"model_a":"gpt-4","model_b":"gpt-5","similarity":-0.0678},{"model_a":"gpt-4.1-nano","model_b":"gpt-5","similarity":-0.0813},{"model_a":"gpt-4.1-mini","model_b":"gpt-5","similarity":-0.082},{"model_a":"gpt-4","model_b":"gpt-4.1-nano","similarity":-0.0859},{"model_a":"gpt-4o-mini","model_b":"gpt-5-pro","similarity":-0.0929},{"model_a":"gpt-4.1-mini","model_b":"gpt-5-pro","similarity":-0.1031},{"model_a":"gpt-4","model_b":"gpt-4.1-mini","similarity":-0.1182},{"model_a":"gpt-3.5-turbo","model_b":"gpt-4.1-mini","similarity":-0.1252},{"model_a":"gpt-4.5","model_b":"gpt-5-pro","similarity":-0.1292},{"model_a":"gpt-3.5-turbo","model_b":"gpt-4o","similarity":-0.1342},{"model_a":"gpt-2","model_b":"gpt-4o","similarity":-0.1529},{"model_a":"gpt-3.5-turbo","model_b":"gpt-4.1-nano","similarity":-0.194},{"model_a":"gpt-4.1","model_b":"gpt-4o-mini","similarity":-0.2084},{"model_a":"gpt-2","model_b":"gpt-4.1-mini","similarity":-0.2148},{"model_a":"gpt-2","model_b":"gpt-4.1","similarity":-0.2358},{"model_a":"gpt-4o-mini","model_b":"gpt-5","similarity":-0.239},{"model_a":"gpt-4.1-nano","model_b":"gpt-5-pro","similarity":-0.2458},{"model_a":"gpt-4.1","model_b":"gpt-5-pro","similarity":-0.2566},{"model_a":"gpt-4o","model_b":"gpt-5","similarity":-0.3788},{"model_a":"gpt-4","model_b":"gpt-4.1","similarity":-0.3915},{"model_a":"gpt-4o","model_b":"gpt-5-pro","similarity":-0.3968},{"model_a":"gpt-2","model_b":"gpt-4.5","similarity":-0.4317},{"model_a":"gpt-2","model_b":"gpt-4.1-nano","similarity":-0.452},{"model_a":"gpt-3.5-turbo","model_b":"gpt-4.1","similarity":-0.4722}]},{"family":"DeepSeek","model_count":3,"avg_similarity":-0.0526,"models":[{"id":"deepseek-chat-v3.1","name":"DeepSeek V3.1","size":"xlarge"},{"id":"deepseek-r1","name":"DeepSeek R1","size":"large"},{"id":"deepseek-v3-03-24","name":"DeepSeek V3 (March 2024)","size":"xlarge"}],"pairs":[{"model_a":"deepseek-r1","model_b":"deepseek-v3-03-24","similarity":0.3461},{"model_a":"deepseek-chat-v3.1","model_b":"deepseek-r1","similarity":0.0193},{"model_a":"deepseek-chat-v3.1","model_b":"deepseek-v3-03-24","similarity":-0.5233}]}],"feature_importance":[{"feature":"sentence_length_variance","mean":1912.333,"stddev":5320.3028,"cv":2.7821,"min":41.4159,"max":44065.6252,"range":44024.2093,"top_3":[{"id":"qwen3-coder-flash","name":"Qwen3 Coder Flash","value":44065.6252},{"id":"claude-sonnet-4","name":"Claude Sonnet 4","value":31811.5027},{"id":"qwen3-coder","name":"Qwen3 Coder","value":28184.1666}],"bottom_3":[{"id":"gpt-3.5-turbo","name":"GPT-3.5 Turbo","value":41.4159},{"id":"cypher-alpha-free","name":"Cypher Alpha (free)","value":42.4517},{"id":"gemini-2.5-flash-preview-05-20-thinking","name":"Gemini 2.5 Flash Preview 05-20 (thinking)","value":43.3821}]},{"feature":"inline_code_rate","mean":0.0348,"stddev":0.0744,"cv":2.1352,"min":0,"max":0.6032,"range":0.6032,"top_3":[{"id":"gpt-4","name":"GPT-4","value":0.6032},{"id":"claude-sonnet-4","name":"Claude Sonnet 4","value":0.3313},{"id":"glm-4.6","name":"Z.AI: GLM 4.6","value":0.2647}],"bottom_3":[{"id":"trinity-large-preview-free","name":"Trinity Large Preview","value":0},{"id":"tng-r1t-chimera-free","name":"TNG R1T Chimera","value":0},{"id":"sonoma-dusk-alpha","name":"Sonoma Dusk Alpha","value":0}]},{"feature":"emoji_rate","mean":0.1309,"stddev":0.2373,"cv":1.8132,"min":0,"max":1.3711,"range":1.3711,"top_3":[{"id":"qwen3-max-thinking","name":"Qwen: Qwen3 Max Thinking","value":1.3711},{"id":"qwen3-30b-a3b-instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","value":1.0364},{"id":"minimax-m2-her","name":"MiniMax M2-her","value":0.9649}],"bottom_3":[{"id":"trinity-large-preview-free","name":"Trinity Large Preview","value":0},{"id":"sonoma-dusk-alpha","name":"Sonoma Dusk Alpha","value":0},{"id":"sonar-pro-search","name":"Sonar Pro Search","value":0}]},{"feature":"ellipsis_rate","mean":0.0953,"stddev":0.1195,"cv":1.2544,"min":0,"max":0.678,"range":0.678,"top_3":[{"id":"deepseek-r1-0528","name":"DeepSeek R1 0528","value":0.678},{"id":"gemini-2.0-flash-thinking-exp","name":"Gemini 2.0 Flash Thinking","value":0.6748},{"id":"qwen3-235b-a22b-thinking-2507","name":"Qwen: Qwen3 235B A22B Thinking 2507","value":0.5016}],"bottom_3":[{"id":"sherlock-dash-alpha","name":"Sherlock Dash Alpha","value":0},{"id":"openai-gpt","name":"GPT-1","value":0},{"id":"o4-mini","name":"OpenAI o4-mini","value":0}]},{"feature":"italic_rate","mean":0.9257,"stddev":1.0946,"cv":1.1825,"min":0,"max":8.4289,"range":8.4289,"top_3":[{"id":"qwen3-30b-a3b-thinking-2507","name":"Qwen3 30B A3B Thinking 2507","value":8.4289},{"id":"qwen3-30b-a3b","name":"Qwen3 30B A3B","value":4.3536},{"id":"qwen3-coder-next","name":"Qwen3 Coder Next","value":4.248}],"bottom_3":[{"id":"palm-2-chat-bison","name":"PaLM 2 Chat","value":0},{"id":"optimus-alpha","name":"Optimus Alpha","value":0},{"id":"openai-gpt","name":"GPT-1","value":0}]},{"feature":"semicolon_rate","mean":0.2225,"stddev":0.2594,"cv":1.1656,"min":0,"max":1.748,"range":1.748,"top_3":[{"id":"gpt-5","name":"GPT-5","value":1.748},{"id":"qwen3-max-thinking","name":"Qwen: Qwen3 Max Thinking","value":1.2753},{"id":"kimi-k2-0905","name":"MoonshotAI: Kimi K2 0905","value":1.1964}],"bottom_3":[{"id":"qwen3-0.6b-04-28","name":"Qwen3 0.6B","value":0},{"id":"openai-gpt","name":"GPT-1","value":0},{"id":"minimax-m2-her","name":"MiniMax M2-her","value":0}]},{"feature":"em_dash_rate","mean":1.4708,"stddev":1.6381,"cv":1.1138,"min":0,"max":9.379,"range":9.379,"top_3":[{"id":"kimi-k2-0905","name":"MoonshotAI: Kimi K2 0905","value":9.379},{"id":"mistral-small-creative","name":"Mistral Small Creative","value":6.5821},{"id":"mercury","name":"Inception: Mercury","value":6.5413}],"bottom_3":[{"id":"palm-2-chat-bison","name":"PaLM 2 Chat","value":0},{"id":"openai-gpt","name":"GPT-1","value":0},{"id":"mistral-nemo","name":"Mistral Nemo","value":0}]},{"feature":"exclamation_rate","mean":0.3691,"stddev":0.3871,"cv":1.0487,"min":0,"max":2.73,"range":2.73,"top_3":[{"id":"gemini-2.5-flash-lite-preview-06-17","name":"Gemini 2.5 Flash Lite Preview 06-17","value":2.73},{"id":"gemini-2.5-flash-preview-05-20-thinking","name":"Gemini 2.5 Flash Preview 05-20 (thinking)","value":2.1475},{"id":"deepseek-r1-0528","name":"DeepSeek R1 0528","value":1.9423}],"bottom_3":[{"id":"openai-gpt","name":"GPT-1","value":0},{"id":"hunter-alpha","name":"Hunter Alpha","value":0},{"id":"gpt-5.4-mini","name":"GPT-5.4 Mini","value":0}]},{"feature":"horizontal_rule_rate","mean":0.3284,"stddev":0.2975,"cv":0.9058,"min":0,"max":1.3304,"range":1.3304,"top_3":[{"id":"claude-sonnet-4.6","name":"Claude Sonnet 4.6","value":1.3304},{"id":"chatgpt-4o-03-25","name":"ChatGPT-4o (March 2025)","value":1.0509},{"id":"gpt-5.3-codex","name":"GPT-5.3-Codex","value":0.9473}],"bottom_3":[{"id":"trinity-large-preview-free","name":"Trinity Large Preview","value":0},{"id":"sherlock-think-alpha","name":"Sherlock Think Alpha","value":0},{"id":"qwen3-0.6b-04-28","name":"Qwen3 0.6B","value":0}]},{"feature":"heading_rate","mean":0.7482,"stddev":0.5769,"cv":0.7711,"min":0,"max":2.516,"range":2.516,"top_3":[{"id":"gpt-5.4-pro","name":"GPT-5.4 Pro","value":2.516},{"id":"claude-haiku-4.5","name":"Claude Haiku 4.5","value":2.4555},{"id":"claude-sonnet-4","name":"Claude Sonnet 4","value":2.1561}],"bottom_3":[{"id":"trinity-large-preview-free","name":"Trinity Large Preview","value":0},{"id":"qwq-32b","name":"QwQ 32B","value":0},{"id":"qwen3-30b-a3b","name":"Qwen3 30B A3B","value":0}]},{"feature":"transition_rate","mean":0.1488,"stddev":0.1106,"cv":0.7433,"min":0,"max":0.5363,"range":0.5363,"top_3":[{"id":"gpt-4.5","name":"GPT-4.5","value":0.5363},{"id":"sherlock-think-alpha","name":"Sherlock Think Alpha","value":0.4721},{"id":"gpt-4","name":"GPT-4","value":0.4513}],"bottom_3":[{"id":"mimo-v2-pro","name":"MiMo-V2-Pro","value":0},{"id":"gpt-2","name":"GPT-2","value":0},{"id":"gemini-2.5-flash-preview-05-20-thinking","name":"Gemini 2.5 Flash Preview 05-20 (thinking)","value":0}]},{"feature":"avg_paragraph_length","mean":46.8306,"stddev":34.4907,"cv":0.7365,"min":20.89,"max":324.6,"range":303.71,"top_3":[{"id":"llama-3.1-405b","name":"Llama 3.1 405B","value":324.6},{"id":"minimax-m2-her","name":"MiniMax M2-her","value":258.3034},{"id":"o4-mini-high","name":"OpenAI o4 Mini High","value":203.9532}],"bottom_3":[{"id":"claude-opus-4.5","name":"Claude Opus 4.5","value":20.89},{"id":"gpt-5.1","name":"GPT-5.1","value":21.223},{"id":"gpt-5.2-chat","name":"GPT-5.2 Chat","value":21.9132}]},{"feature":"avg_sentence_length","mean":22.0155,"stddev":15.0949,"cv":0.6856,"min":10.0048,"max":110.9862,"range":100.9814,"top_3":[{"id":"claude-sonnet-4","name":"Claude Sonnet 4","value":110.9862},{"id":"claude-4.5-sonnet","name":"Claude Sonnet 4.5","value":93.7986},{"id":"qwen3-coder-flash","name":"Qwen3 Coder Flash","value":92.3527}],"bottom_3":[{"id":"gemini-2.5-flash-lite-preview-06-17","name":"Gemini 2.5 Flash Lite Preview 06-17","value":10.0048},{"id":"deepseek-r1-0528","name":"DeepSeek R1 0528","value":10.3578},{"id":"gemini-2.5-flash-preview-05-20-thinking","name":"Gemini 2.5 Flash Preview 05-20 (thinking)","value":11.1204}]},{"feature":"question_rate","mean":0.7586,"stddev":0.4627,"cv":0.61,"min":0,"max":3.161,"range":3.161,"top_3":[{"id":"gemini-2.5-flash-lite-preview-06-17","name":"Gemini 2.5 Flash Lite Preview 06-17","value":3.161},{"id":"qwen3-0.6b-04-28","name":"Qwen3 0.6B","value":2.9271},{"id":"deepseek-r1-0528","name":"DeepSeek R1 0528","value":2.7016}],"bottom_3":[{"id":"gpt-2","name":"GPT-2","value":0},{"id":"golden-gate-claude","name":"Golden Gate Claude","value":0},{"id":"mistral-nemo","name":"Mistral Nemo","value":0.0128}]},{"feature":"parenthetical_rate","mean":1.7995,"stddev":1.0755,"cv":0.5977,"min":0,"max":6.1897,"range":6.1897,"top_3":[{"id":"claude-opus-4","name":"Claude Opus 4","value":6.1897},{"id":"mistral-large","name":"Mistral Large","value":5.2403},{"id":"mistral-small-creative","name":"Mistral Small Creative","value":4.7782}],"bottom_3":[{"id":"claude-3-opus","name":"Claude 3 Opus","value":0},{"id":"gpt-3.5-turbo","name":"GPT-3.5 Turbo","value":0.0325},{"id":"openai-gpt","name":"GPT-1","value":0.1232}]},{"feature":"first_person_rate","mean":0.9774,"stddev":0.5811,"cv":0.5946,"min":0,"max":3.7106,"range":3.7106,"top_3":[{"id":"openai-gpt","name":"GPT-1","value":3.7106},{"id":"gemini-2.5-flash-lite-preview-06-17","name":"Gemini 2.5 Flash Lite Preview 06-17","value":3.5623},{"id":"qwen3-0.6b-04-28","name":"Qwen3 0.6B","value":3.398}],"bottom_3":[{"id":"mistral-nemo","name":"Mistral Nemo","value":0},{"id":"llama-4-scout","name":"Llama 4 Scout","value":0},{"id":"llama-4-maverick","name":"Llama 4 Maverick","value":0.0694}]},{"feature":"bold_rate","mean":4.9154,"stddev":2.7992,"cv":0.5695,"min":0,"max":14.376,"range":14.376,"top_3":[{"id":"mistral-large-2","name":"Mistral Large 2","value":14.376},{"id":"mistral-small-creative","name":"Mistral Small Creative","value":13.6547},{"id":"qwq-32b","name":"QwQ 32B","value":13.6074}],"bottom_3":[{"id":"polaris-alpha","name":"Polaris Alpha","value":0},{"id":"openai-gpt","name":"GPT-1","value":0},{"id":"o4-mini-high","name":"OpenAI o4 Mini High","value":0}]},{"feature":"booster_rate","mean":0.2071,"stddev":0.115,"cv":0.5552,"min":0,"max":0.6995,"range":0.6995,"top_3":[{"id":"o1","name":"o1","value":0.6995},{"id":"claude-opus-4","name":"Claude Opus 4","value":0.6019},{"id":"claude-4.5-sonnet","name":"Claude Sonnet 4.5","value":0.4977}],"bottom_3":[{"id":"qwq-32b","name":"QwQ 32B","value":0},{"id":"openai-gpt","name":"GPT-1","value":0},{"id":"gpt-2","name":"GPT-2","value":0}]},{"feature":"second_person_rate","mean":0.9739,"stddev":0.5387,"cv":0.5531,"min":0.2993,"max":5.6766,"range":5.3773,"top_3":[{"id":"gpt-2","name":"GPT-2","value":5.6766},{"id":"claude-3-opus","name":"Claude 3 Opus","value":3.6906},{"id":"o4-mini","name":"OpenAI o4-mini","value":2.2986}],"bottom_3":[{"id":"mistral-large-2","name":"Mistral Large 2","value":0.2993},{"id":"minimax-m1","name":"MiniMax M1","value":0.3209},{"id":"mistral-large","name":"Mistral Large","value":0.393}]},{"feature":"filler_rate","mean":0.2871,"stddev":0.1567,"cv":0.5458,"min":0,"max":1.1621,"range":1.1621,"top_3":[{"id":"openai-gpt","name":"GPT-1","value":1.1621},{"id":"gpt-5.1-chat","name":"GPT-5.1 Chat","value":0.8434},{"id":"glm-4.7-flash","name":"GLM 4.7 Flash","value":0.7741}],"bottom_3":[{"id":"gpt-2","name":"GPT-2","value":0},{"id":"llama-4-scout","name":"Llama 4 Scout","value":0.0432},{"id":"llama-4-maverick","name":"Llama 4 Maverick","value":0.0464}]},{"feature":"colon_rate","mean":3.3212,"stddev":1.6015,"cv":0.4822,"min":0,"max":19.6197,"range":19.6197,"top_3":[{"id":"claude-opus-4","name":"Claude Opus 4","value":19.6197},{"id":"minimax-m1","name":"MiniMax M1","value":5.5883},{"id":"kimi-k2.5","name":"Kimi K2.5","value":5.5086}],"bottom_3":[{"id":"openai-gpt","name":"GPT-1","value":0},{"id":"gpt-2","name":"GPT-2","value":0.7327},{"id":"claude-3-opus","name":"Claude 3 Opus","value":0.944}]},{"feature":"hedging_rate","mean":0.4785,"stddev":0.2194,"cv":0.4585,"min":0,"max":1.1112,"range":1.1112,"top_3":[{"id":"grok-3-thinking","name":"Grok 3 Thinking","value":1.1112},{"id":"gpt-4","name":"GPT-4","value":1.1},{"id":"mistral-nemo","name":"Mistral Nemo","value":1.0757}],"bottom_3":[{"id":"gpt-2","name":"GPT-2","value":0},{"id":"gemini-2.5-flash-preview-05-20-thinking","name":"Gemini 2.5 Flash Preview 05-20 (thinking)","value":0},{"id":"golden-gate-claude","name":"Golden Gate Claude","value":0.0842}]},{"feature":"list_item_rate","mean":4.3572,"stddev":1.8221,"cv":0.4182,"min":0,"max":11.2577,"range":11.2577,"top_3":[{"id":"polaris-alpha","name":"Polaris Alpha","value":11.2577},{"id":"claude-sonnet-4","name":"Claude Sonnet 4","value":9.263},{"id":"claude-opus-4","name":"Claude Opus 4","value":9.1423}],"bottom_3":[{"id":"qwen3-0.6b-04-28","name":"Qwen3 0.6B","value":0},{"id":"gpt-2","name":"GPT-2","value":0},{"id":"openai-gpt","name":"GPT-1","value":0.269}]},{"feature":"comma_rate","mean":5.4927,"stddev":0.9723,"cv":0.177,"min":2.7135,"max":8.6577,"range":5.9442,"top_3":[{"id":"claude-opus-4","name":"Claude Opus 4","value":8.6577},{"id":"qwen3-235b-a22b-07-25","name":"Qwen: Qwen3 235B A22B 2507","value":7.8494},{"id":"mistral-large","name":"Mistral Large","value":7.7437}],"bottom_3":[{"id":"claude-3.5-sonnet","name":"Claude Sonnet 3.6 (2022-10-22)","value":2.7135},{"id":"llama-3.1-405b","name":"Llama 3.1 405B","value":2.8368},{"id":"gemini-3-flash-preview","name":"Gemini 3 Flash Preview","value":3.5782}]},{"feature":"hapax_ratio","mean":0.4236,"stddev":0.0705,"cv":0.1664,"min":0.2525,"max":0.6197,"range":0.3672,"top_3":[{"id":"o4-mini","name":"OpenAI o4-mini","value":0.6197},{"id":"gpt-5.1-chat","name":"GPT-5.1 Chat","value":0.6082},{"id":"sherlock-dash-alpha","name":"Sherlock Dash Alpha","value":0.5895}],"bottom_3":[{"id":"llama-4-maverick","name":"Llama 4 Maverick","value":0.2525},{"id":"llama-4-scout","name":"Llama 4 Scout","value":0.26},{"id":"mistral-large-2","name":"Mistral Large 2","value":0.2722}]},{"feature":"type_token_ratio","mean":0.5718,"stddev":0.0643,"cv":0.1125,"min":0.4213,"max":0.7338,"range":0.3125,"top_3":[{"id":"o4-mini","name":"OpenAI o4-mini","value":0.7338},{"id":"gpt-5.1-chat","name":"GPT-5.1 Chat","value":0.7322},{"id":"sherlock-dash-alpha","name":"Sherlock Dash Alpha","value":0.717}],"bottom_3":[{"id":"llama-4-maverick","name":"Llama 4 Maverick","value":0.4213},{"id":"mistral-large-2","name":"Mistral Large 2","value":0.4291},{"id":"llama-4-scout","name":"Llama 4 Scout","value":0.4305}]},{"feature":"avg_word_length","mean":5.2466,"stddev":0.2905,"cv":0.0554,"min":4.0704,"max":5.8759,"range":1.8055,"top_3":[{"id":"qwen3-max-thinking","name":"Qwen: Qwen3 Max Thinking","value":5.8759},{"id":"llama-4-scout","name":"Llama 4 Scout","value":5.7458},{"id":"qwen3-coder","name":"Qwen3 Coder","value":5.7237}],"bottom_3":[{"id":"openai-gpt","name":"GPT-1","value":4.0704},{"id":"gpt-2","name":"GPT-2","value":4.3552},{"id":"gemini-2.5-flash-preview-05-20-thinking","name":"Gemini 2.5 Flash Preview 05-20 (thinking)","value":4.4274}]},{"feature":"code_block_rate","mean":0,"stddev":1,"cv":0,"min":0,"max":0,"range":0,"top_3":[{"id":"andromeda-alpha","name":"Andromeda Alpha","value":0},{"id":"aurora-alpha","name":"Aurora Alpha","value":0},{"id":"bert-nebulon-alpha","name":"Bert-Nebulon Alpha","value":0}],"bottom_3":[{"id":"trinity-large-preview-free","name":"Trinity Large Preview","value":0},{"id":"tng-r1t-chimera-free","name":"TNG R1T Chimera","value":0},{"id":"sonoma-sky-alpha","name":"Sonoma Sky Alpha","value":0}]},{"feature":"opens_with_heading_rate","mean":0,"stddev":1,"cv":0,"min":0,"max":0,"range":0,"top_3":[{"id":"andromeda-alpha","name":"Andromeda Alpha","value":0},{"id":"aurora-alpha","name":"Aurora Alpha","value":0},{"id":"bert-nebulon-alpha","name":"Bert-Nebulon Alpha","value":0}],"bottom_3":[{"id":"trinity-large-preview-free","name":"Trinity Large Preview","value":0},{"id":"tng-r1t-chimera-free","name":"TNG R1T Chimera","value":0},{"id":"sonoma-sky-alpha","name":"Sonoma Sky Alpha","value":0}]},{"feature":"opens_with_greeting_rate","mean":0,"stddev":1,"cv":0,"min":0,"max":0,"range":0,"top_3":[{"id":"andromeda-alpha","name":"Andromeda Alpha","value":0},{"id":"aurora-alpha","name":"Aurora Alpha","value":0},{"id":"bert-nebulon-alpha","name":"Bert-Nebulon Alpha","value":0}],"bottom_3":[{"id":"trinity-large-preview-free","name":"Trinity Large Preview","value":0},{"id":"tng-r1t-chimera-free","name":"TNG R1T Chimera","value":0},{"id":"sonoma-sky-alpha","name":"Sonoma Sky Alpha","value":0}]},{"feature":"opens_with_first_person_rate","mean":0,"stddev":1,"cv":0,"min":0,"max":0,"range":0,"top_3":[{"id":"andromeda-alpha","name":"Andromeda Alpha","value":0},{"id":"aurora-alpha","name":"Aurora Alpha","value":0},{"id":"bert-nebulon-alpha","name":"Bert-Nebulon Alpha","value":0}],"bottom_3":[{"id":"trinity-large-preview-free","name":"Trinity Large Preview","value":0},{"id":"tng-r1t-chimera-free","name":"TNG R1T Chimera","value":0},{"id":"sonoma-sky-alpha","name":"Sonoma Sky Alpha","value":0}]},{"feature":"opens_with_emoji_rate","mean":0,"stddev":1,"cv":0,"min":0,"max":0,"range":0,"top_3":[{"id":"andromeda-alpha","name":"Andromeda Alpha","value":0},{"id":"aurora-alpha","name":"Aurora Alpha","value":0},{"id":"bert-nebulon-alpha","name":"Bert-Nebulon Alpha","value":0}],"bottom_3":[{"id":"trinity-large-preview-free","name":"Trinity Large Preview","value":0},{"id":"tng-r1t-chimera-free","name":"TNG R1T Chimera","value":0},{"id":"sonoma-sky-alpha","name":"Sonoma Sky Alpha","value":0}]}],"convergence_features":[{"feature":"code_block_rate","mean":0,"stddev":1,"cv":0,"min":0,"max":0,"range":0,"top_3":[{"id":"andromeda-alpha","name":"Andromeda Alpha","value":0},{"id":"aurora-alpha","name":"Aurora Alpha","value":0},{"id":"bert-nebulon-alpha","name":"Bert-Nebulon Alpha","value":0}],"bottom_3":[{"id":"trinity-large-preview-free","name":"Trinity Large Preview","value":0},{"id":"tng-r1t-chimera-free","name":"TNG R1T Chimera","value":0},{"id":"sonoma-sky-alpha","name":"Sonoma Sky Alpha","value":0}]},{"feature":"opens_with_heading_rate","mean":0,"stddev":1,"cv":0,"min":0,"max":0,"range":0,"top_3":[{"id":"andromeda-alpha","name":"Andromeda Alpha","value":0},{"id":"aurora-alpha","name":"Aurora Alpha","value":0},{"id":"bert-nebulon-alpha","name":"Bert-Nebulon Alpha","value":0}],"bottom_3":[{"id":"trinity-large-preview-free","name":"Trinity Large Preview","value":0},{"id":"tng-r1t-chimera-free","name":"TNG R1T Chimera","value":0},{"id":"sonoma-sky-alpha","name":"Sonoma Sky Alpha","value":0}]},{"feature":"opens_with_greeting_rate","mean":0,"stddev":1,"cv":0,"min":0,"max":0,"range":0,"top_3":[{"id":"andromeda-alpha","name":"Andromeda Alpha","value":0},{"id":"aurora-alpha","name":"Aurora Alpha","value":0},{"id":"bert-nebulon-alpha","name":"Bert-Nebulon Alpha","value":0}],"bottom_3":[{"id":"trinity-large-preview-free","name":"Trinity Large Preview","value":0},{"id":"tng-r1t-chimera-free","name":"TNG R1T Chimera","value":0},{"id":"sonoma-sky-alpha","name":"Sonoma Sky Alpha","value":0}]},{"feature":"opens_with_first_person_rate","mean":0,"stddev":1,"cv":0,"min":0,"max":0,"range":0,"top_3":[{"id":"andromeda-alpha","name":"Andromeda Alpha","value":0},{"id":"aurora-alpha","name":"Aurora Alpha","value":0},{"id":"bert-nebulon-alpha","name":"Bert-Nebulon Alpha","value":0}],"bottom_3":[{"id":"trinity-large-preview-free","name":"Trinity Large Preview","value":0},{"id":"tng-r1t-chimera-free","name":"TNG R1T Chimera","value":0},{"id":"sonoma-sky-alpha","name":"Sonoma Sky Alpha","value":0}]},{"feature":"opens_with_emoji_rate","mean":0,"stddev":1,"cv":0,"min":0,"max":0,"range":0,"top_3":[{"id":"andromeda-alpha","name":"Andromeda Alpha","value":0},{"id":"aurora-alpha","name":"Aurora Alpha","value":0},{"id":"bert-nebulon-alpha","name":"Bert-Nebulon Alpha","value":0}],"bottom_3":[{"id":"trinity-large-preview-free","name":"Trinity Large Preview","value":0},{"id":"tng-r1t-chimera-free","name":"TNG R1T Chimera","value":0},{"id":"sonoma-sky-alpha","name":"Sonoma Sky Alpha","value":0}]},{"feature":"avg_word_length","mean":5.2466,"stddev":0.2905,"cv":0.0554,"min":4.0704,"max":5.8759,"range":1.8055,"top_3":[{"id":"qwen3-max-thinking","name":"Qwen: Qwen3 Max Thinking","value":5.8759},{"id":"llama-4-scout","name":"Llama 4 Scout","value":5.7458},{"id":"qwen3-coder","name":"Qwen3 Coder","value":5.7237}],"bottom_3":[{"id":"openai-gpt","name":"GPT-1","value":4.0704},{"id":"gpt-2","name":"GPT-2","value":4.3552},{"id":"gemini-2.5-flash-preview-05-20-thinking","name":"Gemini 2.5 Flash Preview 05-20 (thinking)","value":4.4274}]},{"feature":"type_token_ratio","mean":0.5718,"stddev":0.0643,"cv":0.1125,"min":0.4213,"max":0.7338,"range":0.3125,"top_3":[{"id":"o4-mini","name":"OpenAI o4-mini","value":0.7338},{"id":"gpt-5.1-chat","name":"GPT-5.1 Chat","value":0.7322},{"id":"sherlock-dash-alpha","name":"Sherlock Dash Alpha","value":0.717}],"bottom_3":[{"id":"llama-4-maverick","name":"Llama 4 Maverick","value":0.4213},{"id":"mistral-large-2","name":"Mistral Large 2","value":0.4291},{"id":"llama-4-scout","name":"Llama 4 Scout","value":0.4305}]},{"feature":"hapax_ratio","mean":0.4236,"stddev":0.0705,"cv":0.1664,"min":0.2525,"max":0.6197,"range":0.3672,"top_3":[{"id":"o4-mini","name":"OpenAI o4-mini","value":0.6197},{"id":"gpt-5.1-chat","name":"GPT-5.1 Chat","value":0.6082},{"id":"sherlock-dash-alpha","name":"Sherlock Dash Alpha","value":0.5895}],"bottom_3":[{"id":"llama-4-maverick","name":"Llama 4 Maverick","value":0.2525},{"id":"llama-4-scout","name":"Llama 4 Scout","value":0.26},{"id":"mistral-large-2","name":"Mistral Large 2","value":0.2722}]},{"feature":"comma_rate","mean":5.4927,"stddev":0.9723,"cv":0.177,"min":2.7135,"max":8.6577,"range":5.9442,"top_3":[{"id":"claude-opus-4","name":"Claude Opus 4","value":8.6577},{"id":"qwen3-235b-a22b-07-25","name":"Qwen: Qwen3 235B A22B 2507","value":7.8494},{"id":"mistral-large","name":"Mistral Large","value":7.7437}],"bottom_3":[{"id":"claude-3.5-sonnet","name":"Claude Sonnet 3.6 (2022-10-22)","value":2.7135},{"id":"llama-3.1-405b","name":"Llama 3.1 405B","value":2.8368},{"id":"gemini-3-flash-preview","name":"Gemini 3 Flash Preview","value":3.5782}]},{"feature":"list_item_rate","mean":4.3572,"stddev":1.8221,"cv":0.4182,"min":0,"max":11.2577,"range":11.2577,"top_3":[{"id":"polaris-alpha","name":"Polaris Alpha","value":11.2577},{"id":"claude-sonnet-4","name":"Claude Sonnet 4","value":9.263},{"id":"claude-opus-4","name":"Claude Opus 4","value":9.1423}],"bottom_3":[{"id":"qwen3-0.6b-04-28","name":"Qwen3 0.6B","value":0},{"id":"gpt-2","name":"GPT-2","value":0},{"id":"openai-gpt","name":"GPT-1","value":0.269}]}],"outliers":{"most_unique":[{"id":"gemini-2.5-flash-preview-05-20-thinking","name":"Gemini 2.5 Flash Preview 05-20 (thinking)","provider":"google","family":"Gemini","avg_similarity":-0.0476,"response_count":3},{"id":"gemini-2.5-flash-lite-preview-06-17","name":"Gemini 2.5 Flash Lite Preview 06-17","provider":"google","family":"Gemini","avg_similarity":-0.0472,"response_count":3},{"id":"minimax-m2-her","name":"MiniMax M2-her","provider":"minimax","family":null,"avg_similarity":-0.0425,"response_count":24},{"id":"deepseek-r1-0528","name":"DeepSeek R1 0528","provider":"deepseek","family":"DeepSeek R1","avg_similarity":-0.0398,"response_count":4},{"id":"qwen3-0.6b-04-28","name":"Qwen3 0.6B","provider":"qwen","family":"Qwen","avg_similarity":-0.0394,"response_count":7},{"id":"claude-sonnet-4","name":"Claude Sonnet 4","provider":"anthropic","family":"Claude","avg_similarity":-0.0379,"response_count":17},{"id":"o4-mini","name":"OpenAI o4-mini","provider":"openai","family":"o-series","avg_similarity":-0.0376,"response_count":10},{"id":"claude-4.5-sonnet","name":"Claude Sonnet 4.5","provider":"anthropic","family":null,"avg_similarity":-0.0368,"response_count":20},{"id":"qwen3-30b-a3b","name":"Qwen3 30B A3B","provider":"qwen","family":"Qwen","avg_similarity":-0.0364,"response_count":4},{"id":"sherlock-dash-alpha","name":"Sherlock Dash Alpha","provider":"openrouter","family":null,"avg_similarity":-0.0363,"response_count":14},{"id":"sherlock-think-alpha","name":"Sherlock Think Alpha","provider":"openrouter","family":null,"avg_similarity":-0.0363,"response_count":14},{"id":"o4-mini-high","name":"OpenAI o4 Mini High","provider":"openai","family":"o-series","avg_similarity":-0.0357,"response_count":14},{"id":"qwen3-max","name":"Qwen: Qwen3 Max","provider":"qwen","family":"Qwen","avg_similarity":-0.0346,"response_count":22},{"id":"qwen3-coder-plus","name":"Qwen3 Coder Plus","provider":"qwen","family":null,"avg_similarity":-0.0342,"response_count":22},{"id":"sonoma-sky-alpha","name":"Sonoma Sky Alpha","provider":"openrouter","family":null,"avg_similarity":-0.0311,"response_count":14},{"id":"qwen3-coder-flash","name":"Qwen3 Coder Flash","provider":"qwen","family":null,"avg_similarity":-0.0308,"response_count":22},{"id":"claude-opus-4.1","name":"Claude Opus 4.1","provider":"anthropic","family":"Claude","avg_similarity":-0.0304,"response_count":17},{"id":"claude-3-opus","name":"Claude 3 Opus","provider":"anthropic","family":"Claude","avg_similarity":-0.0302,"response_count":3},{"id":"claude-3.5-sonnet","name":"Claude Sonnet 3.6 (2022-10-22)","provider":"anthropic","family":"Claude","avg_similarity":-0.03,"response_count":21},{"id":"claude-opus-4.5","name":"Claude Opus 4.5","provider":"anthropic","family":null,"avg_similarity":-0.0298,"response_count":24}],"most_generic":[{"id":"gemini-2.5-flash-lite-preview-09-2025","name":"Google: Gemini 2.5 Flash Lite Preview 09-2025","provider":"google","family":null,"avg_similarity":0.0526,"response_count":22},{"id":"gemma-3n-e4b-it","name":"Gemma 3n 4B","provider":"google","family":null,"avg_similarity":0.0401,"response_count":12},{"id":"llama-4-maverick","name":"Llama 4 Maverick","provider":"meta","family":"Llama","avg_similarity":0.0392,"response_count":12},{"id":"glm-4.5-air","name":"Z.AI: GLM 4.5 Air","provider":"zhipu","family":null,"avg_similarity":0.0391,"response_count":15},{"id":"qwen3.5-flash-02-23","name":"Qwen: Qwen3.5 Flash","provider":"qwen","family":"Qwen","avg_similarity":0.0361,"response_count":23},{"id":"glm-5","name":"Z.ai: GLM 5","provider":"zhipu","family":null,"avg_similarity":0.0354,"response_count":22},{"id":"gpt-5.4-nano","name":"GPT-5.4 Nano","provider":"openai","family":"GPT-5","avg_similarity":0.0349,"response_count":23},{"id":"qwen3.5-plus-02-15","name":"Qwen: Qwen3.5 Plus 2026-02-15","provider":"qwen","family":"Qwen","avg_similarity":0.0334,"response_count":23},{"id":"minimax-m2.5","name":"MiniMax M2.5","provider":"minimax","family":"MiniMax","avg_similarity":0.0331,"response_count":23},{"id":"gpt-4o","name":"GPT-4o (Omni)","provider":"openai","family":"GPT","avg_similarity":0.0331,"response_count":24},{"id":"devstral-medium","name":"Mistral Devstral Medium","provider":"mistral","family":null,"avg_similarity":0.0322,"response_count":21},{"id":"gemini-2.5-flash-preview-09-2025","name":"Google: Gemini 2.5 Flash Preview 09-2025","provider":"google","family":null,"avg_similarity":0.0312,"response_count":22},{"id":"mistral-nemo","name":"Mistral Nemo","provider":"mistral","family":"Mistral","avg_similarity":0.0291,"response_count":10},{"id":"qwen3.5-9b","name":"Qwen3.5 9B","provider":"qwen","family":"Qwen","avg_similarity":0.0288,"response_count":21},{"id":"deepseek-chat-v3.1","name":"DeepSeek V3.1","provider":"deepseek","family":"DeepSeek","avg_similarity":0.0288,"response_count":23},{"id":"qwen3.5-27b","name":"Qwen: Qwen3.5 27B","provider":"qwen","family":"Qwen","avg_similarity":0.0282,"response_count":23},{"id":"qwen3.5-35b-a3b","name":"Qwen: Qwen3.5 35B A3B","provider":"qwen","family":"Qwen","avg_similarity":0.0281,"response_count":23},{"id":"gemini-3-flash-preview","name":"Gemini 3 Flash Preview","provider":"google","family":null,"avg_similarity":0.028,"response_count":24},{"id":"solar-pro-3-free","name":"Solar Pro 3","provider":"upstage","family":null,"avg_similarity":0.0271,"response_count":18},{"id":"mistral-small-2603","name":"Mistral Small 4","provider":"mistral","family":null,"avg_similarity":0.0269,"response_count":23}]},"size_analysis":{"medium":{"model_count":28,"intra_similarity":0.0049,"inter_similarity":-0.0007},"large":{"model_count":67,"intra_similarity":0.004,"inter_similarity":-0.0012},"xlarge":{"model_count":68,"intra_similarity":-0.0033,"inter_similarity":-0.0013},"small":{"model_count":15,"intra_similarity":0.0013,"inter_similarity":0.0064}},"consistency":{"most_consistent":[{"id":"gpt-2","name":"GPT-2","provider":"openai","avg_cv":0.4192,"response_count":7},{"id":"claude-3-opus","name":"Claude 3 Opus","provider":"anthropic","avg_cv":0.5429,"response_count":3},{"id":"gemini-2.5-flash-preview-05-20-thinking","name":"Gemini 2.5 Flash Preview 05-20 (thinking)","provider":"google","avg_cv":0.5793,"response_count":3},{"id":"openai-gpt","name":"GPT-1","provider":"openai","avg_cv":0.6421,"response_count":7},{"id":"claude-3-sonnet","name":"Claude 3 Sonnet","provider":"anthropic","avg_cv":0.69,"response_count":4},{"id":"golden-gate-claude","name":"Golden Gate Claude","provider":"anthropic","avg_cv":0.7217,"response_count":6},{"id":"mistral-nemo","name":"Mistral Nemo","provider":"mistral","avg_cv":0.7915,"response_count":10},{"id":"deepseek-r1-0528","name":"DeepSeek R1 0528","provider":"deepseek","avg_cv":0.8132,"response_count":4},{"id":"qwq-32b","name":"QwQ 32B","provider":"qwen","avg_cv":0.8405,"response_count":4},{"id":"gemini-2.5-flash-lite-preview-06-17","name":"Gemini 2.5 Flash Lite Preview 06-17","provider":"google","avg_cv":0.8648,"response_count":3},{"id":"llama-3.1-405b","name":"Llama 3.1 405B","provider":"meta","avg_cv":0.8653,"response_count":5},{"id":"grok-3-thinking","name":"Grok 3 Thinking","provider":"xai","avg_cv":0.8974,"response_count":6},{"id":"gemini-2.0-flash-thinking-exp","name":"Gemini 2.0 Flash Thinking","provider":"google","avg_cv":0.9083,"response_count":13},{"id":"qwen3-0.6b-04-28","name":"Qwen3 0.6B","provider":"qwen","avg_cv":0.9246,"response_count":7},{"id":"gpt-3.5-turbo","name":"GPT-3.5 Turbo","provider":"openai","avg_cv":0.9282,"response_count":11},{"id":"horizon-beta","name":"Horizon Beta","provider":"openrouter","avg_cv":0.9316,"response_count":16},{"id":"qwen3-30b-a3b","name":"Qwen3 30B A3B","provider":"qwen","avg_cv":0.938,"response_count":4},{"id":"o4-mini","name":"OpenAI o4-mini","provider":"openai","avg_cv":0.9568,"response_count":10},{"id":"gpt-5.2-pro","name":"GPT-5.2 Pro","provider":"openai","avg_cv":0.9574,"response_count":10},{"id":"llama-4-scout","name":"Llama 4 Scout","provider":"meta","avg_cv":0.9732,"response_count":10}],"most_variable":[{"id":"claude-opus-4","name":"Claude Opus 4","provider":"anthropic","avg_cv":2.0102,"response_count":16},{"id":"minimax-m2-her","name":"MiniMax M2-her","provider":"minimax","avg_cv":1.9009,"response_count":24},{"id":"gpt-4o","name":"GPT-4o (Omni)","provider":"openai","avg_cv":1.8614,"response_count":24},{"id":"kimi-k2-0905","name":"MoonshotAI: Kimi K2 0905","provider":"moonshotai","avg_cv":1.7974,"response_count":22},{"id":"gpt-5","name":"GPT-5","provider":"openai","avg_cv":1.7617,"response_count":16},{"id":"claude-opus-4.1","name":"Claude Opus 4.1","provider":"anthropic","avg_cv":1.728,"response_count":17},{"id":"qwen3-coder","name":"Qwen3 Coder","provider":"qwen","avg_cv":1.6707,"response_count":22},{"id":"gpt-oss-20b","name":"GPT OSS 20B","provider":"openai","avg_cv":1.6604,"response_count":21},{"id":"claude-sonnet-4","name":"Claude Sonnet 4","provider":"anthropic","avg_cv":1.6541,"response_count":17},{"id":"kimi-k2","name":"Kimi K2","provider":"moonshotai","avg_cv":1.6526,"response_count":22},{"id":"qwen3.5-27b","name":"Qwen: Qwen3.5 27B","provider":"qwen","avg_cv":1.6431,"response_count":23},{"id":"gpt-4.1","name":"GPT-4.1","provider":"openai","avg_cv":1.6378,"response_count":25},{"id":"seed-2.0-lite","name":"Seed 2.0 Lite","provider":"bytedance","avg_cv":1.626,"response_count":23},{"id":"mercury","name":"Inception: Mercury","provider":"inception","avg_cv":1.6191,"response_count":17},{"id":"claude-3.7-sonnet-thinking","name":"Claude 3.7 Thinking Sonnet","provider":"anthropic","avg_cv":1.6166,"response_count":21},{"id":"grok-4.1-fast","name":"Grok 4.1 Fast","provider":"xai","avg_cv":1.6048,"response_count":24},{"id":"qwen3-coder-plus","name":"Qwen3 Coder Plus","provider":"qwen","avg_cv":1.6045,"response_count":22},{"id":"minimax-m2.1","name":"MiniMax: MiniMax M2.1","provider":"minimax","avg_cv":1.5988,"response_count":24},{"id":"claude-opus-4.5","name":"Claude Opus 4.5","provider":"anthropic","avg_cv":1.5909,"response_count":24},{"id":"qwen3.5-flash-02-23","name":"Qwen: Qwen3.5 Flash","provider":"qwen","avg_cv":1.5898,"response_count":23}]},"challenge_convergence":{"most_convergent":[{"challenge_id":"satirical-fake-news","model_count":135,"avg_similarity":0.0164,"pair_count":9045},{"challenge_id":"stochastic-consistency","model_count":166,"avg_similarity":0.0066,"pair_count":13695},{"challenge_id":"ai-ethics-dilemma","model_count":131,"avg_similarity":0.0022,"pair_count":8515},{"challenge_id":"debug-this-architecture","model_count":116,"avg_similarity":0.0021,"pair_count":6670},{"challenge_id":"michelin-star-recipe","model_count":121,"avg_similarity":0.002,"pair_count":7260},{"challenge_id":"estimate-complexity","model_count":142,"avg_similarity":0.0016,"pair_count":10011},{"challenge_id":"adversarial-contract-review","model_count":115,"avg_similarity":0.0015,"pair_count":6555},{"challenge_id":"historical-counterfactual-analysis","model_count":114,"avg_similarity":0.0007,"pair_count":6441},{"challenge_id":"simple-recipe","model_count":152,"avg_similarity":0.0006,"pair_count":11476},{"challenge_id":"futuristic-prediction","model_count":141,"avg_similarity":0.0005,"pair_count":9870}],"most_divergent":[{"challenge_id":"count-letters","model_count":22,"avg_similarity":-0.0254,"pair_count":231},{"challenge_id":"mini-lbo-underwrite","model_count":66,"avg_similarity":-0.0099,"pair_count":2145},{"challenge_id":"advanced-investment-memo","model_count":67,"avg_similarity":-0.0087,"pair_count":2211},{"challenge_id":"explain-like-im-a-specific-expert","model_count":115,"avg_similarity":-0.006,"pair_count":6555},{"challenge_id":"ethical-dilemma-with-stakeholders","model_count":119,"avg_similarity":-0.0045,"pair_count":7021},{"challenge_id":"startup-pitch-teardown","model_count":119,"avg_similarity":-0.0043,"pair_count":7021},{"challenge_id":"character-voice-test","model_count":132,"avg_similarity":-0.0037,"pair_count":8646},{"challenge_id":"ai-generated-manifesto","model_count":131,"avg_similarity":-0.0024,"pair_count":8515},{"challenge_id":"logic-puzzle","model_count":141,"avg_similarity":-0.0021,"pair_count":9870},{"challenge_id":"realistic-ai-interview","model_count":148,"avg_similarity":-0.0017,"pair_count":10878}],"all":[{"challenge_id":"satirical-fake-news","model_count":135,"avg_similarity":0.0164,"pair_count":9045},{"challenge_id":"stochastic-consistency","model_count":166,"avg_similarity":0.0066,"pair_count":13695},{"challenge_id":"ai-ethics-dilemma","model_count":131,"avg_similarity":0.0022,"pair_count":8515},{"challenge_id":"debug-this-architecture","model_count":116,"avg_similarity":0.0021,"pair_count":6670},{"challenge_id":"michelin-star-recipe","model_count":121,"avg_similarity":0.002,"pair_count":7260},{"challenge_id":"estimate-complexity","model_count":142,"avg_similarity":0.0016,"pair_count":10011},{"challenge_id":"adversarial-contract-review","model_count":115,"avg_similarity":0.0015,"pair_count":6555},{"challenge_id":"historical-counterfactual-analysis","model_count":114,"avg_similarity":0.0007,"pair_count":6441},{"challenge_id":"simple-recipe","model_count":152,"avg_similarity":0.0006,"pair_count":11476},{"challenge_id":"futuristic-prediction","model_count":141,"avg_similarity":0.0005,"pair_count":9870},{"challenge_id":"advanced-longevity-plan","model_count":120,"avg_similarity":0.0002,"pair_count":7140},{"challenge_id":"standup-routine","model_count":150,"avg_similarity":-0.0003,"pair_count":11175},{"challenge_id":"longevity-plan","model_count":153,"avg_similarity":-0.0009,"pair_count":11628},{"challenge_id":"math-misconception","model_count":96,"avg_similarity":-0.0013,"pair_count":4560},{"challenge_id":"sentience-test","model_count":151,"avg_similarity":-0.0013,"pair_count":11325},{"challenge_id":"realistic-ai-interview","model_count":148,"avg_similarity":-0.0017,"pair_count":10878},{"challenge_id":"logic-puzzle","model_count":141,"avg_similarity":-0.0021,"pair_count":9870},{"challenge_id":"ai-generated-manifesto","model_count":131,"avg_similarity":-0.0024,"pair_count":8515},{"challenge_id":"character-voice-test","model_count":132,"avg_similarity":-0.0037,"pair_count":8646},{"challenge_id":"startup-pitch-teardown","model_count":119,"avg_similarity":-0.0043,"pair_count":7021},{"challenge_id":"ethical-dilemma-with-stakeholders","model_count":119,"avg_similarity":-0.0045,"pair_count":7021},{"challenge_id":"explain-like-im-a-specific-expert","model_count":115,"avg_similarity":-0.006,"pair_count":6555},{"challenge_id":"advanced-investment-memo","model_count":67,"avg_similarity":-0.0087,"pair_count":2211},{"challenge_id":"mini-lbo-underwrite","model_count":66,"avg_similarity":-0.0099,"pair_count":2145},{"challenge_id":"count-letters","model_count":22,"avg_similarity":-0.0254,"pair_count":231}]},"head_to_head":[{"model_a":"mistral-large-2","model_b":"mistral-large-2512","name_a":"Mistral Large 2","name_b":"Mistral Large 3 2512","provider_a":"mistral","provider_b":"mistral","shared_challenges":10,"avg_similarity":0.8956,"stddev":0.0601,"min_similarity":0.7585,"max_similarity":0.9613,"confidence":0.8448,"aggregate_similarity":0.8929,"most_similar_on":"explain-like-im-a-specific-expert","least_similar_on":"longevity-plan"},{"model_a":"devstral-medium","model_b":"llama-4-maverick","name_a":"Mistral Devstral Medium","name_b":"Llama 4 Maverick","provider_a":"mistral","provider_b":"meta","shared_challenges":10,"avg_similarity":0.8089,"stddev":0.0691,"min_similarity":0.7238,"max_similarity":0.9301,"confidence":0.7566,"aggregate_similarity":0.7395,"most_similar_on":"michelin-star-recipe","least_similar_on":"longevity-plan"},{"model_a":"mistral-large","model_b":"mistral-large-2","name_a":"Mistral Large","name_b":"Mistral Large 2","provider_a":"mistral","provider_b":"mistral","shared_challenges":10,"avg_similarity":0.8299,"stddev":0.0984,"min_similarity":0.6383,"max_similarity":0.9472,"confidence":0.7556,"aggregate_similarity":0.7742,"most_similar_on":"historical-counterfactual-analysis","least_similar_on":"advanced-longevity-plan"},{"model_a":"qwen3.5-27b","model_b":"qwen3.5-35b-a3b","name_a":"Qwen: Qwen3.5 27B","name_b":"Qwen: Qwen3.5 35B A3B","provider_a":"qwen","provider_b":"qwen","shared_challenges":23,"avg_similarity":0.8297,"stddev":0.1095,"min_similarity":0.5351,"max_similarity":0.9884,"confidence":0.7478,"aggregate_similarity":0.911,"most_similar_on":"sentience-test","least_similar_on":"estimate-complexity"},{"model_a":"bert-nebulon-alpha","model_b":"mistral-large-2512","name_a":"Bert-Nebulon Alpha","name_b":"Mistral Large 3 2512","provider_a":"openrouter","provider_b":"mistral","shared_challenges":14,"avg_similarity":0.8254,"stddev":0.1289,"min_similarity":0.5506,"max_similarity":1,"confidence":0.7311,"aggregate_similarity":0.7378,"most_similar_on":"math-misconception","least_similar_on":"estimate-complexity"},{"model_a":"gemma-3-12b-it","model_b":"gemma-3n-e2b-it-free","name_a":"Gemma 3 12B","name_b":"Google: Gemma 3n 2B","provider_a":"google","provider_b":"google","shared_challenges":14,"avg_similarity":0.8126,"stddev":0.1154,"min_similarity":0.5976,"max_similarity":0.9613,"confidence":0.7285,"aggregate_similarity":0.7388,"most_similar_on":"advanced-longevity-plan","least_similar_on":"simple-recipe"},{"model_a":"aurora-alpha","model_b":"mercury-2","name_a":"Aurora Alpha","name_b":"Inception: Mercury 2","provider_a":"openrouter","provider_b":"inception","shared_challenges":22,"avg_similarity":0.8025,"stddev":0.1145,"min_similarity":0.5634,"max_similarity":0.9798,"confidence":0.7201,"aggregate_similarity":0.8895,"most_similar_on":"mini-lbo-underwrite","least_similar_on":"sentience-test"},{"model_a":"grok-3","model_b":"grok-4","name_a":"Grok 3","name_b":"xAI: Grok 4","provider_a":"xai","provider_b":"xai","shared_challenges":14,"avg_similarity":0.8141,"stddev":0.1329,"min_similarity":0.3745,"max_similarity":0.9433,"confidence":0.7186,"aggregate_similarity":0.778,"most_similar_on":"adversarial-contract-review","least_similar_on":"historical-counterfactual-analysis"},{"model_a":"llama-3.1-70b","model_b":"llama-4-maverick","name_a":"Llama 3.1 70B (Instruct)","name_b":"Llama 4 Maverick","provider_a":"meta","provider_b":"meta","shared_challenges":10,"avg_similarity":0.8013,"stddev":0.1294,"min_similarity":0.5725,"max_similarity":0.9509,"confidence":0.7095,"aggregate_similarity":0.7058,"most_similar_on":"simple-recipe","least_similar_on":"longevity-plan"},{"model_a":"qwen-plus-2025-07-28-thinking","model_b":"qwen3-30b-a3b-thinking-2507","name_a":"Qwen Plus 0728 (thinking)","name_b":"Qwen3 30B A3B Thinking 2507","provider_a":"qwen","provider_b":"qwen","shared_challenges":12,"avg_similarity":0.7788,"stddev":0.1021,"min_similarity":0.5369,"max_similarity":0.9419,"confidence":0.7067,"aggregate_similarity":0.7851,"most_similar_on":"logic-puzzle","least_similar_on":"satirical-fake-news"},{"model_a":"gemma-3n-e2b-it-free","model_b":"gemma-3n-e4b-it","name_a":"Google: Gemma 3n 2B","name_b":"Gemma 3n 4B","provider_a":"google","provider_b":"google","shared_challenges":10,"avg_similarity":0.8405,"stddev":0.1931,"min_similarity":0.2903,"max_similarity":0.9705,"confidence":0.7045,"aggregate_similarity":0.7555,"most_similar_on":"ethical-dilemma-with-stakeholders","least_similar_on":"startup-pitch-teardown"},{"model_a":"deepseek-v3-03-24","model_b":"mistral-medium-3","name_a":"DeepSeek V3 (March 2024)","name_b":"Mistral Medium 3","provider_a":"deepseek","provider_b":"mistral","shared_challenges":13,"avg_similarity":0.7703,"stddev":0.1013,"min_similarity":0.5453,"max_similarity":0.923,"confidence":0.6994,"aggregate_similarity":0.8004,"most_similar_on":"adversarial-contract-review","least_similar_on":"startup-pitch-teardown"},{"model_a":"llama-4-maverick","model_b":"mistral-nemo","name_a":"Llama 4 Maverick","name_b":"Mistral Nemo","provider_a":"meta","provider_b":"mistral","shared_challenges":10,"avg_similarity":0.7781,"stddev":0.1144,"min_similarity":0.5799,"max_similarity":0.9314,"confidence":0.6982,"aggregate_similarity":0.8637,"most_similar_on":"michelin-star-recipe","least_similar_on":"debug-this-architecture"},{"model_a":"qwen3.5-35b-a3b","model_b":"qwen3.5-flash-02-23","name_a":"Qwen: Qwen3.5 35B A3B","name_b":"Qwen: Qwen3.5 Flash","provider_a":"qwen","provider_b":"qwen","shared_challenges":23,"avg_similarity":0.7894,"stddev":0.1356,"min_similarity":0.3988,"max_similarity":0.98,"confidence":0.6951,"aggregate_similarity":0.8322,"most_similar_on":"sentience-test","least_similar_on":"satirical-fake-news"},{"model_a":"glm-5","model_b":"pony-alpha","name_a":"Z.ai: GLM 5","name_b":"Pony Alpha","provider_a":"zhipu","provider_b":"openrouter","shared_challenges":19,"avg_similarity":0.8054,"stddev":0.1742,"min_similarity":0.3996,"max_similarity":0.9941,"confidence":0.6859,"aggregate_similarity":0.7452,"most_similar_on":"logic-puzzle","least_similar_on":"simple-recipe"},{"model_a":"gpt-5.2","model_b":"gpt-5.2-chat","name_a":"GPT-5.2","name_b":"GPT-5.2 Chat","provider_a":"openai","provider_b":"openai","shared_challenges":15,"avg_similarity":0.7613,"stddev":0.124,"min_similarity":0.5467,"max_similarity":0.9871,"confidence":0.6773,"aggregate_similarity":0.8516,"most_similar_on":"logic-puzzle","least_similar_on":"ai-ethics-dilemma"},{"model_a":"horizon-alpha","model_b":"horizon-beta","name_a":"Horizon Alpha","name_b":"Horizon Beta","provider_a":"openrouter","provider_b":"openrouter","shared_challenges":14,"avg_similarity":0.7754,"stddev":0.1532,"min_similarity":0.4328,"max_similarity":0.9734,"confidence":0.6724,"aggregate_similarity":0.868,"most_similar_on":"standup-routine","least_similar_on":"math-misconception"},{"model_a":"grok-4-fast-free","model_b":"sonoma-dusk-alpha","name_a":"xAI: Grok 4 Fast (free)","name_b":"Sonoma Dusk Alpha","provider_a":"xai","provider_b":"openrouter","shared_challenges":14,"avg_similarity":0.7889,"stddev":0.1784,"min_similarity":0.2856,"max_similarity":0.9713,"confidence":0.6695,"aggregate_similarity":0.7567,"most_similar_on":"futuristic-prediction","least_similar_on":"math-misconception"},{"model_a":"qwen3.5-27b","model_b":"qwen3.5-flash-02-23","name_a":"Qwen: Qwen3.5 27B","name_b":"Qwen: Qwen3.5 Flash","provider_a":"qwen","provider_b":"qwen","shared_challenges":23,"avg_similarity":0.7739,"stddev":0.1636,"min_similarity":0.2614,"max_similarity":0.9912,"confidence":0.6651,"aggregate_similarity":0.8265,"most_similar_on":"sentience-test","least_similar_on":"satirical-fake-news"},{"model_a":"gemini-2.0-flash-thinking-exp","model_b":"gemini-2.5-flash-preview","name_a":"Gemini 2.0 Flash Thinking","name_b":"Gemini 2.5 Flash Preview","provider_a":"google","provider_b":"google","shared_challenges":10,"avg_similarity":0.8022,"stddev":0.2144,"min_similarity":0.2255,"max_similarity":0.9819,"confidence":0.6606,"aggregate_similarity":0.7053,"most_similar_on":"math-misconception","least_similar_on":"logic-puzzle"},{"model_a":"claude-opus-4.1","model_b":"qwen3-coder-plus","name_a":"Claude Opus 4.1","name_b":"Qwen3 Coder Plus","provider_a":"anthropic","provider_b":"qwen","shared_challenges":15,"avg_similarity":0.7818,"stddev":0.1859,"min_similarity":0.3317,"max_similarity":0.9772,"confidence":0.6593,"aggregate_similarity":0.7998,"most_similar_on":"michelin-star-recipe","least_similar_on":"startup-pitch-teardown"},{"model_a":"aurora-alpha","model_b":"solar-pro-3-free","name_a":"Aurora Alpha","name_b":"Solar Pro 3","provider_a":"openrouter","provider_b":"upstage","shared_challenges":17,"avg_similarity":0.7263,"stddev":0.1066,"min_similarity":0.5252,"max_similarity":0.9105,"confidence":0.6563,"aggregate_similarity":0.907,"most_similar_on":"futuristic-prediction","least_similar_on":"character-voice-test"},{"model_a":"gemma-3n-e4b-it","model_b":"glm-4.5-air","name_a":"Gemma 3n 4B","name_b":"Z.AI: GLM 4.5 Air","provider_a":"google","provider_b":"zhipu","shared_challenges":10,"avg_similarity":0.7456,"stddev":0.1369,"min_similarity":0.5179,"max_similarity":0.9043,"confidence":0.6559,"aggregate_similarity":0.8728,"most_similar_on":"explain-like-im-a-specific-expert","least_similar_on":"advanced-longevity-plan"},{"model_a":"gemma-3n-e4b-it","model_b":"llama-4-maverick","name_a":"Gemma 3n 4B","name_b":"Llama 4 Maverick","provider_a":"google","provider_b":"meta","shared_challenges":12,"avg_similarity":0.7314,"stddev":0.1177,"min_similarity":0.5142,"max_similarity":0.8589,"confidence":0.6544,"aggregate_similarity":0.8365,"most_similar_on":"explain-like-im-a-specific-expert","least_similar_on":"mini-lbo-underwrite"},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-9b","name_a":"Qwen: Qwen3.5 122B A10B","name_b":"Qwen3.5 9B","provider_a":"qwen","provider_b":"qwen","shared_challenges":21,"avg_similarity":0.7586,"stddev":0.1601,"min_similarity":0.4182,"max_similarity":0.9688,"confidence":0.6539,"aggregate_similarity":0.8466,"most_similar_on":"michelin-star-recipe","least_similar_on":"longevity-plan"},{"model_a":"qwen3.5-9b","model_b":"qwen3.5-flash-02-23","name_a":"Qwen3.5 9B","name_b":"Qwen: Qwen3.5 Flash","provider_a":"qwen","provider_b":"qwen","shared_challenges":21,"avg_similarity":0.7516,"stddev":0.1545,"min_similarity":0.2669,"max_similarity":0.9653,"confidence":0.651,"aggregate_similarity":0.838,"most_similar_on":"sentience-test","least_similar_on":"futuristic-prediction"},{"model_a":"mercury-2","model_b":"solar-pro-3-free","name_a":"Inception: Mercury 2","name_b":"Solar Pro 3","provider_a":"inception","provider_b":"upstage","shared_challenges":18,"avg_similarity":0.7576,"stddev":0.1672,"min_similarity":0.2686,"max_similarity":0.9149,"confidence":0.6491,"aggregate_similarity":0.9261,"most_similar_on":"futuristic-prediction","least_similar_on":"realistic-ai-interview"},{"model_a":"qwen3.5-35b-a3b","model_b":"qwen3.5-9b","name_a":"Qwen: Qwen3.5 35B A3B","name_b":"Qwen3.5 9B","provider_a":"qwen","provider_b":"qwen","shared_challenges":21,"avg_similarity":0.7645,"stddev":0.1783,"min_similarity":0.2091,"max_similarity":0.9612,"confidence":0.6488,"aggregate_similarity":0.7872,"most_similar_on":"standup-routine","least_similar_on":"debug-this-architecture"},{"model_a":"gpt-oss-120b","model_b":"mercury-2","name_a":"GPT OSS 120B","name_b":"Inception: Mercury 2","provider_a":"openai","provider_b":"inception","shared_challenges":21,"avg_similarity":0.7457,"stddev":0.1637,"min_similarity":0.4178,"max_similarity":0.9767,"confidence":0.6408,"aggregate_similarity":0.8682,"most_similar_on":"satirical-fake-news","least_similar_on":"sentience-test"},{"model_a":"devstral-small","model_b":"gemma-3n-e2b-it-free","name_a":"Mistral Devstral Small 1.1","name_b":"Google: Gemma 3n 2B","provider_a":"mistral","provider_b":"google","shared_challenges":14,"avg_similarity":0.7225,"stddev":0.1347,"min_similarity":0.4624,"max_similarity":0.9268,"confidence":0.6368,"aggregate_similarity":0.7829,"most_similar_on":"debug-this-architecture","least_similar_on":"realistic-ai-interview"},{"model_a":"claude-opus-4.1","model_b":"qwen3-coder","name_a":"Claude Opus 4.1","name_b":"Qwen3 Coder","provider_a":"anthropic","provider_b":"qwen","shared_challenges":15,"avg_similarity":0.7536,"stddev":0.1856,"min_similarity":0.1827,"max_similarity":0.9136,"confidence":0.6356,"aggregate_similarity":0.7793,"most_similar_on":"stochastic-consistency","least_similar_on":"debug-this-architecture"},{"model_a":"gpt-oss-120b","model_b":"solar-pro-3-free","name_a":"GPT OSS 120B","name_b":"Solar Pro 3","provider_a":"openai","provider_b":"upstage","shared_challenges":18,"avg_similarity":0.748,"stddev":0.1777,"min_similarity":0.1384,"max_similarity":0.9399,"confidence":0.6351,"aggregate_similarity":0.8727,"most_similar_on":"futuristic-prediction","least_similar_on":"character-voice-test"},{"model_a":"qwen3.5-27b","model_b":"qwen3.5-9b","name_a":"Qwen: Qwen3.5 27B","name_b":"Qwen3.5 9B","provider_a":"qwen","provider_b":"qwen","shared_challenges":21,"avg_similarity":0.7489,"stddev":0.1804,"min_similarity":0.3664,"max_similarity":0.9623,"confidence":0.6344,"aggregate_similarity":0.7327,"most_similar_on":"sentience-test","least_similar_on":"futuristic-prediction"},{"model_a":"llama-3.1-70b","model_b":"llama-4-scout","name_a":"Llama 3.1 70B (Instruct)","name_b":"Llama 4 Scout","provider_a":"meta","provider_b":"meta","shared_challenges":10,"avg_similarity":0.745,"stddev":0.1776,"min_similarity":0.4508,"max_similarity":0.9509,"confidence":0.6327,"aggregate_similarity":0.709,"most_similar_on":"simple-recipe","least_similar_on":"advanced-longevity-plan"},{"model_a":"glm-4.7","model_b":"glm-5","name_a":"Z.AI: GLM 4.7","name_b":"Z.ai: GLM 5","provider_a":"openrouter","provider_b":"zhipu","shared_challenges":20,"avg_similarity":0.7564,"stddev":0.1988,"min_similarity":0.3012,"max_similarity":0.9723,"confidence":0.6309,"aggregate_similarity":0.7818,"most_similar_on":"stochastic-consistency","least_similar_on":"logic-puzzle"},{"model_a":"devstral-medium","model_b":"gemma-3n-e2b-it-free","name_a":"Mistral Devstral Medium","name_b":"Google: Gemma 3n 2B","provider_a":"mistral","provider_b":"google","shared_challenges":14,"avg_similarity":0.7274,"stddev":0.1533,"min_similarity":0.434,"max_similarity":0.9043,"confidence":0.6307,"aggregate_similarity":0.7084,"most_similar_on":"explain-like-im-a-specific-expert","least_similar_on":"startup-pitch-teardown"},{"model_a":"qwen3.5-397b-a17b","model_b":"qwen3.5-flash-02-23","name_a":"Qwen: Qwen3.5 397B A17B","name_b":"Qwen: Qwen3.5 Flash","provider_a":"qwen","provider_b":"qwen","shared_challenges":23,"avg_similarity":0.7579,"stddev":0.2024,"min_similarity":0.196,"max_similarity":0.9895,"confidence":0.6303,"aggregate_similarity":0.8265,"most_similar_on":"logic-puzzle","least_similar_on":"debug-this-architecture"},{"model_a":"aurora-alpha","model_b":"gpt-oss-120b","name_a":"Aurora Alpha","name_b":"GPT OSS 120B","provider_a":"openrouter","provider_b":"openai","shared_challenges":20,"avg_similarity":0.7122,"stddev":0.132,"min_similarity":0.4139,"max_similarity":0.8845,"confidence":0.6291,"aggregate_similarity":0.8213,"most_similar_on":"standup-routine","least_similar_on":"startup-pitch-teardown"},{"model_a":"claude-3-haiku","model_b":"llama-3.1-70b","name_a":"Claude 3 Haiku","name_b":"Llama 3.1 70B (Instruct)","provider_a":"anthropic","provider_b":"meta","shared_challenges":12,"avg_similarity":0.7132,"stddev":0.1349,"min_similarity":0.3749,"max_similarity":0.8996,"confidence":0.6284,"aggregate_similarity":0.7325,"most_similar_on":"adversarial-contract-review","least_similar_on":"startup-pitch-teardown"},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-27b","name_a":"Qwen: Qwen3.5 122B A10B","name_b":"Qwen: Qwen3.5 27B","provider_a":"qwen","provider_b":"qwen","shared_challenges":23,"avg_similarity":0.778,"stddev":0.2405,"min_similarity":-0.2058,"max_similarity":0.9714,"confidence":0.6272,"aggregate_similarity":0.796,"most_similar_on":"logic-puzzle","least_similar_on":"satirical-fake-news"},{"model_a":"qwen-plus-2025-07-28-thinking","model_b":"qwen3-next-80b-a3b-thinking","name_a":"Qwen Plus 0728 (thinking)","name_b":"Qwen3 Next 80B A3B Thinking","provider_a":"qwen","provider_b":"qwen","shared_challenges":17,"avg_similarity":0.7187,"stddev":0.1505,"min_similarity":0.44,"max_similarity":0.978,"confidence":0.6246,"aggregate_similarity":0.7829,"most_similar_on":"logic-puzzle","least_similar_on":"longevity-plan"},{"model_a":"mistral-medium-3.1","model_b":"mistral-small-creative","name_a":"Mistral Medium 3.1","name_b":"Mistral Small Creative","provider_a":"mistral","provider_b":"mistral","shared_challenges":22,"avg_similarity":0.7481,"stddev":0.1982,"min_similarity":0.0459,"max_similarity":0.9399,"confidence":0.6243,"aggregate_similarity":0.9081,"most_similar_on":"sentience-test","least_similar_on":"math-misconception"},{"model_a":"gemma-3-12b-it","model_b":"gemma-3-27b-it","name_a":"Gemma 3 12B","name_b":"Gemma 3 27B","provider_a":"google","provider_b":"google","shared_challenges":21,"avg_similarity":0.7529,"stddev":0.2137,"min_similarity":0.0372,"max_similarity":0.9806,"confidence":0.6203,"aggregate_similarity":0.7358,"most_similar_on":"realistic-ai-interview","least_similar_on":"logic-puzzle"},{"model_a":"aurora-alpha","model_b":"gpt-oss-20b","name_a":"Aurora Alpha","name_b":"GPT OSS 20B","provider_a":"openrouter","provider_b":"openai","shared_challenges":19,"avg_similarity":0.7174,"stddev":0.1606,"min_similarity":0.2562,"max_similarity":0.9753,"confidence":0.6181,"aggregate_similarity":0.8511,"most_similar_on":"stochastic-consistency","least_similar_on":"logic-puzzle"},{"model_a":"qwen3-coder","model_b":"qwen3-coder-plus","name_a":"Qwen3 Coder","name_b":"Qwen3 Coder Plus","provider_a":"qwen","provider_b":"qwen","shared_challenges":22,"avg_similarity":0.7273,"stddev":0.1836,"min_similarity":0.2654,"max_similarity":0.9936,"confidence":0.6145,"aggregate_similarity":0.861,"most_similar_on":"satirical-fake-news","least_similar_on":"debug-this-architecture"},{"model_a":"glm-5","model_b":"qwen3.5-9b","name_a":"Z.ai: GLM 5","name_b":"Qwen3.5 9B","provider_a":"zhipu","provider_b":"qwen","shared_challenges":20,"avg_similarity":0.7233,"stddev":0.1772,"min_similarity":0.3901,"max_similarity":0.9727,"confidence":0.6145,"aggregate_similarity":0.7351,"most_similar_on":"sentience-test","least_similar_on":"estimate-complexity"},{"model_a":"glm-5","model_b":"qwen3.5-27b","name_a":"Z.ai: GLM 5","name_b":"Qwen: Qwen3.5 27B","provider_a":"zhipu","provider_b":"qwen","shared_challenges":22,"avg_similarity":0.7251,"stddev":0.1845,"min_similarity":0.2561,"max_similarity":0.9611,"confidence":0.6121,"aggregate_similarity":0.7323,"most_similar_on":"logic-puzzle","least_similar_on":"satirical-fake-news"},{"model_a":"mistral-large-2","model_b":"mistral-small-creative","name_a":"Mistral Large 2","name_b":"Mistral Small Creative","provider_a":"mistral","provider_b":"mistral","shared_challenges":10,"avg_similarity":0.7137,"stddev":0.167,"min_similarity":0.3121,"max_similarity":0.9141,"confidence":0.6115,"aggregate_similarity":0.7969,"most_similar_on":"adversarial-contract-review","least_similar_on":"simple-recipe"},{"model_a":"glm-4.7","model_b":"pony-alpha","name_a":"Z.AI: GLM 4.7","name_b":"Pony Alpha","provider_a":"openrouter","provider_b":"openrouter","shared_challenges":20,"avg_similarity":0.7366,"stddev":0.2046,"min_similarity":0.2249,"max_similarity":0.9682,"confidence":0.6115,"aggregate_similarity":0.7137,"most_similar_on":"realistic-ai-interview","least_similar_on":"logic-puzzle"},{"model_a":"gpt-5.1-codex-max","model_b":"o4-mini","name_a":"GPT-5.1 Codex Max","name_b":"OpenAI o4-mini","provider_a":"openai","provider_b":"openai","shared_challenges":8,"avg_similarity":0.7172,"stddev":0.1741,"min_similarity":0.3839,"max_similarity":0.9311,"confidence":0.6108,"aggregate_similarity":0.8093,"most_similar_on":"logic-puzzle","least_similar_on":"ai-generated-manifesto"}],"prompt_dependent_twins":[{"model_a":"gpt-5.4-mini","model_b":"gpt-5.4-pro","name_a":"GPT-5.4 Mini","name_b":"GPT-5.4 Pro","provider_a":"openai","provider_b":"openai","shared_challenges":12,"avg_similarity":0.6173,"stddev":0.3982,"min_similarity":-0.1302,"max_similarity":0.9767,"confidence":0.4415,"aggregate_similarity":0.7826,"most_similar_on":"advanced-longevity-plan","least_similar_on":"startup-pitch-teardown"},{"model_a":"gpt-5.4","model_b":"gpt-5.4-pro","name_a":"GPT-5.4","name_b":"GPT-5.4 Pro","provider_a":"openai","provider_b":"openai","shared_challenges":11,"avg_similarity":0.5944,"stddev":0.3853,"min_similarity":-0.042,"max_similarity":0.9743,"confidence":0.4291,"aggregate_similarity":0.8092,"most_similar_on":"advanced-longevity-plan","least_similar_on":"startup-pitch-teardown"},{"model_a":"kimi-k2-0905","model_b":"o3","name_a":"MoonshotAI: Kimi K2 0905","name_b":"OpenAI o3","provider_a":"moonshotai","provider_b":"openai","shared_challenges":16,"avg_similarity":0.4211,"stddev":0.3679,"min_similarity":-0.1877,"max_similarity":0.9769,"confidence":0.3079,"aggregate_similarity":0.7728,"most_similar_on":"standup-routine","least_similar_on":"math-misconception"},{"model_a":"claude-sonnet-4","model_b":"qwen3-coder-flash","name_a":"Claude Sonnet 4","name_b":"Qwen3 Coder Flash","provider_a":"anthropic","provider_b":"qwen","shared_challenges":14,"avg_similarity":0.6487,"stddev":0.3323,"min_similarity":0.0397,"max_similarity":0.9805,"confidence":0.4869,"aggregate_similarity":0.7458,"most_similar_on":"advanced-longevity-plan","least_similar_on":"debug-this-architecture"},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-397b-a17b","name_a":"Qwen: Qwen3.5 122B A10B","name_b":"Qwen: Qwen3.5 397B A17B","provider_a":"qwen","provider_b":"qwen","shared_challenges":23,"avg_similarity":0.6821,"stddev":0.3303,"min_similarity":-0.5527,"max_similarity":0.9812,"confidence":0.5128,"aggregate_similarity":0.7491,"most_similar_on":"logic-puzzle","least_similar_on":"satirical-fake-news"},{"model_a":"gemini-2.0-flash-thinking-exp","model_b":"gemma-3-27b-it","name_a":"Gemini 2.0 Flash Thinking","name_b":"Gemma 3 27B","provider_a":"google","provider_b":"google","shared_challenges":13,"avg_similarity":0.6101,"stddev":0.3293,"min_similarity":0.0217,"max_similarity":0.9865,"confidence":0.459,"aggregate_similarity":0.8172,"most_similar_on":"realistic-ai-interview","least_similar_on":"count-letters"},{"model_a":"gpt-5-codex","model_b":"gpt-5.1-chat","name_a":"GPT-5 Codex","name_b":"GPT-5.1 Chat","provider_a":"openai","provider_b":"openai","shared_challenges":13,"avg_similarity":0.5704,"stddev":0.3283,"min_similarity":-0.1095,"max_similarity":0.9632,"confidence":0.4294,"aggregate_similarity":0.7472,"most_similar_on":"satirical-fake-news","least_similar_on":"longevity-plan"},{"model_a":"glm-4.7","model_b":"qwen3.5-122b-a10b","name_a":"Z.AI: GLM 4.7","name_b":"Qwen: Qwen3.5 122B A10B","provider_a":"openrouter","provider_b":"qwen","shared_challenges":21,"avg_similarity":0.6983,"stddev":0.322,"min_similarity":-0.4817,"max_similarity":0.9685,"confidence":0.5282,"aggregate_similarity":0.7056,"most_similar_on":"michelin-star-recipe","least_similar_on":"satirical-fake-news"},{"model_a":"mistral-large","model_b":"mistral-small-creative","name_a":"Mistral Large","name_b":"Mistral Small Creative","provider_a":"mistral","provider_b":"mistral","shared_challenges":15,"avg_similarity":0.5737,"stddev":0.3206,"min_similarity":-0.1583,"max_similarity":0.9798,"confidence":0.4345,"aggregate_similarity":0.7152,"most_similar_on":"advanced-longevity-plan","least_similar_on":"estimate-complexity"},{"model_a":"gpt-5-codex","model_b":"kimi-linear-48b-a3b-instruct","name_a":"GPT-5 Codex","name_b":"Kimi Linear 48B A3B Instruct","provider_a":"openai","provider_b":"moonshotai","shared_challenges":13,"avg_similarity":0.6,"stddev":0.3176,"min_similarity":-0.1464,"max_similarity":0.9658,"confidence":0.4554,"aggregate_similarity":0.7237,"most_similar_on":"satirical-fake-news","least_similar_on":"longevity-plan"},{"model_a":"bert-nebulon-alpha","model_b":"devstral-2512-free","name_a":"Bert-Nebulon Alpha","name_b":"Mistral: Devstral 2 2512","provider_a":"openrouter","provider_b":"mistral","shared_challenges":14,"avg_similarity":0.6159,"stddev":0.3151,"min_similarity":-0.068,"max_similarity":0.9795,"confidence":0.4683,"aggregate_similarity":0.7812,"most_similar_on":"stochastic-consistency","least_similar_on":"satirical-fake-news"},{"model_a":"claude-haiku-4.5","model_b":"claude-sonnet-4","name_a":"Claude Haiku 4.5","name_b":"Claude Sonnet 4","provider_a":"anthropic","provider_b":"anthropic","shared_challenges":16,"avg_similarity":0.5415,"stddev":0.3104,"min_similarity":0.0361,"max_similarity":0.9791,"confidence":0.4132,"aggregate_similarity":0.7262,"most_similar_on":"advanced-longevity-plan","least_similar_on":"math-misconception"},{"model_a":"qwen-plus-2025-07-28-thinking","model_b":"qwen3-235b-a22b-thinking-2507","name_a":"Qwen Plus 0728 (thinking)","name_b":"Qwen: Qwen3 235B A22B Thinking 2507","provider_a":"qwen","provider_b":"qwen","shared_challenges":18,"avg_similarity":0.6663,"stddev":0.3024,"min_similarity":-0.1444,"max_similarity":0.9543,"confidence":0.5116,"aggregate_similarity":0.774,"most_similar_on":"character-voice-test","least_similar_on":"michelin-star-recipe"},{"model_a":"devstral-2512-free","model_b":"qwen3-30b-a3b-thinking-2507","name_a":"Mistral: Devstral 2 2512","name_b":"Qwen3 30B A3B Thinking 2507","provider_a":"mistral","provider_b":"qwen","shared_challenges":13,"avg_similarity":0.4728,"stddev":0.3014,"min_similarity":0.0132,"max_similarity":0.8788,"confidence":0.3633,"aggregate_similarity":0.7122,"most_similar_on":"realistic-ai-interview","least_similar_on":"satirical-fake-news"}],"challenge_top_pairs":{"ai-ethics-dilemma":{"model_count":131,"top_pairs":[{"model_a":"gpt-4o","model_b":"palm-2-chat-bison","similarity":1,"name_a":"GPT-4o (Omni)","name_b":"PaLM 2 Chat"},{"model_a":"devstral-small","model_b":"gemini-2.5-pro-exp","similarity":0.969,"name_a":"Mistral Devstral Small 1.1","name_b":"Gemini 2.5 Pro Experimental"},{"model_a":"andromeda-alpha","model_b":"gpt-4.5","similarity":0.9634,"name_a":"Andromeda Alpha","name_b":"GPT-4.5"},{"model_a":"gemini-3-pro-preview","model_b":"qwen3.5-397b-a17b","similarity":0.9563,"name_a":"Gemini 3 Pro Preview","name_b":"Qwen: Qwen3.5 397B A17B"},{"model_a":"gpt-4.5","model_b":"mistral-large","similarity":0.956,"name_a":"GPT-4.5","name_b":"Mistral Large"}],"avg_similarity":0.3788},"ai-generated-manifesto":{"model_count":131,"top_pairs":[{"model_a":"glm-4.7-flash","model_b":"qwen3.5-27b","similarity":0.9501,"name_a":"GLM 4.7 Flash","name_b":"Qwen: Qwen3.5 27B"},{"model_a":"gemini-2.5-pro-preview-06-05","model_b":"glm-4.6","similarity":0.9449,"name_a":"Gemini 2.5 Pro Preview 06-05","name_b":"Z.AI: GLM 4.6"},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-flash-02-23","similarity":0.937,"name_a":"Qwen: Qwen3.5 122B A10B","name_b":"Qwen: Qwen3.5 Flash"},{"model_a":"gpt-oss-120b","model_b":"minimax-m2.7","similarity":0.9369,"name_a":"GPT OSS 120B","name_b":"MiniMax M2.7"},{"model_a":"glm-4.5","model_b":"grok-3-beta","similarity":0.9306,"name_a":"Z.AI: GLM 4.5","name_b":"Grok 3 Beta"}],"avg_similarity":0.3112},"character-voice-test":{"model_count":132,"top_pairs":[{"model_a":"gemini-2.0-flash-thinking-exp","model_b":"gemini-2.5-flash-preview","similarity":0.9645,"name_a":"Gemini 2.0 Flash Thinking","name_b":"Gemini 2.5 Flash Preview"},{"model_a":"bert-nebulon-alpha","model_b":"qwen3-30b-a3b-thinking-2507","similarity":0.9632,"name_a":"Bert-Nebulon Alpha","name_b":"Qwen3 30B A3B Thinking 2507"},{"model_a":"mimo-v2-pro","model_b":"qwen3-coder-flash","similarity":0.9604,"name_a":"MiMo-V2-Pro","name_b":"Qwen3 Coder Flash"},{"model_a":"intellect-3","model_b":"qwen-plus-2025-07-28-thinking","similarity":0.9552,"name_a":"INTELLECT-3","name_b":"Qwen Plus 0728 (thinking)"},{"model_a":"qwen-plus-2025-07-28-thinking","model_b":"qwen3-235b-a22b-thinking-2507","similarity":0.9543,"name_a":"Qwen Plus 0728 (thinking)","name_b":"Qwen: Qwen3 235B A22B Thinking 2507"}],"avg_similarity":0.4304},"futuristic-prediction":{"model_count":141,"top_pairs":[{"model_a":"grok-4","model_b":"sonoma-dusk-alpha","similarity":0.9895,"name_a":"xAI: Grok 4","name_b":"Sonoma Dusk Alpha"},{"model_a":"andromeda-alpha","model_b":"tng-r1t-chimera-free","similarity":0.9833,"name_a":"Andromeda Alpha","name_b":"TNG R1T Chimera"},{"model_a":"nemotron-nano-9b-v2","model_b":"tng-r1t-chimera-free","similarity":0.9802,"name_a":"NVIDIA Nemotron Nano 9B V2","name_b":"TNG R1T Chimera"},{"model_a":"devstral-small","model_b":"nova-premier-v1","similarity":0.9775,"name_a":"Mistral Devstral Small 1.1","name_b":"Nova Premier 1.0"},{"model_a":"devstral-small","model_b":"nemotron-nano-9b-v2","similarity":0.9771,"name_a":"Mistral Devstral Small 1.1","name_b":"NVIDIA Nemotron Nano 9B V2"}],"avg_similarity":0.3931},"logic-puzzle":{"model_count":141,"top_pairs":[{"model_a":"gpt-5","model_b":"gpt-5-nano","similarity":0.9974,"name_a":"GPT-5","name_b":"GPT-5 Nano"},{"model_a":"glm-5","model_b":"pony-alpha","similarity":0.9941,"name_a":"Z.ai: GLM 5","name_b":"Pony Alpha"},{"model_a":"devstral-small","model_b":"gpt-4o-mini","similarity":0.9938,"name_a":"Mistral Devstral Small 1.1","name_b":"GPT-4o mini"},{"model_a":"nemotron-nano-9b-v2","model_b":"qwen3.5-397b-a17b","similarity":0.9938,"name_a":"NVIDIA Nemotron Nano 9B V2","name_b":"Qwen: Qwen3.5 397B A17B"},{"model_a":"gemini-3-pro-preview","model_b":"glm-5","similarity":0.9936,"name_a":"Gemini 3 Pro Preview","name_b":"Z.ai: GLM 5"}],"avg_similarity":0.2919},"longevity-plan":{"model_count":153,"top_pairs":[{"model_a":"mistral-large","model_b":"mistral-large-2512","similarity":0.9773,"name_a":"Mistral Large","name_b":"Mistral Large 3 2512"},{"model_a":"glm-4.7-flash","model_b":"qwen3.5-27b","similarity":0.9672,"name_a":"GLM 4.7 Flash","name_b":"Qwen: Qwen3.5 27B"},{"model_a":"gpt-5-mini","model_b":"gpt-5-nano","similarity":0.9649,"name_a":"GPT-5 Mini","name_b":"GPT-5 Nano"},{"model_a":"gemma-3n-e2b-it-free","model_b":"gemma-3n-e4b-it","similarity":0.9618,"name_a":"Google: Gemma 3n 2B","name_b":"Gemma 3n 4B"},{"model_a":"minimax-m2.7","model_b":"mistral-large-2","similarity":0.957,"name_a":"MiniMax M2.7","name_b":"Mistral Large 2"}],"avg_similarity":0.3024},"math-misconception":{"model_count":96,"top_pairs":[{"model_a":"bert-nebulon-alpha","model_b":"mistral-large-2512","similarity":1,"name_a":"Bert-Nebulon Alpha","name_b":"Mistral Large 3 2512"},{"model_a":"gemini-pro","model_b":"gpt-4o-mini","similarity":1,"name_a":"Gemini Pro 1.0","name_b":"GPT-4o mini"},{"model_a":"gemini-2.5-flash-lite-preview-09-2025","model_b":"gemini-2.5-flash-preview-09-2025","similarity":0.9906,"name_a":"Google: Gemini 2.5 Flash Lite Preview 09-2025","name_b":"Google: Gemini 2.5 Flash Preview 09-2025"},{"model_a":"horizon-beta","model_b":"o3-mini","similarity":0.9898,"name_a":"Horizon Beta","name_b":"o3 Mini"},{"model_a":"horizon-alpha","model_b":"polaris-alpha","similarity":0.9866,"name_a":"Horizon Alpha","name_b":"Polaris Alpha"}],"avg_similarity":0.2298},"realistic-ai-interview":{"model_count":148,"top_pairs":[{"model_a":"gemini-2.0-flash-thinking-exp","model_b":"gemma-3-27b-it","similarity":0.9865,"name_a":"Gemini 2.0 Flash Thinking","name_b":"Gemma 3 27B"},{"model_a":"gemma-3-12b-it","model_b":"gemma-3-27b-it","similarity":0.9806,"name_a":"Gemma 3 12B","name_b":"Gemma 3 27B"},{"model_a":"pony-alpha","model_b":"qwen3.5-27b","similarity":0.9707,"name_a":"Pony Alpha","name_b":"Qwen: Qwen3.5 27B"},{"model_a":"glm-4.7","model_b":"pony-alpha","similarity":0.9682,"name_a":"Z.AI: GLM 4.7","name_b":"Pony Alpha"},{"model_a":"pony-alpha","model_b":"qwen3.5-122b-a10b","similarity":0.9667,"name_a":"Pony Alpha","name_b":"Qwen: Qwen3.5 122B A10B"}],"avg_similarity":0.4708},"satirical-fake-news":{"model_count":135,"top_pairs":[{"model_a":"gpt-5.2-pro","model_b":"gpt-oss-120b","similarity":0.9998,"name_a":"GPT-5.2 Pro","name_b":"GPT OSS 120B"},{"model_a":"gpt-5.2-pro","model_b":"optimus-alpha","similarity":0.9993,"name_a":"GPT-5.2 Pro","name_b":"Optimus Alpha"},{"model_a":"glm-4-32b","model_b":"gpt-5.2-pro","similarity":0.9991,"name_a":"Z.AI: GLM 4 32B","name_b":"GPT-5.2 Pro"},{"model_a":"gpt-4o-mini","model_b":"gpt-5.1","similarity":0.9991,"name_a":"GPT-4o mini","name_b":"GPT-5.1"},{"model_a":"gemini-2.0-flash-thinking-exp","model_b":"optimus-alpha","similarity":0.9989,"name_a":"Gemini 2.0 Flash Thinking","name_b":"Optimus Alpha"}],"avg_similarity":0.4841},"sentience-test":{"model_count":151,"top_pairs":[{"model_a":"qwen3.5-27b","model_b":"qwen3.5-flash-02-23","similarity":0.9912,"name_a":"Qwen: Qwen3.5 27B","name_b":"Qwen: Qwen3.5 Flash"},{"model_a":"qwen3.5-27b","model_b":"qwen3.5-35b-a3b","similarity":0.9884,"name_a":"Qwen: Qwen3.5 27B","name_b":"Qwen: Qwen3.5 35B A3B"},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-35b-a3b","similarity":0.9806,"name_a":"Qwen: Qwen3.5 122B A10B","name_b":"Qwen: Qwen3.5 35B A3B"},{"model_a":"qwen3.5-35b-a3b","model_b":"qwen3.5-flash-02-23","similarity":0.98,"name_a":"Qwen: Qwen3.5 35B A3B","name_b":"Qwen: Qwen3.5 Flash"},{"model_a":"mimo-v2-flash","model_b":"pony-alpha","similarity":0.9767,"name_a":"MiMo-V2-Flash","name_b":"Pony Alpha"}],"avg_similarity":0.5901},"simple-recipe":{"model_count":152,"top_pairs":[{"model_a":"devstral-medium","model_b":"devstral-small","similarity":0.9869,"name_a":"Mistral Devstral Medium","name_b":"Mistral Devstral Small 1.1"},{"model_a":"deepseek-v3-03-24","model_b":"qwen3-30b-a3b-instruct-2507","similarity":0.9814,"name_a":"DeepSeek V3 (March 2024)","name_b":"Qwen: Qwen3 30B A3B Instruct 2507"},{"model_a":"qwen3-coder-next","model_b":"qwen3-max-thinking","similarity":0.9787,"name_a":"Qwen3 Coder Next","name_b":"Qwen: Qwen3 Max Thinking"},{"model_a":"llama-4-maverick","model_b":"llama-4-scout","similarity":0.9757,"name_a":"Llama 4 Maverick","name_b":"Llama 4 Scout"},{"model_a":"mistral-small-creative","model_b":"qwen3-coder-next","similarity":0.9708,"name_a":"Mistral Small Creative","name_b":"Qwen3 Coder Next"}],"avg_similarity":0.4105},"standup-routine":{"model_count":150,"top_pairs":[{"model_a":"gpt-5","model_b":"horizon-beta","similarity":0.9883,"name_a":"GPT-5","name_b":"Horizon Beta"},{"model_a":"gpt-5.1-codex-max","model_b":"horizon-alpha","similarity":0.9866,"name_a":"GPT-5.1 Codex Max","name_b":"Horizon Alpha"},{"model_a":"claude-3-haiku","model_b":"gpt-4.1-nano","similarity":0.9799,"name_a":"Claude 3 Haiku","name_b":"GPT-4.1 Nano"},{"model_a":"gemini-3.1-flash-lite-preview","model_b":"qwen3.5-plus-02-15","similarity":0.9776,"name_a":"Google: Gemini 3.1 Flash Lite Preview","name_b":"Qwen: Qwen3.5 Plus 2026-02-15"},{"model_a":"gpt-oss-20b","model_b":"o4-mini-high","similarity":0.9769,"name_a":"GPT OSS 20B","name_b":"OpenAI o4 Mini High"}],"avg_similarity":0.6907},"stochastic-consistency":{"model_count":166,"top_pairs":[{"model_a":"bert-nebulon-alpha","model_b":"mistral-large-2512","similarity":1,"name_a":"Bert-Nebulon Alpha","name_b":"Mistral Large 3 2512"},{"model_a":"devstral-medium","model_b":"devstral-small","similarity":1,"name_a":"Mistral Devstral Medium","name_b":"Mistral Devstral Small 1.1"},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-35b-a3b","similarity":0.999,"name_a":"Qwen: Qwen3.5 122B A10B","name_b":"Qwen: Qwen3.5 35B A3B"},{"model_a":"claude-opus-4.1","model_b":"qwen3-coder-flash","similarity":0.9979,"name_a":"Claude Opus 4.1","name_b":"Qwen3 Coder Flash"},{"model_a":"gemini-3.1-flash-lite-preview","model_b":"gpt-oss-20b","similarity":0.997,"name_a":"Google: Gemini 3.1 Flash Lite Preview","name_b":"GPT OSS 20B"}],"avg_similarity":0.5221},"advanced-investment-memo":{"model_count":67,"top_pairs":[{"model_a":"gpt-5.2","model_b":"gpt-5.2-pro","similarity":0.9608,"name_a":"GPT-5.2","name_b":"GPT-5.2 Pro"},{"model_a":"mercury-2","model_b":"minimax-m2.7","similarity":0.9443,"name_a":"Inception: Mercury 2","name_b":"MiniMax M2.7"},{"model_a":"gpt-5.1-chat","model_b":"gpt-5.3-chat","similarity":0.9315,"name_a":"GPT-5.1 Chat","name_b":"GPT-5.3 Chat"},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-flash-02-23","similarity":0.927,"name_a":"Qwen: Qwen3.5 122B A10B","name_b":"Qwen: Qwen3.5 Flash"},{"model_a":"claude-opus-4.5","model_b":"qwen3-coder-next","similarity":0.9226,"name_a":"Claude Opus 4.5","name_b":"Qwen3 Coder Next"}],"avg_similarity":0.3703},"adversarial-contract-review":{"model_count":115,"top_pairs":[{"model_a":"deepseek-r1","model_b":"deepseek-v3-03-24","similarity":0.9848,"name_a":"DeepSeek R1","name_b":"DeepSeek V3 (March 2024)"},{"model_a":"grok-4","model_b":"grok-code-fast-1","similarity":0.9844,"name_a":"xAI: Grok 4","name_b":"Grok Code Fast 1"},{"model_a":"llama-4-maverick","model_b":"llama-4-scout","similarity":0.9762,"name_a":"Llama 4 Maverick","name_b":"Llama 4 Scout"},{"model_a":"gemma-3-12b-it","model_b":"gemma-3n-e4b-it","similarity":0.9726,"name_a":"Gemma 3 12B","name_b":"Gemma 3n 4B"},{"model_a":"chatgpt-4o-03-25","model_b":"claude-3-haiku","similarity":0.9658,"name_a":"ChatGPT-4o (March 2025)","name_b":"Claude 3 Haiku"}],"avg_similarity":0.5635},"debug-this-architecture":{"model_count":116,"top_pairs":[{"model_a":"claude-opus-4.5","model_b":"claude-sonnet-4.6","similarity":0.9925,"name_a":"Claude Opus 4.5","name_b":"Claude Sonnet 4.6"},{"model_a":"claude-opus-4.6","model_b":"minimax-m2.7","similarity":0.9876,"name_a":"Claude Opus 4.6","name_b":"MiniMax M2.7"},{"model_a":"claude-4.5-sonnet","model_b":"claude-haiku-4.5","similarity":0.9865,"name_a":"Claude Sonnet 4.5","name_b":"Claude Haiku 4.5"},{"model_a":"deepseek-chat-v3.1","model_b":"gemini-2.5-pro-preview-06-05","similarity":0.9844,"name_a":"DeepSeek V3.1","name_b":"Gemini 2.5 Pro Preview 06-05"},{"model_a":"qwen3-coder-flash","model_b":"qwen3-max","similarity":0.9839,"name_a":"Qwen3 Coder Flash","name_b":"Qwen: Qwen3 Max"}],"avg_similarity":0.3351},"estimate-complexity":{"model_count":142,"top_pairs":[{"model_a":"gemini-2.5-pro-preview-06-05","model_b":"glm-4-32b","similarity":0.9585,"name_a":"Gemini 2.5 Pro Preview 06-05","name_b":"Z.AI: GLM 4 32B"},{"model_a":"hunter-alpha","model_b":"qwen3-max","similarity":0.9574,"name_a":"Hunter Alpha","name_b":"Qwen: Qwen3 Max"},{"model_a":"qwen3.5-35b-a3b","model_b":"qwen3.5-397b-a17b","similarity":0.9566,"name_a":"Qwen: Qwen3.5 35B A3B","name_b":"Qwen: Qwen3.5 397B A17B"},{"model_a":"gpt-4.1-mini","model_b":"hunter-alpha","similarity":0.9562,"name_a":"GPT-4.1 Mini","name_b":"Hunter Alpha"},{"model_a":"deepseek-v3.2-exp","model_b":"hunter-alpha","similarity":0.9536,"name_a":"DeepSeek V3.2 Exp","name_b":"Hunter Alpha"}],"avg_similarity":0.3624},"ethical-dilemma-with-stakeholders":{"model_count":119,"top_pairs":[{"model_a":"deepseek-v3.2","model_b":"deepseek-v3.2-exp","similarity":0.9752,"name_a":"DeepSeek V3.2","name_b":"DeepSeek V3.2 Exp"},{"model_a":"gemma-3n-e2b-it-free","model_b":"gemma-3n-e4b-it","similarity":0.9705,"name_a":"Google: Gemma 3n 2B","name_b":"Gemma 3n 4B"},{"model_a":"gemma-3-12b-it","model_b":"gemma-3-27b-it","similarity":0.9567,"name_a":"Gemma 3 12B","name_b":"Gemma 3 27B"},{"model_a":"gemini-2.5-pro-exp","model_b":"gemini-2.5-pro-preview-06-05","similarity":0.9531,"name_a":"Gemini 2.5 Pro Experimental","name_b":"Gemini 2.5 Pro Preview 06-05"},{"model_a":"gemini-2.5-pro-preview-06-05","model_b":"glm-4.6","similarity":0.9526,"name_a":"Gemini 2.5 Pro Preview 06-05","name_b":"Z.AI: GLM 4.6"}],"avg_similarity":0.4121},"explain-like-im-a-specific-expert":{"model_count":115,"top_pairs":[{"model_a":"claude-3-haiku","model_b":"llama-4-scout","similarity":0.9738,"name_a":"Claude 3 Haiku","name_b":"Llama 4 Scout"},{"model_a":"mistral-large-2","model_b":"mistral-large-2512","similarity":0.9613,"name_a":"Mistral Large 2","name_b":"Mistral Large 3 2512"},{"model_a":"claude-opus-4.6","model_b":"claude-sonnet-4.6","similarity":0.9568,"name_a":"Claude Opus 4.6","name_b":"Claude Sonnet 4.6"},{"model_a":"pony-alpha","model_b":"qwen3.5-35b-a3b","similarity":0.9459,"name_a":"Pony Alpha","name_b":"Qwen: Qwen3.5 35B A3B"},{"model_a":"claude-sonnet-4","model_b":"qwen3-coder","similarity":0.9453,"name_a":"Claude Sonnet 4","name_b":"Qwen3 Coder"}],"avg_similarity":0.5568},"historical-counterfactual-analysis":{"model_count":114,"top_pairs":[{"model_a":"gpt-4o","model_b":"gpt-4o-mini","similarity":0.9979,"name_a":"GPT-4o (Omni)","name_b":"GPT-4o mini"},{"model_a":"gemini-2.5-pro-exp","model_b":"gemini-2.5-pro-preview-06-05","similarity":0.9887,"name_a":"Gemini 2.5 Pro Experimental","name_b":"Gemini 2.5 Pro Preview 06-05"},{"model_a":"deepseek-v3.2-exp","model_b":"nemotron-nano-9b-v2","similarity":0.9823,"name_a":"DeepSeek V3.2 Exp","name_b":"NVIDIA Nemotron Nano 9B V2"},{"model_a":"mistral-large","model_b":"mistral-small-2603","similarity":0.982,"name_a":"Mistral Large","name_b":"Mistral Small 4"},{"model_a":"claude-opus-4.6","model_b":"minimax-m2.1","similarity":0.9819,"name_a":"Claude Opus 4.6","name_b":"MiniMax: MiniMax M2.1"}],"avg_similarity":0.5019},"michelin-star-recipe":{"model_count":121,"top_pairs":[{"model_a":"gpt-5","model_b":"o3","similarity":1,"name_a":"GPT-5","name_b":"OpenAI o3"},{"model_a":"gemini-2.5-pro-exp","model_b":"gemini-2.5-pro-preview-05-06","similarity":0.9806,"name_a":"Gemini 2.5 Pro Experimental","name_b":"Gemini 2.5 Pro (I/O Edition)"},{"model_a":"gpt-5.4","model_b":"gpt-5.4-mini","similarity":0.9799,"name_a":"GPT-5.4","name_b":"GPT-5.4 Mini"},{"model_a":"gemini-2.5-pro-preview-05-06","model_b":"gemini-2.5-pro-preview-06-05","similarity":0.9781,"name_a":"Gemini 2.5 Pro (I/O Edition)","name_b":"Gemini 2.5 Pro Preview 06-05"},{"model_a":"claude-opus-4.1","model_b":"qwen3-coder-plus","similarity":0.9772,"name_a":"Claude Opus 4.1","name_b":"Qwen3 Coder Plus"}],"avg_similarity":0.5022},"mini-lbo-underwrite":{"model_count":66,"top_pairs":[{"model_a":"claude-opus-4.1","model_b":"claude-sonnet-4","similarity":0.9927,"name_a":"Claude Opus 4.1","name_b":"Claude Sonnet 4"},{"model_a":"aurora-alpha","model_b":"mercury-2","similarity":0.9798,"name_a":"Aurora Alpha","name_b":"Inception: Mercury 2"},{"model_a":"claude-opus-4","model_b":"claude-opus-4.1","similarity":0.9691,"name_a":"Claude Opus 4","name_b":"Claude Opus 4.1"},{"model_a":"gpt-5.1-codex-max","model_b":"sonar-pro-search","similarity":0.9607,"name_a":"GPT-5.1 Codex Max","name_b":"Sonar Pro Search"},{"model_a":"gemini-3-flash-preview","model_b":"glm-5","similarity":0.9599,"name_a":"Gemini 3 Flash Preview","name_b":"Z.ai: GLM 5"}],"avg_similarity":0.4486},"startup-pitch-teardown":{"model_count":119,"top_pairs":[{"model_a":"mistral-large-2","model_b":"mistral-large-2512","similarity":0.9487,"name_a":"Mistral Large 2","name_b":"Mistral Large 3 2512"},{"model_a":"grok-4","model_b":"grok-code-fast-1","similarity":0.9347,"name_a":"xAI: Grok 4","name_b":"Grok Code Fast 1"},{"model_a":"gpt-4o-mini","model_b":"llama-4-maverick","similarity":0.9335,"name_a":"GPT-4o mini","name_b":"Llama 4 Maverick"},{"model_a":"llama-4-maverick","model_b":"mistral-nemo","similarity":0.9307,"name_a":"Llama 4 Maverick","name_b":"Mistral Nemo"},{"model_a":"mistral-large","model_b":"mistral-medium-3.1","similarity":0.9177,"name_a":"Mistral Large","name_b":"Mistral Medium 3.1"}],"avg_similarity":0.2333},"advanced-longevity-plan":{"model_count":120,"top_pairs":[{"model_a":"qwen3-coder","model_b":"qwen3-coder-flash","similarity":0.9969,"name_a":"Qwen3 Coder","name_b":"Qwen3 Coder Flash"},{"model_a":"claude-haiku-4.5","model_b":"qwen3-coder","similarity":0.9895,"name_a":"Claude Haiku 4.5","name_b":"Qwen3 Coder"},{"model_a":"claude-haiku-4.5","model_b":"qwen3-coder-flash","similarity":0.9885,"name_a":"Claude Haiku 4.5","name_b":"Qwen3 Coder Flash"},{"model_a":"claude-opus-4.6","model_b":"hunter-alpha","similarity":0.9849,"name_a":"Claude Opus 4.6","name_b":"Hunter Alpha"},{"model_a":"claude-haiku-4.5","model_b":"claude-opus-4.6","similarity":0.9843,"name_a":"Claude Haiku 4.5","name_b":"Claude Opus 4.6"}],"avg_similarity":0.4173}},"feature_records":{"avg_word_length":{"max":{"value":8.6957,"model_id":"llama-3.1-405b","model_name":"Llama 3.1 405B","challenge_id":"xbox-controller-svg","response_id":"llama-3.1-405b-xbox-controller-svg"},"min":{"value":2.5,"model_id":"gemini-2.5-pro-exp","model_name":"Gemini 2.5 Pro Experimental","challenge_id":"count-letters","response_id":"gemini-2.5-pro-exp-count-letters"}},"type_token_ratio":{"max":{"value":1,"model_id":"claude-3.7-sonnet","model_name":"Claude 3.7 Sonnet","challenge_id":"satirical-fake-news","response_id":"claude-3.7-sonnet-satirical-fake-news"},"min":{"value":0.0633,"model_id":"minimax-m2-her","model_name":"MiniMax M2-her","challenge_id":"adversarial-contract-review","response_id":"minimax-m2-her-adversarial-contract-review"}},"hapax_ratio":{"max":{"value":1,"model_id":"claude-3.7-sonnet","model_name":"Claude 3.7 Sonnet","challenge_id":"satirical-fake-news","response_id":"claude-3.7-sonnet-satirical-fake-news"},"min":{"value":0.0178,"model_id":"minimax-m2-her","model_name":"MiniMax M2-her","challenge_id":"adversarial-contract-review","response_id":"minimax-m2-her-adversarial-contract-review"}},"avg_sentence_length":{"max":{"value":961,"model_id":"claude-4.5-sonnet","model_name":"Claude Sonnet 4.5","challenge_id":"advanced-longevity-plan","response_id":"claude-4.5-sonnet-advanced-longevity-plan"},"min":{"value":5,"model_id":"qwen3-0.6b-04-28","model_name":"Qwen3 0.6B","challenge_id":"satirical-fake-news","response_id":"qwen3-0.6b-04-28-satirical-fake-news"}},"sentence_length_variance":{"max":{"value":746642,"model_id":"qwen3-coder-flash","model_name":"Qwen3 Coder Flash","challenge_id":"advanced-longevity-plan","response_id":"qwen3-coder-flash-advanced-longevity-plan"},"min":{"value":0,"model_id":"aurora-alpha","model_name":"Aurora Alpha","challenge_id":"satirical-fake-news","response_id":"aurora-alpha-satirical-fake-news"}},"comma_rate":{"max":{"value":83.8235,"model_id":"claude-opus-4","model_name":"Claude Opus 4","challenge_id":"advanced-longevity-plan","response_id":"claude-opus-4-advanced-longevity-plan"},"min":{"value":0,"model_id":"andromeda-alpha","model_name":"Andromeda Alpha","challenge_id":"stochastic-consistency","response_id":"andromeda-alpha-stochastic-consistency"}},"semicolon_rate":{"max":{"value":11.2088,"model_id":"gpt-5-nano","model_name":"GPT-5 Nano","challenge_id":"advanced-longevity-plan","response_id":"gpt-5-nano-advanced-longevity-plan"},"min":{"value":0,"model_id":"andromeda-alpha","model_name":"Andromeda Alpha","challenge_id":"ai-ethics-dilemma","response_id":"andromeda-alpha-ai-ethics-dilemma"}},"colon_rate":{"max":{"value":238.2353,"model_id":"claude-opus-4","model_name":"Claude Opus 4","challenge_id":"advanced-longevity-plan","response_id":"claude-opus-4-advanced-longevity-plan"},"min":{"value":0,"model_id":"aurora-alpha","model_name":"Aurora Alpha","challenge_id":"logic-puzzle","response_id":"aurora-alpha-logic-puzzle"}},"exclamation_rate":{"max":{"value":9.5238,"model_id":"sherlock-dash-alpha","model_name":"Sherlock Dash Alpha","challenge_id":"stochastic-consistency","response_id":"sherlock-dash-alpha-stochastic-consistency"},"min":{"value":0,"model_id":"andromeda-alpha","model_name":"Andromeda Alpha","challenge_id":"ai-ethics-dilemma","response_id":"andromeda-alpha-ai-ethics-dilemma"}},"question_rate":{"max":{"value":10,"model_id":"qwen3-0.6b-04-28","model_name":"Qwen3 0.6B","challenge_id":"satirical-fake-news","response_id":"qwen3-0.6b-04-28-satirical-fake-news"},"min":{"value":0,"model_id":"andromeda-alpha","model_name":"Andromeda Alpha","challenge_id":"futuristic-prediction","response_id":"andromeda-alpha-futuristic-prediction"}},"em_dash_rate":{"max":{"value":72.7715,"model_id":"mistral-small-creative","model_name":"Mistral Small Creative","challenge_id":"advanced-longevity-plan","response_id":"mistral-small-creative-advanced-longevity-plan"},"min":{"value":0,"model_id":"andromeda-alpha","model_name":"Andromeda Alpha","challenge_id":"ai-ethics-dilemma","response_id":"andromeda-alpha-ai-ethics-dilemma"}},"ellipsis_rate":{"max":{"value":4.4316,"model_id":"qwen3-235b-a22b-thinking-2507","model_name":"Qwen: Qwen3 235B A22B Thinking 2507","challenge_id":"character-voice-test","response_id":"qwen3-235b-a22b-thinking-2507-character-voice-test"},"min":{"value":0,"model_id":"andromeda-alpha","model_name":"Andromeda Alpha","challenge_id":"ai-ethics-dilemma","response_id":"andromeda-alpha-ai-ethics-dilemma"}},"parenthetical_rate":{"max":{"value":76.4706,"model_id":"claude-opus-4","model_name":"Claude Opus 4","challenge_id":"advanced-longevity-plan","response_id":"claude-opus-4-advanced-longevity-plan"},"min":{"value":0,"model_id":"andromeda-alpha","model_name":"Andromeda Alpha","challenge_id":"ai-generated-manifesto","response_id":"andromeda-alpha-ai-generated-manifesto"}},"heading_rate":{"max":{"value":9.2308,"model_id":"claude-4.5-sonnet","model_name":"Claude Sonnet 4.5","challenge_id":"debug-this-architecture","response_id":"claude-4.5-sonnet-debug-this-architecture"},"min":{"value":0,"model_id":"andromeda-alpha","model_name":"Andromeda Alpha","challenge_id":"ai-generated-manifesto","response_id":"andromeda-alpha-ai-generated-manifesto"}},"bold_rate":{"max":{"value":39.7351,"model_id":"bert-nebulon-alpha","model_name":"Bert-Nebulon Alpha","challenge_id":"math-misconception","response_id":"bert-nebulon-alpha-math-misconception"},"min":{"value":0,"model_id":"chatgpt-4o-03-25","model_name":"ChatGPT-4o (March 2025)","challenge_id":"adversarial-contract-review","response_id":"chatgpt-4o-03-25-adversarial-contract-review"}},"italic_rate":{"max":{"value":22.0913,"model_id":"qwen3-30b-a3b-thinking-2507","model_name":"Qwen3 30B A3B Thinking 2507","challenge_id":"character-voice-test","response_id":"qwen3-30b-a3b-thinking-2507-character-voice-test"},"min":{"value":0,"model_id":"andromeda-alpha","model_name":"Andromeda Alpha","challenge_id":"futuristic-prediction","response_id":"andromeda-alpha-futuristic-prediction"}},"list_item_rate":{"max":{"value":55.5556,"model_id":"grok-3-beta","model_name":"Grok 3 Beta","challenge_id":"count-letters","response_id":"grok-3-beta-count-letters"},"min":{"value":0,"model_id":"andromeda-alpha","model_name":"Andromeda Alpha","challenge_id":"character-voice-test","response_id":"andromeda-alpha-character-voice-test"}},"code_block_rate":{"max":{"value":0,"model_id":"andromeda-alpha","model_name":"Andromeda Alpha","challenge_id":"ai-ethics-dilemma","response_id":"andromeda-alpha-ai-ethics-dilemma"},"min":{"value":0,"model_id":"andromeda-alpha","model_name":"Andromeda Alpha","challenge_id":"ai-ethics-dilemma","response_id":"andromeda-alpha-ai-ethics-dilemma"}},"inline_code_rate":{"max":{"value":4.5872,"model_id":"grok-4.1-fast","model_name":"Grok 4.1 Fast","challenge_id":"math-misconception","response_id":"grok-4.1-fast-math-misconception"},"min":{"value":0,"model_id":"andromeda-alpha","model_name":"Andromeda Alpha","challenge_id":"ai-ethics-dilemma","response_id":"andromeda-alpha-ai-ethics-dilemma"}},"emoji_rate":{"max":{"value":23.1579,"model_id":"minimax-m2-her","model_name":"MiniMax M2-her","challenge_id":"stochastic-consistency","response_id":"minimax-m2-her-stochastic-consistency"},"min":{"value":0,"model_id":"andromeda-alpha","model_name":"Andromeda Alpha","challenge_id":"ai-ethics-dilemma","response_id":"andromeda-alpha-ai-ethics-dilemma"}},"horizontal_rule_rate":{"max":{"value":6.993,"model_id":"deepseek-v3.2-exp","model_name":"DeepSeek V3.2 Exp","challenge_id":"logic-puzzle","response_id":"deepseek-v3.2-exp-logic-puzzle"},"min":{"value":0,"model_id":"andromeda-alpha","model_name":"Andromeda Alpha","challenge_id":"ai-ethics-dilemma","response_id":"andromeda-alpha-ai-ethics-dilemma"}},"hedging_rate":{"max":{"value":7.1429,"model_id":"grok-code-fast-1","model_name":"Grok Code Fast 1","challenge_id":"count-letters","response_id":"grok-code-fast-1-count-letters"},"min":{"value":0,"model_id":"andromeda-alpha","model_name":"Andromeda Alpha","challenge_id":"ai-generated-manifesto","response_id":"andromeda-alpha-ai-generated-manifesto"}},"booster_rate":{"max":{"value":6.25,"model_id":"o1","model_name":"o1","challenge_id":"logic-puzzle","response_id":"o1-logic-puzzle"},"min":{"value":0,"model_id":"andromeda-alpha","model_name":"Andromeda Alpha","challenge_id":"ai-ethics-dilemma","response_id":"andromeda-alpha-ai-ethics-dilemma"}},"transition_rate":{"max":{"value":5,"model_id":"gpt-oss-20b","model_name":"GPT OSS 20B","challenge_id":"math-misconception","response_id":"gpt-oss-20b-math-misconception"},"min":{"value":0,"model_id":"andromeda-alpha","model_name":"Andromeda Alpha","challenge_id":"ai-generated-manifesto","response_id":"andromeda-alpha-ai-generated-manifesto"}},"filler_rate":{"max":{"value":9.0909,"model_id":"gpt-5.1-chat","model_name":"GPT-5.1 Chat","challenge_id":"character-voice-test","response_id":"gpt-5.1-chat-character-voice-test"},"min":{"value":0,"model_id":"andromeda-alpha","model_name":"Andromeda Alpha","challenge_id":"ai-ethics-dilemma","response_id":"andromeda-alpha-ai-ethics-dilemma"}},"first_person_rate":{"max":{"value":13.879,"model_id":"qwen3-0.6b-04-28","model_name":"Qwen3 0.6B","challenge_id":"standup-routine","response_id":"qwen3-0.6b-04-28-standup-routine"},"min":{"value":0,"model_id":"andromeda-alpha","model_name":"Andromeda Alpha","challenge_id":"ai-ethics-dilemma","response_id":"andromeda-alpha-ai-ethics-dilemma"}},"second_person_rate":{"max":{"value":13.9241,"model_id":"gpt-2","model_name":"GPT-2","challenge_id":"surprise-animal-svg","response_id":"gpt-2-surprise-animal-svg"},"min":{"value":0,"model_id":"andromeda-alpha","model_name":"Andromeda Alpha","challenge_id":"ai-ethics-dilemma","response_id":"andromeda-alpha-ai-ethics-dilemma"}},"avg_paragraph_length":{"max":{"value":1861,"model_id":"minimax-m2-her","model_name":"MiniMax M2-her","challenge_id":"explain-like-im-a-specific-expert","response_id":"minimax-m2-her-explain-like-im-a-specific-expert"},"min":{"value":6,"model_id":"claude-3.5-sonnet","model_name":"Claude Sonnet 3.6 (2022-10-22)","challenge_id":"count-letters","response_id":"claude-3.5-sonnet-count-letters"}}},"challenge_fingerprints":{"ai-ethics-dilemma":{"model_count":131,"most_variable_features":[{"feature":"exclamation_rate","mean":0.0019,"variance":0.0002,"cv":8.1378},{"feature":"sentence_length_variance","mean":255.1306,"variance":2016683.0291,"cv":5.5662},{"feature":"horizontal_rule_rate","mean":0.1187,"variance":0.095,"cv":2.5969},{"feature":"first_person_rate","mean":0.2584,"variance":0.4439,"cv":2.578},{"feature":"second_person_rate","mean":0.241,"variance":0.2247,"cv":1.9671}]},"ai-generated-manifesto":{"model_count":131,"most_variable_features":[{"feature":"inline_code_rate","mean":0.004,"variance":0.0012,"cv":8.7102},{"feature":"emoji_rate","mean":0.0469,"variance":0.0431,"cv":4.4209},{"feature":"ellipsis_rate","mean":0.0207,"variance":0.0082,"cv":4.3863},{"feature":"sentence_length_variance","mean":191.8546,"variance":371906.0148,"cv":3.1787},{"feature":"exclamation_rate","mean":0.1288,"variance":0.1302,"cv":2.8013}]},"character-voice-test":{"model_count":132,"most_variable_features":[{"feature":"inline_code_rate","mean":0.0043,"variance":0.0024,"cv":11.4455},{"feature":"emoji_rate","mean":0.0622,"variance":0.1509,"cv":6.2503},{"feature":"transition_rate","mean":0.0102,"variance":0.003,"cv":5.3708},{"feature":"semicolon_rate","mean":0.0638,"variance":0.042,"cv":3.2133},{"feature":"list_item_rate","mean":0.1018,"variance":0.0992,"cv":3.0938}]},"futuristic-prediction":{"model_count":141,"most_variable_features":[{"feature":"sentence_length_variance","mean":2002.7947,"variance":208688911.3802,"cv":7.213},{"feature":"exclamation_rate","mean":0.003,"variance":0.0003,"cv":6.0171},{"feature":"emoji_rate","mean":0.0137,"variance":0.0051,"cv":5.2015},{"feature":"first_person_rate","mean":0.0536,"variance":0.0237,"cv":2.874},{"feature":"em_dash_rate","mean":1.7264,"variance":22.4524,"cv":2.7447}]},"logic-puzzle":{"model_count":141,"most_variable_features":[{"feature":"semicolon_rate","mean":0.0202,"variance":0.0465,"cv":10.6696},{"feature":"second_person_rate","mean":0.0278,"variance":0.0796,"cv":10.1496},{"feature":"filler_rate","mean":0.0406,"variance":0.0782,"cv":6.8807},{"feature":"exclamation_rate","mean":0.095,"variance":0.2,"cv":4.7093},{"feature":"horizontal_rule_rate","mean":0.2121,"variance":0.9023,"cv":4.4792}]},"longevity-plan":{"model_count":153,"most_variable_features":[{"feature":"ellipsis_rate","mean":0.0089,"variance":0.012,"cv":12.3288},{"feature":"inline_code_rate","mean":0.0036,"variance":0.002,"cv":12.3288},{"feature":"sentence_length_variance","mean":1443.4364,"variance":52794916.9824,"cv":5.0338},{"feature":"transition_rate","mean":0.0075,"variance":0.0012,"cv":4.6621},{"feature":"hedging_rate","mean":0.0717,"variance":0.0359,"cv":2.6416}]},"math-misconception":{"model_count":96,"most_variable_features":[{"feature":"exclamation_rate","mean":0.0083,"variance":0.0066,"cv":9.7468},{"feature":"semicolon_rate","mean":0.119,"variance":0.685,"cv":6.9522},{"feature":"horizontal_rule_rate","mean":0.0569,"variance":0.1522,"cv":6.8607},{"feature":"question_rate","mean":0.0143,"variance":0.0096,"cv":6.8567},{"feature":"em_dash_rate","mean":0.1813,"variance":1.0005,"cv":5.5157}]},"realistic-ai-interview":{"model_count":148,"most_variable_features":[{"feature":"emoji_rate","mean":0.0086,"variance":0.0041,"cv":7.4271},{"feature":"list_item_rate","mean":0.2681,"variance":1.125,"cv":3.9565},{"feature":"transition_rate","mean":0.022,"variance":0.0069,"cv":3.79},{"feature":"heading_rate","mean":0.1924,"variance":0.2721,"cv":2.7108},{"feature":"exclamation_rate","mean":0.0273,"variance":0.0053,"cv":2.664}]},"satirical-fake-news":{"model_count":135,"most_variable_features":[{"feature":"emoji_rate","mean":0.1162,"variance":0.9364,"cv":8.3248},{"feature":"horizontal_rule_rate","mean":0.0361,"variance":0.0618,"cv":6.8802},{"feature":"transition_rate","mean":0.0182,"variance":0.0118,"cv":5.9627},{"feature":"sentence_length_variance","mean":283.3929,"variance":2618498.6167,"cv":5.71},{"feature":"booster_rate","mean":0.0225,"variance":0.015,"cv":5.4446}]},"sentience-test":{"model_count":151,"most_variable_features":[{"feature":"inline_code_rate","mean":0.001,"variance":0.0001,"cv":12.2474},{"feature":"exclamation_rate","mean":0.0354,"variance":0.1426,"cv":10.6557},{"feature":"heading_rate","mean":0.0906,"variance":0.1127,"cv":3.7055},{"feature":"list_item_rate","mean":0.1925,"variance":0.3166,"cv":2.9222},{"feature":"horizontal_rule_rate","mean":0.1161,"variance":0.0492,"cv":1.9106}]},"simple-recipe":{"model_count":152,"most_variable_features":[{"feature":"transition_rate","mean":0.0058,"variance":0.0027,"cv":9.0643},{"feature":"first_person_rate","mean":0.1091,"variance":0.9162,"cv":8.7697},{"feature":"question_rate","mean":0.0601,"variance":0.0781,"cv":4.6539},{"feature":"booster_rate","mean":0.0342,"variance":0.0123,"cv":3.2463},{"feature":"semicolon_rate","mean":0.0841,"variance":0.0511,"cv":2.6903}]},"standup-routine":{"model_count":150,"most_variable_features":[{"feature":"emoji_rate","mean":0.0266,"variance":0.0336,"cv":6.8991},{"feature":"list_item_rate","mean":0.1214,"variance":0.2175,"cv":3.8426},{"feature":"heading_rate","mean":0.0423,"variance":0.0141,"cv":2.8023},{"feature":"semicolon_rate","mean":0.0384,"variance":0.009,"cv":2.4726},{"feature":"horizontal_rule_rate","mean":0.1775,"variance":0.1734,"cv":2.3461}]},"stochastic-consistency":{"model_count":166,"most_variable_features":[{"feature":"booster_rate","mean":0.0152,"variance":0.0138,"cv":7.7011},{"feature":"semicolon_rate","mean":0.0535,"variance":0.098,"cv":5.8525},{"feature":"emoji_rate","mean":0.4592,"variance":3.8006,"cv":4.2453},{"feature":"hedging_rate","mean":0.0551,"variance":0.048,"cv":3.9768},{"feature":"transition_rate","mean":0.0763,"variance":0.0682,"cv":3.4199}]},"advanced-investment-memo":{"model_count":67,"most_variable_features":[{"feature":"emoji_rate","mean":0.0164,"variance":0.0089,"cv":5.7243},{"feature":"ellipsis_rate","mean":0.0089,"variance":0.0015,"cv":4.3023},{"feature":"sentence_length_variance","mean":2178.4287,"variance":19526440.107,"cv":2.0285},{"feature":"filler_rate","mean":0.037,"variance":0.0052,"cv":1.9506},{"feature":"transition_rate","mean":0.0387,"variance":0.0042,"cv":1.674}]},"adversarial-contract-review":{"model_count":115,"most_variable_features":[{"feature":"first_person_rate","mean":0.1692,"variance":1.2673,"cv":6.6532},{"feature":"sentence_length_variance","mean":500.2473,"variance":8559345.2137,"cv":5.8484},{"feature":"emoji_rate","mean":0.0761,"variance":0.1385,"cv":4.8933},{"feature":"exclamation_rate","mean":0.0042,"variance":0.0004,"cv":4.7699},{"feature":"inline_code_rate","mean":0.072,"variance":0.1147,"cv":4.7039}]},"debug-this-architecture":{"model_count":116,"most_variable_features":[{"feature":"exclamation_rate","mean":0.0086,"variance":0.0027,"cv":6.0459},{"feature":"sentence_length_variance","mean":5232.9367,"variance":729995166.0027,"cv":5.1631},{"feature":"question_rate","mean":0.0204,"variance":0.0057,"cv":3.7122},{"feature":"ellipsis_rate","mean":0.0299,"variance":0.0118,"cv":3.6364},{"feature":"emoji_rate","mean":0.2846,"variance":0.7573,"cv":3.0578}]},"estimate-complexity":{"model_count":142,"most_variable_features":[{"feature":"ellipsis_rate","mean":0.0036,"variance":0.0018,"cv":11.8743},{"feature":"emoji_rate","mean":0.0319,"variance":0.0373,"cv":6.0588},{"feature":"inline_code_rate","mean":0.0676,"variance":0.1442,"cv":5.6194},{"feature":"exclamation_rate","mean":0.0121,"variance":0.0028,"cv":4.3749},{"feature":"avg_paragraph_length","mean":39.638,"variance":14065.6762,"cv":2.992}]},"ethical-dilemma-with-stakeholders":{"model_count":119,"most_variable_features":[{"feature":"exclamation_rate","mean":0.0004,"variance":0,"cv":10.8628},{"feature":"inline_code_rate","mean":0.0009,"variance":0.0001,"cv":10.8628},{"feature":"emoji_rate","mean":0.0106,"variance":0.0042,"cv":6.1177},{"feature":"ellipsis_rate","mean":0.0099,"variance":0.0027,"cv":5.2187},{"feature":"sentence_length_variance","mean":476.0652,"variance":3110978.4189,"cv":3.7049}]},"explain-like-im-a-specific-expert":{"model_count":115,"most_variable_features":[{"feature":"exclamation_rate","mean":0.0139,"variance":0.003,"cv":3.9244},{"feature":"inline_code_rate","mean":0.0322,"variance":0.012,"cv":3.4023},{"feature":"list_item_rate","mean":0.0963,"variance":0.0826,"cv":2.9836},{"feature":"first_person_rate","mean":0.0173,"variance":0.0023,"cv":2.8022},{"feature":"ellipsis_rate","mean":0.0259,"variance":0.0031,"cv":2.1382}]},"historical-counterfactual-analysis":{"model_count":114,"most_variable_features":[{"feature":"ellipsis_rate","mean":0.0034,"variance":0.0013,"cv":10.6301},{"feature":"sentence_length_variance","mean":2139.5732,"variance":223832062.1235,"cv":6.9925},{"feature":"exclamation_rate","mean":0.0048,"variance":0.0006,"cv":5.2403},{"feature":"emoji_rate","mean":0.0297,"variance":0.0148,"cv":4.0984},{"feature":"second_person_rate","mean":0.0208,"variance":0.004,"cv":3.0188}]},"michelin-star-recipe":{"model_count":121,"most_variable_features":[{"feature":"ellipsis_rate","mean":0.0132,"variance":0.0211,"cv":10.9545},{"feature":"inline_code_rate","mean":0.0035,"variance":0.001,"cv":9.0224},{"feature":"emoji_rate","mean":0.0475,"variance":0.0723,"cv":5.6571},{"feature":"first_person_rate","mean":0.0363,"variance":0.0328,"cv":4.9953},{"feature":"question_rate","mean":0.0383,"variance":0.0357,"cv":4.9384}]},"mini-lbo-underwrite":{"model_count":66,"most_variable_features":[{"feature":"question_rate","mean":0.0012,"variance":0.0001,"cv":8.0623},{"feature":"filler_rate","mean":0.0033,"variance":0.0004,"cv":5.8558},{"feature":"ellipsis_rate","mean":0.0062,"variance":0.0013,"cv":5.7284},{"feature":"transition_rate","mean":0.0429,"variance":0.0485,"cv":5.1352},{"feature":"emoji_rate","mean":0.0268,"variance":0.0144,"cv":4.4793}]},"startup-pitch-teardown":{"model_count":119,"most_variable_features":[{"feature":"inline_code_rate","mean":0.0017,"variance":0.0003,"cv":10.8628},{"feature":"exclamation_rate","mean":0.0071,"variance":0.0011,"cv":4.6403},{"feature":"emoji_rate","mean":0.0664,"variance":0.0898,"cv":4.5147},{"feature":"sentence_length_variance","mean":1137.1644,"variance":20674057.0018,"cv":3.9984},{"feature":"em_dash_rate","mean":1.5959,"variance":27.2787,"cv":3.2726}]},"advanced-longevity-plan":{"model_count":120,"most_variable_features":[{"feature":"ellipsis_rate","mean":0.0007,"variance":0.0001,"cv":10.9087},{"feature":"inline_code_rate","mean":0.0055,"variance":0.001,"cv":5.7271},{"feature":"sentence_length_variance","mean":29371.7757,"variance":9960705044.6487,"cv":3.3979},{"feature":"emoji_rate","mean":0.2121,"variance":0.5085,"cv":3.3614},{"feature":"exclamation_rate","mean":0.0152,"variance":0.0018,"cv":2.7966}]},"count-letters":{"model_count":22,"most_variable_features":[{"feature":"em_dash_rate","mean":0.0131,"variance":0.0036,"cv":4.5826},{"feature":"heading_rate","mean":0.1417,"variance":0.4215,"cv":4.5826},{"feature":"emoji_rate","mean":0.4413,"variance":4.0897,"cv":4.5826},{"feature":"transition_rate","mean":0.1196,"variance":0.3005,"cv":4.5826},{"feature":"filler_rate","mean":0.0131,"variance":0.0036,"cv":4.5826}]}},"feature_correlations":[{"model_a":"qwen3.5-27b","model_b":"qwen3.5-35b-a3b","name_a":"Qwen: Qwen3.5 27B","name_b":"Qwen: Qwen3.5 35B A3B","provider_a":"qwen","provider_b":"qwen","shared_challenges":23,"avg_abs_correlation":0.7561,"top_correlated_features":[{"feature":"sentence_length_variance","r":0.9971},{"feature":"semicolon_rate","r":0.9762},{"feature":"transition_rate","r":0.9724},{"feature":"question_rate","r":0.9688},{"feature":"ellipsis_rate","r":0.9591}],"top_uncorrelated_features":[{"feature":"emoji_rate","r":0},{"feature":"inline_code_rate","r":0},{"feature":"code_block_rate","r":0}],"aggregate_similarity":0.911},{"model_a":"mistral-large-2","model_b":"mistral-large-2512","name_a":"Mistral Large 2","name_b":"Mistral Large 3 2512","provider_a":"mistral","provider_b":"mistral","shared_challenges":10,"avg_abs_correlation":0.7134,"top_correlated_features":[{"feature":"inline_code_rate","r":1},{"feature":"exclamation_rate","r":0.9998},{"feature":"horizontal_rule_rate","r":0.9705},{"feature":"heading_rate","r":0.9663},{"feature":"filler_rate","r":0.9532}],"top_uncorrelated_features":[{"feature":"first_person_rate","r":0},{"feature":"code_block_rate","r":0},{"feature":"ellipsis_rate","r":0}],"aggregate_similarity":0.8929},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-9b","name_a":"Qwen: Qwen3.5 122B A10B","name_b":"Qwen3.5 9B","provider_a":"qwen","provider_b":"qwen","shared_challenges":21,"avg_abs_correlation":0.7077,"top_correlated_features":[{"feature":"inline_code_rate","r":1},{"feature":"sentence_length_variance","r":0.9826},{"feature":"question_rate","r":0.9703},{"feature":"list_item_rate","r":0.9327},{"feature":"parenthetical_rate","r":0.9143}],"top_uncorrelated_features":[{"feature":"emoji_rate","r":0},{"feature":"code_block_rate","r":0},{"feature":"exclamation_rate","r":-0.0321}],"aggregate_similarity":0.8466},{"model_a":"mistral-medium-3.1","model_b":"mistral-small-creative","name_a":"Mistral Medium 3.1","name_b":"Mistral Small Creative","provider_a":"mistral","provider_b":"mistral","shared_challenges":22,"avg_abs_correlation":0.6918,"top_correlated_features":[{"feature":"inline_code_rate","r":1},{"feature":"parenthetical_rate","r":0.9782},{"feature":"exclamation_rate","r":0.964},{"feature":"em_dash_rate","r":0.9614},{"feature":"first_person_rate","r":0.9241}],"top_uncorrelated_features":[{"feature":"code_block_rate","r":0},{"feature":"semicolon_rate","r":-0.1685},{"feature":"avg_sentence_length","r":0.228}],"aggregate_similarity":0.9081},{"model_a":"aurora-alpha","model_b":"mercury-2","name_a":"Aurora Alpha","name_b":"Inception: Mercury 2","provider_a":"openrouter","provider_b":"inception","shared_challenges":22,"avg_abs_correlation":0.6833,"top_correlated_features":[{"feature":"question_rate","r":0.9966},{"feature":"exclamation_rate","r":0.9642},{"feature":"type_token_ratio","r":0.9641},{"feature":"hapax_ratio","r":0.9636},{"feature":"first_person_rate","r":0.9542}],"top_uncorrelated_features":[{"feature":"code_block_rate","r":0},{"feature":"booster_rate","r":0.0376},{"feature":"italic_rate","r":0.0875}],"aggregate_similarity":0.8895},{"model_a":"mercury-2","model_b":"solar-pro-3-free","name_a":"Inception: Mercury 2","name_b":"Solar Pro 3","provider_a":"inception","provider_b":"upstage","shared_challenges":18,"avg_abs_correlation":0.6753,"top_correlated_features":[{"feature":"ellipsis_rate","r":1},{"feature":"question_rate","r":0.9461},{"feature":"transition_rate","r":0.9428},{"feature":"booster_rate","r":0.9273},{"feature":"inline_code_rate","r":0.9272}],"top_uncorrelated_features":[{"feature":"code_block_rate","r":0},{"feature":"italic_rate","r":0.2397},{"feature":"horizontal_rule_rate","r":0.2736}],"aggregate_similarity":0.9261},{"model_a":"gpt-5.2","model_b":"gpt-5.2-chat","name_a":"GPT-5.2","name_b":"GPT-5.2 Chat","provider_a":"openai","provider_b":"openai","shared_challenges":15,"avg_abs_correlation":0.6657,"top_correlated_features":[{"feature":"exclamation_rate","r":1},{"feature":"transition_rate","r":0.9951},{"feature":"emoji_rate","r":0.9655},{"feature":"first_person_rate","r":0.9564},{"feature":"hapax_ratio","r":0.9445}],"top_uncorrelated_features":[{"feature":"inline_code_rate","r":0},{"feature":"code_block_rate","r":0},{"feature":"ellipsis_rate","r":0}],"aggregate_similarity":0.8516},{"model_a":"mistral-large-2512","model_b":"mistral-medium-3.1","name_a":"Mistral Large 3 2512","name_b":"Mistral Medium 3.1","provider_a":"mistral","provider_b":"mistral","shared_challenges":22,"avg_abs_correlation":0.6613,"top_correlated_features":[{"feature":"inline_code_rate","r":1},{"feature":"avg_sentence_length","r":0.9756},{"feature":"em_dash_rate","r":0.9614},{"feature":"question_rate","r":0.9561},{"feature":"avg_word_length","r":0.94}],"top_uncorrelated_features":[{"feature":"code_block_rate","r":0},{"feature":"transition_rate","r":0.088},{"feature":"sentence_length_variance","r":-0.1705}],"aggregate_similarity":0.8906},{"model_a":"gpt-oss-120b","model_b":"solar-pro-3-free","name_a":"GPT OSS 120B","name_b":"Solar Pro 3","provider_a":"openai","provider_b":"upstage","shared_challenges":18,"avg_abs_correlation":0.6503,"top_correlated_features":[{"feature":"first_person_rate","r":0.9986},{"feature":"question_rate","r":0.9835},{"feature":"avg_word_length","r":0.9535},{"feature":"transition_rate","r":0.8995},{"feature":"booster_rate","r":0.8968}],"top_uncorrelated_features":[{"feature":"code_block_rate","r":0},{"feature":"ellipsis_rate","r":-0.0962},{"feature":"inline_code_rate","r":0.2011}],"aggregate_similarity":0.8727},{"model_a":"mistral-medium-3.1","model_b":"mistral-small-2603","name_a":"Mistral Medium 3.1","name_b":"Mistral Small 4","provider_a":"mistral","provider_b":"mistral","shared_challenges":21,"avg_abs_correlation":0.6472,"top_correlated_features":[{"feature":"inline_code_rate","r":1},{"feature":"question_rate","r":0.948},{"feature":"second_person_rate","r":0.9312},{"feature":"avg_word_length","r":0.9057},{"feature":"hapax_ratio","r":0.9044}],"top_uncorrelated_features":[{"feature":"code_block_rate","r":0},{"feature":"semicolon_rate","r":0.0811},{"feature":"transition_rate","r":0.1221}],"aggregate_similarity":0.8998},{"model_a":"qwen3-coder","model_b":"qwen3-coder-plus","name_a":"Qwen3 Coder","name_b":"Qwen3 Coder Plus","provider_a":"qwen","provider_b":"qwen","shared_challenges":22,"avg_abs_correlation":0.6412,"top_correlated_features":[{"feature":"first_person_rate","r":0.973},{"feature":"question_rate","r":0.9575},{"feature":"avg_word_length","r":0.9291},{"feature":"italic_rate","r":0.9272},{"feature":"transition_rate","r":0.9199}],"top_uncorrelated_features":[{"feature":"inline_code_rate","r":0},{"feature":"code_block_rate","r":0},{"feature":"semicolon_rate","r":-0.0293}],"aggregate_similarity":0.861},{"model_a":"mistral-large-2512","model_b":"mistral-small-2603","name_a":"Mistral Large 3 2512","name_b":"Mistral Small 4","provider_a":"mistral","provider_b":"mistral","shared_challenges":23,"avg_abs_correlation":0.6394,"top_correlated_features":[{"feature":"inline_code_rate","r":1},{"feature":"question_rate","r":0.9689},{"feature":"hapax_ratio","r":0.94},{"feature":"parenthetical_rate","r":0.9349},{"feature":"type_token_ratio","r":0.9329}],"top_uncorrelated_features":[{"feature":"code_block_rate","r":0},{"feature":"sentence_length_variance","r":0.0996},{"feature":"semicolon_rate","r":0.1067}],"aggregate_similarity":0.9016},{"model_a":"aurora-alpha","model_b":"solar-pro-3-free","name_a":"Aurora Alpha","name_b":"Solar Pro 3","provider_a":"openrouter","provider_b":"upstage","shared_challenges":17,"avg_abs_correlation":0.6384,"top_correlated_features":[{"feature":"inline_code_rate","r":0.9692},{"feature":"ellipsis_rate","r":0.9654},{"feature":"exclamation_rate","r":0.9573},{"feature":"question_rate","r":0.9409},{"feature":"avg_word_length","r":0.9197}],"top_uncorrelated_features":[{"feature":"code_block_rate","r":0},{"feature":"booster_rate","r":0.1313},{"feature":"comma_rate","r":0.2502}],"aggregate_similarity":0.907},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-flash-02-23","name_a":"Qwen: Qwen3.5 122B A10B","name_b":"Qwen: Qwen3.5 Flash","provider_a":"qwen","provider_b":"qwen","shared_challenges":23,"avg_abs_correlation":0.6362,"top_correlated_features":[{"feature":"inline_code_rate","r":1},{"feature":"transition_rate","r":0.993},{"feature":"question_rate","r":0.9897},{"feature":"avg_sentence_length","r":0.9614},{"feature":"sentence_length_variance","r":0.9593}],"top_uncorrelated_features":[{"feature":"code_block_rate","r":0},{"feature":"exclamation_rate","r":-0.0083},{"feature":"emoji_rate","r":-0.0455}],"aggregate_similarity":0.8451},{"model_a":"gpt-oss-120b","model_b":"mercury-2","name_a":"GPT OSS 120B","name_b":"Inception: Mercury 2","provider_a":"openai","provider_b":"inception","shared_challenges":21,"avg_abs_correlation":0.6316,"top_correlated_features":[{"feature":"transition_rate","r":0.9821},{"feature":"booster_rate","r":0.9674},{"feature":"question_rate","r":0.96},{"feature":"hapax_ratio","r":0.9574},{"feature":"type_token_ratio","r":0.9493}],"top_uncorrelated_features":[{"feature":"code_block_rate","r":0},{"feature":"ellipsis_rate","r":0.0041},{"feature":"sentence_length_variance","r":0.0246}],"aggregate_similarity":0.8682},{"model_a":"claude-opus-4.1","model_b":"claude-sonnet-4","name_a":"Claude Opus 4.1","name_b":"Claude Sonnet 4","provider_a":"anthropic","provider_b":"anthropic","shared_challenges":14,"avg_abs_correlation":0.6016,"top_correlated_features":[{"feature":"question_rate","r":0.978},{"feature":"em_dash_rate","r":0.9661},{"feature":"bold_rate","r":0.8813},{"feature":"exclamation_rate","r":0.8546},{"feature":"booster_rate","r":0.8332}],"top_uncorrelated_features":[{"feature":"code_block_rate","r":0},{"feature":"ellipsis_rate","r":0},{"feature":"comma_rate","r":-0.0819}],"aggregate_similarity":0.8922},{"model_a":"qwen3-coder","model_b":"qwen3-coder-flash","name_a":"Qwen3 Coder","name_b":"Qwen3 Coder Flash","provider_a":"qwen","provider_b":"qwen","shared_challenges":22,"avg_abs_correlation":0.5972,"top_correlated_features":[{"feature":"sentence_length_variance","r":0.9805},{"feature":"first_person_rate","r":0.9353},{"feature":"question_rate","r":0.9327},{"feature":"avg_word_length","r":0.9319},{"feature":"transition_rate","r":0.8977}],"top_uncorrelated_features":[{"feature":"emoji_rate","r":0},{"feature":"inline_code_rate","r":0},{"feature":"code_block_rate","r":0}],"aggregate_similarity":0.9556},{"model_a":"mistral-large-2512","model_b":"mistral-small-creative","name_a":"Mistral Large 3 2512","name_b":"Mistral Small Creative","provider_a":"mistral","provider_b":"mistral","shared_challenges":24,"avg_abs_correlation":0.5883,"top_correlated_features":[{"feature":"inline_code_rate","r":1},{"feature":"exclamation_rate","r":0.9536},{"feature":"em_dash_rate","r":0.9446},{"feature":"comma_rate","r":0.9042},{"feature":"first_person_rate","r":0.8721}],"top_uncorrelated_features":[{"feature":"code_block_rate","r":0},{"feature":"sentence_length_variance","r":0.0145},{"feature":"semicolon_rate","r":0.0307}],"aggregate_similarity":0.9459},{"model_a":"aurora-alpha","model_b":"gpt-oss-20b","name_a":"Aurora Alpha","name_b":"GPT OSS 20B","provider_a":"openrouter","provider_b":"openai","shared_challenges":19,"avg_abs_correlation":0.581,"top_correlated_features":[{"feature":"inline_code_rate","r":1},{"feature":"question_rate","r":0.9891},{"feature":"first_person_rate","r":0.9622},{"feature":"type_token_ratio","r":0.9564},{"feature":"hapax_ratio","r":0.948}],"top_uncorrelated_features":[{"feature":"code_block_rate","r":0},{"feature":"transition_rate","r":0.0292},{"feature":"ellipsis_rate","r":-0.0364}],"aggregate_similarity":0.8511},{"model_a":"mistral-small-2603","model_b":"mistral-small-creative","name_a":"Mistral Small 4","name_b":"Mistral Small Creative","provider_a":"mistral","provider_b":"mistral","shared_challenges":23,"avg_abs_correlation":0.5682,"top_correlated_features":[{"feature":"inline_code_rate","r":1},{"feature":"second_person_rate","r":0.9068},{"feature":"parenthetical_rate","r":0.8808},{"feature":"italic_rate","r":0.8694},{"feature":"question_rate","r":0.8561}],"top_uncorrelated_features":[{"feature":"code_block_rate","r":0},{"feature":"emoji_rate","r":0.0533},{"feature":"transition_rate","r":0.0559}],"aggregate_similarity":0.8744},{"model_a":"devstral-medium","model_b":"devstral-small","name_a":"Mistral Devstral Medium","name_b":"Mistral Devstral Small 1.1","provider_a":"mistral","provider_b":"mistral","shared_challenges":21,"avg_abs_correlation":0.5205,"top_correlated_features":[{"feature":"first_person_rate","r":0.9956},{"feature":"question_rate","r":0.9919},{"feature":"hapax_ratio","r":0.9719},{"feature":"type_token_ratio","r":0.9656},{"feature":"avg_word_length","r":0.9584}],"top_uncorrelated_features":[{"feature":"horizontal_rule_rate","r":0},{"feature":"emoji_rate","r":0},{"feature":"inline_code_rate","r":0}],"aggregate_similarity":0.9568},{"model_a":"gemma-3n-e4b-it","model_b":"glm-4.5-air","name_a":"Gemma 3n 4B","name_b":"Z.AI: GLM 4.5 Air","provider_a":"google","provider_b":"zhipu","shared_challenges":10,"avg_abs_correlation":0.5164,"top_correlated_features":[{"feature":"exclamation_rate","r":0.99},{"feature":"question_rate","r":0.9082},{"feature":"hedging_rate","r":0.8622},{"feature":"booster_rate","r":0.8545},{"feature":"type_token_ratio","r":0.8122}],"top_uncorrelated_features":[{"feature":"emoji_rate","r":0},{"feature":"inline_code_rate","r":0},{"feature":"code_block_rate","r":0}],"aggregate_similarity":0.8728},{"model_a":"llama-4-maverick","model_b":"mistral-nemo","name_a":"Llama 4 Maverick","name_b":"Mistral Nemo","provider_a":"meta","provider_b":"mistral","shared_challenges":10,"avg_abs_correlation":0.5061,"top_correlated_features":[{"feature":"exclamation_rate","r":1},{"feature":"question_rate","r":1},{"feature":"type_token_ratio","r":0.9129},{"feature":"parenthetical_rate","r":0.8961},{"feature":"sentence_length_variance","r":0.8849}],"top_uncorrelated_features":[{"feature":"first_person_rate","r":0},{"feature":"horizontal_rule_rate","r":0},{"feature":"emoji_rate","r":0}],"aggregate_similarity":0.8637},{"model_a":"horizon-alpha","model_b":"horizon-beta","name_a":"Horizon Alpha","name_b":"Horizon Beta","provider_a":"openrouter","provider_b":"openrouter","shared_challenges":14,"avg_abs_correlation":0.5017,"top_correlated_features":[{"feature":"first_person_rate","r":0.9862},{"feature":"transition_rate","r":0.9675},{"feature":"exclamation_rate","r":0.9404},{"feature":"type_token_ratio","r":0.938},{"feature":"avg_word_length","r":0.9368}],"top_uncorrelated_features":[{"feature":"horizontal_rule_rate","r":0},{"feature":"emoji_rate","r":0},{"feature":"inline_code_rate","r":0}],"aggregate_similarity":0.868},{"model_a":"gpt-5.4","model_b":"gpt-5.4-mini","name_a":"GPT-5.4","name_b":"GPT-5.4 Mini","provider_a":"openai","provider_b":"openai","shared_challenges":22,"avg_abs_correlation":0.4919,"top_correlated_features":[{"feature":"first_person_rate","r":0.9294},{"feature":"second_person_rate","r":0.915},{"feature":"question_rate","r":0.8714},{"feature":"hedging_rate","r":0.8598},{"feature":"avg_word_length","r":0.8543}],"top_uncorrelated_features":[{"feature":"emoji_rate","r":0},{"feature":"inline_code_rate","r":0},{"feature":"code_block_rate","r":0}],"aggregate_similarity":0.9328},{"model_a":"gpt-5-pro","model_b":"horizon-alpha","name_a":"GPT-5 Pro","name_b":"Horizon Alpha","provider_a":"openai","provider_b":"openrouter","shared_challenges":11,"avg_abs_correlation":0.4767,"top_correlated_features":[{"feature":"ellipsis_rate","r":1},{"feature":"exclamation_rate","r":0.999},{"feature":"sentence_length_variance","r":0.9858},{"feature":"parenthetical_rate","r":0.9784},{"feature":"avg_word_length","r":0.9565}],"top_uncorrelated_features":[{"feature":"horizontal_rule_rate","r":0},{"feature":"emoji_rate","r":0},{"feature":"inline_code_rate","r":0}],"aggregate_similarity":0.8592},{"model_a":"llama-4-maverick","model_b":"llama-4-scout","name_a":"Llama 4 Maverick","name_b":"Llama 4 Scout","provider_a":"meta","provider_b":"meta","shared_challenges":10,"avg_abs_correlation":0.4327,"top_correlated_features":[{"feature":"exclamation_rate","r":1},{"feature":"second_person_rate","r":0.9773},{"feature":"avg_word_length","r":0.9753},{"feature":"colon_rate","r":0.8874},{"feature":"italic_rate","r":0.8531}],"top_uncorrelated_features":[{"feature":"first_person_rate","r":0},{"feature":"horizontal_rule_rate","r":0},{"feature":"emoji_rate","r":0}],"aggregate_similarity":0.919},{"model_a":"gpt-5-mini","model_b":"horizon-beta","name_a":"GPT-5 Mini","name_b":"Horizon Beta","provider_a":"openai","provider_b":"openrouter","shared_challenges":15,"avg_abs_correlation":0.4256,"top_correlated_features":[{"feature":"first_person_rate","r":0.9955},{"feature":"semicolon_rate","r":0.9701},{"feature":"avg_word_length","r":0.9482},{"feature":"exclamation_rate","r":0.9421},{"feature":"parenthetical_rate","r":0.9163}],"top_uncorrelated_features":[{"feature":"horizontal_rule_rate","r":0},{"feature":"emoji_rate","r":0},{"feature":"inline_code_rate","r":0}],"aggregate_similarity":0.9005},{"model_a":"gpt-5","model_b":"gpt-5-nano","name_a":"GPT-5","name_b":"GPT-5 Nano","provider_a":"openai","provider_b":"openai","shared_challenges":14,"avg_abs_correlation":0.3978,"top_correlated_features":[{"feature":"booster_rate","r":0.9772},{"feature":"parenthetical_rate","r":0.9355},{"feature":"first_person_rate","r":0.9353},{"feature":"hapax_ratio","r":0.9248},{"feature":"avg_word_length","r":0.9203}],"top_uncorrelated_features":[{"feature":"horizontal_rule_rate","r":0},{"feature":"emoji_rate","r":0},{"feature":"inline_code_rate","r":0}],"aggregate_similarity":0.9116},{"model_a":"llama-4-scout","model_b":"mistral-nemo","name_a":"Llama 4 Scout","name_b":"Mistral Nemo","provider_a":"meta","provider_b":"mistral","shared_challenges":10,"avg_abs_correlation":0.3643,"top_correlated_features":[{"feature":"exclamation_rate","r":1},{"feature":"avg_word_length","r":0.8453},{"feature":"hedging_rate","r":0.8399},{"feature":"second_person_rate","r":0.8392},{"feature":"booster_rate","r":0.75}],"top_uncorrelated_features":[{"feature":"first_person_rate","r":0},{"feature":"horizontal_rule_rate","r":0},{"feature":"emoji_rate","r":0}],"aggregate_similarity":0.872}],"length_correlations":[{"model_a":"horizon-alpha","model_b":"horizon-beta","name_a":"Horizon Alpha","name_b":"Horizon Beta","shared_challenges":14,"length_correlation":0.9866,"avg_length_ratio":0.8878,"aggregate_similarity":0.868},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-9b","name_a":"Qwen: Qwen3.5 122B A10B","name_b":"Qwen3.5 9B","shared_challenges":21,"length_correlation":0.9775,"avg_length_ratio":0.8811,"aggregate_similarity":0.8466},{"model_a":"gemini-2.5-flash-preview","model_b":"gemini-2.5-flash-preview-thinking","name_a":"Gemini 2.5 Flash Preview","name_b":"Gemini 2.5 Flash Preview (thinking)","shared_challenges":6,"length_correlation":0.9771,"avg_length_ratio":0.8862,"aggregate_similarity":0.7777},{"model_a":"aurora-alpha","model_b":"mercury-2","name_a":"Aurora Alpha","name_b":"Inception: Mercury 2","shared_challenges":22,"length_correlation":0.9481,"avg_length_ratio":0.849,"aggregate_similarity":0.8895},{"model_a":"aurora-alpha","model_b":"gpt-oss-20b","name_a":"Aurora Alpha","name_b":"GPT OSS 20B","shared_challenges":19,"length_correlation":0.9467,"avg_length_ratio":0.7686,"aggregate_similarity":0.8511},{"model_a":"qwen3-30b-a3b-thinking-2507","model_b":"qwen3-coder-next","name_a":"Qwen3 30B A3B Thinking 2507","name_b":"Qwen3 Coder Next","shared_challenges":13,"length_correlation":0.9405,"avg_length_ratio":0.7858,"aggregate_similarity":0.7717},{"model_a":"qwen3.5-35b-a3b","model_b":"qwen3.5-9b","name_a":"Qwen: Qwen3.5 35B A3B","name_b":"Qwen3.5 9B","shared_challenges":21,"length_correlation":0.9381,"avg_length_ratio":0.8751,"aggregate_similarity":0.7872},{"model_a":"glm-4.7","model_b":"glm-5","name_a":"Z.AI: GLM 4.7","name_b":"Z.ai: GLM 5","shared_challenges":20,"length_correlation":0.938,"avg_length_ratio":0.8386,"aggregate_similarity":0.7818},{"model_a":"claude-3.7-sonnet-thinking","model_b":"qwen3-coder","name_a":"Claude 3.7 Thinking Sonnet","name_b":"Qwen3 Coder","shared_challenges":13,"length_correlation":0.9348,"avg_length_ratio":0.8093,"aggregate_similarity":0.799},{"model_a":"qwen-plus-2025-07-28-thinking","model_b":"qwen3-30b-a3b-thinking-2507","name_a":"Qwen Plus 0728 (thinking)","name_b":"Qwen3 30B A3B Thinking 2507","shared_challenges":12,"length_correlation":0.9311,"avg_length_ratio":0.7776,"aggregate_similarity":0.7851},{"model_a":"gpt-5-mini","model_b":"gpt-5-nano","name_a":"GPT-5 Mini","name_b":"GPT-5 Nano","shared_challenges":14,"length_correlation":0.9284,"avg_length_ratio":0.7734,"aggregate_similarity":0.7895},{"model_a":"gemini-2.0-flash-thinking-exp","model_b":"gemma-3-27b-it","name_a":"Gemini 2.0 Flash Thinking","name_b":"Gemma 3 27B","shared_challenges":13,"length_correlation":0.9244,"avg_length_ratio":0.6123,"aggregate_similarity":0.8172},{"model_a":"nova-2-lite-v1-free","model_b":"qwen3-30b-a3b-thinking-2507","name_a":"Amazon Nova 2 Lite","name_b":"Qwen3 30B A3B Thinking 2507","shared_challenges":13,"length_correlation":0.9181,"avg_length_ratio":0.7443,"aggregate_similarity":0.8046},{"model_a":"sherlock-dash-alpha","model_b":"sherlock-think-alpha","name_a":"Sherlock Dash Alpha","name_b":"Sherlock Think Alpha","shared_challenges":14,"length_correlation":0.9157,"avg_length_ratio":0.788,"aggregate_similarity":0.8275},{"model_a":"gpt-5-pro","model_b":"horizon-alpha","name_a":"GPT-5 Pro","name_b":"Horizon Alpha","shared_challenges":11,"length_correlation":0.9148,"avg_length_ratio":0.7171,"aggregate_similarity":0.8592},{"model_a":"claude-opus-4.1","model_b":"qwen3-coder-plus","name_a":"Claude Opus 4.1","name_b":"Qwen3 Coder Plus","shared_challenges":15,"length_correlation":0.9123,"avg_length_ratio":0.7594,"aggregate_similarity":0.7998},{"model_a":"deepseek-v3-03-24","model_b":"mistral-medium-3","name_a":"DeepSeek V3 (March 2024)","name_b":"Mistral Medium 3","shared_challenges":13,"length_correlation":0.9069,"avg_length_ratio":0.8259,"aggregate_similarity":0.8004},{"model_a":"mistral-large-2512","model_b":"mistral-small-creative","name_a":"Mistral Large 3 2512","name_b":"Mistral Small Creative","shared_challenges":24,"length_correlation":0.9037,"avg_length_ratio":0.767,"aggregate_similarity":0.9459},{"model_a":"gpt-5.1-codex-max","model_b":"o4-mini","name_a":"GPT-5.1 Codex Max","name_b":"OpenAI o4-mini","shared_challenges":8,"length_correlation":0.9005,"avg_length_ratio":0.7871,"aggregate_similarity":0.8093},{"model_a":"mercury","model_b":"mercury-2","name_a":"Inception: Mercury","name_b":"Inception: Mercury 2","shared_challenges":16,"length_correlation":0.8969,"avg_length_ratio":0.7121,"aggregate_similarity":0.8183},{"model_a":"gpt-5-mini","model_b":"gpt-5-pro","name_a":"GPT-5 Mini","name_b":"GPT-5 Pro","shared_challenges":11,"length_correlation":0.8911,"avg_length_ratio":0.7651,"aggregate_similarity":0.7641},{"model_a":"qwen3.5-27b","model_b":"qwen3.5-35b-a3b","name_a":"Qwen: Qwen3.5 27B","name_b":"Qwen: Qwen3.5 35B A3B","shared_challenges":23,"length_correlation":0.8858,"avg_length_ratio":0.838,"aggregate_similarity":0.911},{"model_a":"mistral-large-2512","model_b":"mistral-medium-3.1","name_a":"Mistral Large 3 2512","name_b":"Mistral Medium 3.1","shared_challenges":22,"length_correlation":0.8828,"avg_length_ratio":0.7647,"aggregate_similarity":0.8906},{"model_a":"gemini-3-flash-preview","model_b":"glm-4.7","name_a":"Gemini 3 Flash Preview","name_b":"Z.AI: GLM 4.7","shared_challenges":21,"length_correlation":0.8828,"avg_length_ratio":0.7921,"aggregate_similarity":0.8101},{"model_a":"pony-alpha","model_b":"qwen3.5-flash-02-23","name_a":"Pony Alpha","name_b":"Qwen: Qwen3.5 Flash","shared_challenges":20,"length_correlation":0.8817,"avg_length_ratio":0.7837,"aggregate_similarity":0.7769},{"model_a":"glm-5","model_b":"qwen3.5-35b-a3b","name_a":"Z.ai: GLM 5","name_b":"Qwen: Qwen3.5 35B A3B","shared_challenges":22,"length_correlation":0.8796,"avg_length_ratio":0.8192,"aggregate_similarity":0.7734},{"model_a":"kimi-k2-0905","model_b":"o3","name_a":"MoonshotAI: Kimi K2 0905","name_b":"OpenAI o3","shared_challenges":16,"length_correlation":0.8795,"avg_length_ratio":0.6971,"aggregate_similarity":0.7728},{"model_a":"pony-alpha","model_b":"qwen3.5-122b-a10b","name_a":"Pony Alpha","name_b":"Qwen: Qwen3.5 122B A10B","shared_challenges":20,"length_correlation":0.8782,"avg_length_ratio":0.8085,"aggregate_similarity":0.7967},{"model_a":"gpt-5-mini","model_b":"horizon-alpha","name_a":"GPT-5 Mini","name_b":"Horizon Alpha","shared_challenges":14,"length_correlation":0.8763,"avg_length_ratio":0.7241,"aggregate_similarity":0.7917},{"model_a":"glm-4.7","model_b":"qwen3.5-flash-02-23","name_a":"Z.AI: GLM 4.7","name_b":"Qwen: Qwen3.5 Flash","shared_challenges":21,"length_correlation":0.8763,"avg_length_ratio":0.8145,"aggregate_similarity":0.7734}],"feature_twins":{"avg_word_length":[{"model_a":"llama-4-maverick","model_b":"llama-4-scout","name_a":"Llama 4 Maverick","name_b":"Llama 4 Scout","correlation":0.9753,"shared_challenges":10},{"model_a":"qwen3.5-27b","model_b":"qwen3.5-flash-02-23","name_a":"Qwen: Qwen3.5 27B","name_b":"Qwen: Qwen3.5 Flash","correlation":0.9647,"shared_challenges":23},{"model_a":"devstral-medium","model_b":"devstral-small","name_a":"Mistral Devstral Medium","name_b":"Mistral Devstral Small 1.1","correlation":0.9584,"shared_challenges":21}],"type_token_ratio":[{"model_a":"devstral-medium","model_b":"devstral-small","name_a":"Mistral Devstral Medium","name_b":"Mistral Devstral Small 1.1","correlation":0.9656,"shared_challenges":21},{"model_a":"aurora-alpha","model_b":"mercury-2","name_a":"Aurora Alpha","name_b":"Inception: Mercury 2","correlation":0.9641,"shared_challenges":22},{"model_a":"aurora-alpha","model_b":"gpt-oss-20b","name_a":"Aurora Alpha","name_b":"GPT OSS 20B","correlation":0.9564,"shared_challenges":19}],"hapax_ratio":[{"model_a":"devstral-medium","model_b":"devstral-small","name_a":"Mistral Devstral Medium","name_b":"Mistral Devstral Small 1.1","correlation":0.9719,"shared_challenges":21},{"model_a":"aurora-alpha","model_b":"mercury-2","name_a":"Aurora Alpha","name_b":"Inception: Mercury 2","correlation":0.9636,"shared_challenges":22},{"model_a":"qwen3.5-27b","model_b":"qwen3.5-35b-a3b","name_a":"Qwen: Qwen3.5 27B","name_b":"Qwen: Qwen3.5 35B A3B","correlation":0.9579,"shared_challenges":23}],"avg_sentence_length":[{"model_a":"mistral-large-2512","model_b":"mistral-medium-3.1","name_a":"Mistral Large 3 2512","name_b":"Mistral Medium 3.1","correlation":0.9756,"shared_challenges":22},{"model_a":"qwen3.5-397b-a17b","model_b":"qwen3.5-flash-02-23","name_a":"Qwen: Qwen3.5 397B A17B","name_b":"Qwen: Qwen3.5 Flash","correlation":0.9654,"shared_challenges":23},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-flash-02-23","name_a":"Qwen: Qwen3.5 122B A10B","name_b":"Qwen: Qwen3.5 Flash","correlation":0.9614,"shared_challenges":23}],"sentence_length_variance":[{"model_a":"qwen3.5-27b","model_b":"qwen3.5-35b-a3b","name_a":"Qwen: Qwen3.5 27B","name_b":"Qwen: Qwen3.5 35B A3B","correlation":0.9971,"shared_challenges":23},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-35b-a3b","name_a":"Qwen: Qwen3.5 122B A10B","name_b":"Qwen: Qwen3.5 35B A3B","correlation":0.9887,"shared_challenges":23},{"model_a":"gpt-5-pro","model_b":"horizon-alpha","name_a":"GPT-5 Pro","name_b":"Horizon Alpha","correlation":0.9858,"shared_challenges":11}],"comma_rate":[{"model_a":"mistral-medium-3.1","model_b":"mistral-small-creative","name_a":"Mistral Medium 3.1","name_b":"Mistral Small Creative","correlation":0.9136,"shared_challenges":22},{"model_a":"mistral-large-2512","model_b":"mistral-small-creative","name_a":"Mistral Large 3 2512","name_b":"Mistral Small Creative","correlation":0.9042,"shared_challenges":24},{"model_a":"mistral-large-2512","model_b":"mistral-medium-3.1","name_a":"Mistral Large 3 2512","name_b":"Mistral Medium 3.1","correlation":0.8964,"shared_challenges":22}],"semicolon_rate":[{"model_a":"qwen3.5-27b","model_b":"qwen3.5-35b-a3b","name_a":"Qwen: Qwen3.5 27B","name_b":"Qwen: Qwen3.5 35B A3B","correlation":0.9762,"shared_challenges":23},{"model_a":"gpt-5-mini","model_b":"horizon-beta","name_a":"GPT-5 Mini","name_b":"Horizon Beta","correlation":0.9701,"shared_challenges":15},{"model_a":"gemma-3n-e4b-it","model_b":"llama-4-maverick","name_a":"Gemma 3n 4B","name_b":"Llama 4 Maverick","correlation":0.8976,"shared_challenges":12}],"colon_rate":[{"model_a":"qwen3.5-27b","model_b":"qwen3.5-35b-a3b","name_a":"Qwen: Qwen3.5 27B","name_b":"Qwen: Qwen3.5 35B A3B","correlation":0.9359,"shared_challenges":23},{"model_a":"devstral-medium","model_b":"devstral-small","name_a":"Mistral Devstral Medium","name_b":"Mistral Devstral Small 1.1","correlation":0.9318,"shared_challenges":21},{"model_a":"qwen3.5-397b-a17b","model_b":"qwen3.5-flash-02-23","name_a":"Qwen: Qwen3.5 397B A17B","name_b":"Qwen: Qwen3.5 Flash","correlation":0.9168,"shared_challenges":23}],"exclamation_rate":[{"model_a":"llama-4-maverick","model_b":"llama-4-scout","name_a":"Llama 4 Maverick","name_b":"Llama 4 Scout","correlation":1,"shared_challenges":10},{"model_a":"llama-4-scout","model_b":"mistral-nemo","name_a":"Llama 4 Scout","name_b":"Mistral Nemo","correlation":1,"shared_challenges":10},{"model_a":"llama-4-maverick","model_b":"mistral-nemo","name_a":"Llama 4 Maverick","name_b":"Mistral Nemo","correlation":1,"shared_challenges":10}],"question_rate":[{"model_a":"llama-4-maverick","model_b":"mistral-nemo","name_a":"Llama 4 Maverick","name_b":"Mistral Nemo","correlation":1,"shared_challenges":10},{"model_a":"claude-4.5-sonnet","model_b":"claude-opus-4.1","name_a":"Claude Sonnet 4.5","name_b":"Claude Opus 4.1","correlation":0.9983,"shared_challenges":13},{"model_a":"aurora-alpha","model_b":"mercury-2","name_a":"Aurora Alpha","name_b":"Inception: Mercury 2","correlation":0.9966,"shared_challenges":22}],"em_dash_rate":[{"model_a":"claude-opus-4.1","model_b":"claude-sonnet-4","name_a":"Claude Opus 4.1","name_b":"Claude Sonnet 4","correlation":0.9661,"shared_challenges":14},{"model_a":"mistral-medium-3.1","model_b":"mistral-small-creative","name_a":"Mistral Medium 3.1","name_b":"Mistral Small Creative","correlation":0.9614,"shared_challenges":22},{"model_a":"mistral-large-2512","model_b":"mistral-medium-3.1","name_a":"Mistral Large 3 2512","name_b":"Mistral Medium 3.1","correlation":0.9614,"shared_challenges":22}],"ellipsis_rate":[{"model_a":"mercury-2","model_b":"solar-pro-3-free","name_a":"Inception: Mercury 2","name_b":"Solar Pro 3","correlation":1,"shared_challenges":18},{"model_a":"gpt-5-pro","model_b":"horizon-alpha","name_a":"GPT-5 Pro","name_b":"Horizon Alpha","correlation":1,"shared_challenges":11},{"model_a":"cypher-alpha-free","model_b":"gpt-3.5-turbo","name_a":"Cypher Alpha (free)","name_b":"GPT-3.5 Turbo","correlation":1,"shared_challenges":10}],"parenthetical_rate":[{"model_a":"gpt-5-pro","model_b":"horizon-alpha","name_a":"GPT-5 Pro","name_b":"Horizon Alpha","correlation":0.9784,"shared_challenges":11},{"model_a":"mistral-medium-3.1","model_b":"mistral-small-creative","name_a":"Mistral Medium 3.1","name_b":"Mistral Small Creative","correlation":0.9782,"shared_challenges":22},{"model_a":"claude-4.5-sonnet","model_b":"claude-opus-4.1","name_a":"Claude Sonnet 4.5","name_b":"Claude Opus 4.1","correlation":0.9601,"shared_challenges":13}],"heading_rate":[{"model_a":"mistral-large-2","model_b":"mistral-large-2512","name_a":"Mistral Large 2","name_b":"Mistral Large 3 2512","correlation":0.9663,"shared_challenges":10},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-flash-02-23","name_a":"Qwen: Qwen3.5 122B A10B","name_b":"Qwen: Qwen3.5 Flash","correlation":0.9233,"shared_challenges":23},{"model_a":"qwen3.5-397b-a17b","model_b":"qwen3.5-flash-02-23","name_a":"Qwen: Qwen3.5 397B A17B","name_b":"Qwen: Qwen3.5 Flash","correlation":0.8907,"shared_challenges":23}],"bold_rate":[{"model_a":"qwen3.5-397b-a17b","model_b":"qwen3.5-flash-02-23","name_a":"Qwen: Qwen3.5 397B A17B","name_b":"Qwen: Qwen3.5 Flash","correlation":0.9384,"shared_challenges":23},{"model_a":"gpt-5.2","model_b":"gpt-5.2-chat","name_a":"GPT-5.2","name_b":"GPT-5.2 Chat","correlation":0.9263,"shared_challenges":15},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-35b-a3b","name_a":"Qwen: Qwen3.5 122B A10B","name_b":"Qwen: Qwen3.5 35B A3B","correlation":0.8999,"shared_challenges":23}],"italic_rate":[{"model_a":"qwen3-coder","model_b":"qwen3-coder-plus","name_a":"Qwen3 Coder","name_b":"Qwen3 Coder Plus","correlation":0.9272,"shared_challenges":22},{"model_a":"mistral-medium-3.1","model_b":"mistral-small-2603","name_a":"Mistral Medium 3.1","name_b":"Mistral Small 4","correlation":0.8859,"shared_challenges":21},{"model_a":"mistral-small-2603","model_b":"mistral-small-creative","name_a":"Mistral Small 4","name_b":"Mistral Small Creative","correlation":0.8694,"shared_challenges":23}],"list_item_rate":[{"model_a":"cypher-alpha-free","model_b":"gpt-3.5-turbo","name_a":"Cypher Alpha (free)","name_b":"GPT-3.5 Turbo","correlation":0.9842,"shared_challenges":10},{"model_a":"aurora-alpha","model_b":"mercury-2","name_a":"Aurora Alpha","name_b":"Inception: Mercury 2","correlation":0.9408,"shared_challenges":22},{"model_a":"qwen3.5-35b-a3b","model_b":"qwen3.5-flash-02-23","name_a":"Qwen: Qwen3.5 35B A3B","name_b":"Qwen: Qwen3.5 Flash","correlation":0.9399,"shared_challenges":23}],"inline_code_rate":[{"model_a":"mistral-large-2512","model_b":"mistral-small-creative","name_a":"Mistral Large 3 2512","name_b":"Mistral Small Creative","correlation":1,"shared_challenges":24},{"model_a":"mistral-medium-3.1","model_b":"mistral-small-creative","name_a":"Mistral Medium 3.1","name_b":"Mistral Small Creative","correlation":1,"shared_challenges":22},{"model_a":"mistral-large-2512","model_b":"mistral-small-2603","name_a":"Mistral Large 3 2512","name_b":"Mistral Small 4","correlation":1,"shared_challenges":23}],"emoji_rate":[{"model_a":"gpt-5.2","model_b":"gpt-5.2-chat","name_a":"GPT-5.2","name_b":"GPT-5.2 Chat","correlation":0.9655,"shared_challenges":15},{"model_a":"sherlock-dash-alpha","model_b":"sherlock-think-alpha","name_a":"Sherlock Dash Alpha","name_b":"Sherlock Think Alpha","correlation":0.8416,"shared_challenges":14},{"model_a":"mercury-2","model_b":"solar-pro-3-free","name_a":"Inception: Mercury 2","name_b":"Solar Pro 3","correlation":0.8314,"shared_challenges":18}],"horizontal_rule_rate":[{"model_a":"mistral-large-2","model_b":"mistral-large-2512","name_a":"Mistral Large 2","name_b":"Mistral Large 3 2512","correlation":0.9705,"shared_challenges":10},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-35b-a3b","name_a":"Qwen: Qwen3.5 122B A10B","name_b":"Qwen: Qwen3.5 35B A3B","correlation":0.9238,"shared_challenges":23},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-9b","name_a":"Qwen: Qwen3.5 122B A10B","name_b":"Qwen3.5 9B","correlation":0.9085,"shared_challenges":21}],"hedging_rate":[{"model_a":"mistral-large-2","model_b":"mistral-small-2603","name_a":"Mistral Large 2","name_b":"Mistral Small 4","correlation":0.9868,"shared_challenges":10},{"model_a":"claude-4.5-sonnet","model_b":"claude-sonnet-4","name_a":"Claude Sonnet 4.5","name_b":"Claude Sonnet 4","correlation":0.927,"shared_challenges":14},{"model_a":"mistral-large-2","model_b":"mistral-large-2512","name_a":"Mistral Large 2","name_b":"Mistral Large 3 2512","correlation":0.9172,"shared_challenges":10}],"booster_rate":[{"model_a":"gpt-5","model_b":"gpt-5-nano","name_a":"GPT-5","name_b":"GPT-5 Nano","correlation":0.9772,"shared_challenges":14},{"model_a":"gpt-oss-120b","model_b":"mercury-2","name_a":"GPT OSS 120B","name_b":"Inception: Mercury 2","correlation":0.9674,"shared_challenges":21},{"model_a":"mercury-2","model_b":"solar-pro-3-free","name_a":"Inception: Mercury 2","name_b":"Solar Pro 3","correlation":0.9273,"shared_challenges":18}],"transition_rate":[{"model_a":"gpt-5.2","model_b":"gpt-5.2-chat","name_a":"GPT-5.2","name_b":"GPT-5.2 Chat","correlation":0.9951,"shared_challenges":15},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-flash-02-23","name_a":"Qwen: Qwen3.5 122B A10B","name_b":"Qwen: Qwen3.5 Flash","correlation":0.993,"shared_challenges":23},{"model_a":"claude-4.5-sonnet","model_b":"claude-opus-4.1","name_a":"Claude Sonnet 4.5","name_b":"Claude Opus 4.1","correlation":0.9902,"shared_challenges":13}],"filler_rate":[{"model_a":"mistral-large-2","model_b":"mistral-large-2512","name_a":"Mistral Large 2","name_b":"Mistral Large 3 2512","correlation":0.9532,"shared_challenges":10},{"model_a":"gemini-2.0-flash-thinking-exp","model_b":"gemma-3-27b-it","name_a":"Gemini 2.0 Flash Thinking","name_b":"Gemma 3 27B","correlation":0.889,"shared_challenges":13},{"model_a":"claude-4.5-sonnet","model_b":"claude-sonnet-4","name_a":"Claude Sonnet 4.5","name_b":"Claude Sonnet 4","correlation":0.8889,"shared_challenges":14}],"first_person_rate":[{"model_a":"gpt-oss-120b","model_b":"solar-pro-3-free","name_a":"GPT OSS 120B","name_b":"Solar Pro 3","correlation":0.9986,"shared_challenges":18},{"model_a":"devstral-medium","model_b":"devstral-small","name_a":"Mistral Devstral Medium","name_b":"Mistral Devstral Small 1.1","correlation":0.9956,"shared_challenges":21},{"model_a":"gpt-5-mini","model_b":"horizon-beta","name_a":"GPT-5 Mini","name_b":"Horizon Beta","correlation":0.9955,"shared_challenges":15}],"second_person_rate":[{"model_a":"llama-4-maverick","model_b":"llama-4-scout","name_a":"Llama 4 Maverick","name_b":"Llama 4 Scout","correlation":0.9773,"shared_challenges":10},{"model_a":"gemma-3n-e4b-it","model_b":"llama-4-maverick","name_a":"Gemma 3n 4B","name_b":"Llama 4 Maverick","correlation":0.9492,"shared_challenges":12},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-flash-02-23","name_a":"Qwen: Qwen3.5 122B A10B","name_b":"Qwen: Qwen3.5 Flash","correlation":0.9391,"shared_challenges":23}],"avg_paragraph_length":[{"model_a":"mistral-large-2","model_b":"mistral-large-2512","name_a":"Mistral Large 2","name_b":"Mistral Large 3 2512","correlation":0.9363,"shared_challenges":10},{"model_a":"claude-4.5-sonnet","model_b":"claude-sonnet-4","name_a":"Claude Sonnet 4.5","name_b":"Claude Sonnet 4","correlation":0.9331,"shared_challenges":14},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-35b-a3b","name_a":"Qwen: Qwen3.5 122B A10B","name_b":"Qwen: Qwen3.5 35B A3B","correlation":0.9302,"shared_challenges":23}]},"composite_clone_scores":[{"model_a":"mistral-large-2","model_b":"mistral-large-2512","name_a":"Mistral Large 2","name_b":"Mistral Large 3 2512","provider_a":"mistral","provider_b":"mistral","composite_score":0.8482,"signals":{"aggregate_similarity":0.8929,"h2h_avg":0.8956,"h2h_consistency":0.9399,"feature_correlation":0.7134,"length_correlation":0.793},"shared_challenges":10,"top_correlated_features":[{"feature":"inline_code_rate","r":1},{"feature":"exclamation_rate","r":0.9998},{"feature":"horizontal_rule_rate","r":0.9705}]},{"model_a":"qwen3.5-27b","model_b":"qwen3.5-35b-a3b","name_a":"Qwen: Qwen3.5 27B","name_b":"Qwen: Qwen3.5 35B A3B","provider_a":"qwen","provider_b":"qwen","composite_score":0.8413,"signals":{"aggregate_similarity":0.911,"h2h_avg":0.8297,"h2h_consistency":0.8905,"feature_correlation":0.7561,"length_correlation":0.8858},"shared_challenges":23,"top_correlated_features":[{"feature":"sentence_length_variance","r":0.9971},{"feature":"semicolon_rate","r":0.9762},{"feature":"transition_rate","r":0.9724}]},{"model_a":"aurora-alpha","model_b":"mercury-2","name_a":"Aurora Alpha","name_b":"Inception: Mercury 2","provider_a":"openrouter","provider_b":"inception","composite_score":0.8169,"signals":{"aggregate_similarity":0.8895,"h2h_avg":0.8025,"h2h_consistency":0.8855,"feature_correlation":0.6833,"length_correlation":0.9481},"shared_challenges":22,"top_correlated_features":[{"feature":"question_rate","r":0.9966},{"feature":"exclamation_rate","r":0.9642},{"feature":"type_token_ratio","r":0.9641}]},{"model_a":"qwen3.5-122b-a10b","model_b":"qwen3.5-9b","name_a":"Qwen: Qwen3.5 122B A10B","name_b":"Qwen3.5 9B","provider_a":"qwen","provider_b":"qwen","composite_score":0.7972,"signals":{"aggregate_similarity":0.8466,"h2h_avg":0.7586,"h2h_consistency":0.8399,"feature_correlation":0.7077,"length_correlation":0.9775},"shared_challenges":21,"top_correlated_features":[{"feature":"inline_code_rate","r":1},{"feature":"sentence_length_variance","r":0.9826},{"feature":"question_rate","r":0.9703}]},{"model_a":"mistral-medium-3.1","model_b":"mistral-small-creative","name_a":"Mistral Medium 3.1","name_b":"Mistral Small Creative","provider_a":"mistral","provider_b":"mistral","composite_score":0.7794,"signals":{"aggregate_similarity":0.9081,"h2h_avg":0.7481,"h2h_consistency":0.8018000000000001,"feature_correlation":0.6918,"length_correlation":0.8543},"shared_challenges":22,"top_correlated_features":[{"feature":"inline_code_rate","r":1},{"feature":"parenthetical_rate","r":0.9782},{"feature":"exclamation_rate","r":0.964}]},{"model_a":"mercury-2","model_b":"solar-pro-3-free","name_a":"Inception: Mercury 2","name_b":"Solar Pro 3","provider_a":"inception","provider_b":"upstage","composite_score":0.7764,"signals":{"aggregate_similarity":0.9261,"h2h_avg":0.7576,"h2h_consistency":0.8328,"feature_correlation":0.6753,"length_correlation":0.7477},"shared_challenges":18,"top_correlated_features":[{"feature":"ellipsis_rate","r":1},{"feature":"question_rate","r":0.9461},{"feature":"transition_rate","r":0.9428}]},{"model_a":"aurora-alpha","model_b":"solar-pro-3-free","name_a":"Aurora Alpha","name_b":"Solar Pro 3","provider_a":"openrouter","provider_b":"upstage","composite_score":0.7726,"signals":{"aggregate_similarity":0.907,"h2h_avg":0.7263,"h2h_consistency":0.8934,"feature_correlation":0.6384,"length_correlation":0.804},"shared_challenges":17,"top_correlated_features":[{"feature":"inline_code_rate","r":0.9692},{"feature":"ellipsis_rate","r":0.9654},{"feature":"exclamation_rate","r":0.9573}]},{"model_a":"gpt-oss-120b","model_b":"mercury-2","name_a":"GPT OSS 120B","name_b":"Inception: Mercury 2","provider_a":"openai","provider_b":"inception","composite_score":0.7658,"signals":{"aggregate_similarity":0.8682,"h2h_avg":0.7457,"h2h_consistency":0.8363,"feature_correlation":0.6316,"length_correlation":0.8666},"shared_challenges":21,"top_correlated_features":[{"feature":"transition_rate","r":0.9821},{"feature":"booster_rate","r":0.9674},{"feature":"question_rate","r":0.96}]},{"model_a":"gpt-5.2","model_b":"gpt-5.2-chat","name_a":"GPT-5.2","name_b":"GPT-5.2 Chat","provider_a":"openai","provider_b":"openai","composite_score":0.7613,"signals":{"aggregate_similarity":0.8516,"h2h_avg":0.7613,"h2h_consistency":0.876,"feature_correlation":0.6657,"length_correlation":0.635},"shared_challenges":15,"top_correlated_features":[{"feature":"exclamation_rate","r":1},{"feature":"transition_rate","r":0.9951},{"feature":"emoji_rate","r":0.9655}]},{"model_a":"horizon-alpha","model_b":"horizon-beta","name_a":"Horizon Alpha","name_b":"Horizon Beta","provider_a":"openrouter","provider_b":"openrouter","composite_score":0.7563,"signals":{"aggregate_similarity":0.868,"h2h_avg":0.7754,"h2h_consistency":0.8468,"feature_correlation":0.5017,"length_correlation":0.9866},"shared_challenges":14,"top_correlated_features":[{"feature":"first_person_rate","r":0.9862},{"feature":"transition_rate","r":0.9675},{"feature":"exclamation_rate","r":0.9404}]},{"model_a":"qwen3-coder","model_b":"qwen3-coder-plus","name_a":"Qwen3 Coder","name_b":"Qwen3 Coder Plus","provider_a":"qwen","provider_b":"qwen","composite_score":0.7537,"signals":{"aggregate_similarity":0.861,"h2h_avg":0.7273,"h2h_consistency":0.8164,"feature_correlation":0.6412,"length_correlation":0.8283},"shared_challenges":22,"top_correlated_features":[{"feature":"first_person_rate","r":0.973},{"feature":"question_rate","r":0.9575},{"feature":"avg_word_length","r":0.9291}]},{"model_a":"llama-4-maverick","model_b":"mistral-nemo","name_a":"Llama 4 Maverick","name_b":"Mistral Nemo","provider_a":"meta","provider_b":"mistral","composite_score":0.7533,"signals":{"aggregate_similarity":0.8637,"h2h_avg":0.7781,"h2h_consistency":0.8855999999999999,"feature_correlation":0.5061,"length_correlation":0.8663},"shared_challenges":10,"top_correlated_features":[{"feature":"exclamation_rate","r":1},{"feature":"question_rate","r":1},{"feature":"type_token_ratio","r":0.9129}]},{"model_a":"aurora-alpha","model_b":"gpt-oss-20b","name_a":"Aurora Alpha","name_b":"GPT OSS 20B","provider_a":"openrouter","provider_b":"openai","composite_score":0.7507,"signals":{"aggregate_similarity":0.8511,"h2h_avg":0.7174,"h2h_consistency":0.8394,"feature_correlation":0.581,"length_correlation":0.9467},"shared_challenges":19,"top_correlated_features":[{"feature":"inline_code_rate","r":1},{"feature":"question_rate","r":0.9891},{"feature":"first_person_rate","r":0.9622}]},{"model_a":"gpt-oss-120b","model_b":"solar-pro-3-free","name_a":"GPT OSS 120B","name_b":"Solar Pro 3","provider_a":"openai","provider_b":"upstage","composite_score":0.746,"signals":{"aggregate_similarity":0.8727,"h2h_avg":0.748,"h2h_consistency":0.8223,"feature_correlation":0.6503,"length_correlation":0.6362},"shared_challenges":18,"top_correlated_features":[{"feature":"first_person_rate","r":0.9986},{"feature":"question_rate","r":0.9835},{"feature":"avg_word_length","r":0.9535}]},{"model_a":"gemma-3n-e4b-it","model_b":"glm-4.5-air","name_a":"Gemma 3n 4B","name_b":"Z.AI: GLM 4.5 Air","provider_a":"google","provider_b":"zhipu","composite_score":0.7332,"signals":{"aggregate_similarity":0.8728,"h2h_avg":0.7456,"h2h_consistency":0.8631,"feature_correlation":0.5164,"length_correlation":0.7685},"shared_challenges":10,"top_correlated_features":[{"feature":"exclamation_rate","r":0.99},{"feature":"question_rate","r":0.9082},{"feature":"hedging_rate","r":0.8622}]},{"model_a":"qwen-plus-2025-07-28-thinking","model_b":"qwen3-30b-a3b-thinking-2507","name_a":"Qwen Plus 0728 (thinking)","name_b":"Qwen3 30B A3B Thinking 2507","provider_a":"qwen","provider_b":"qwen","composite_score":0.6241,"signals":{"aggregate_similarity":0.7851,"h2h_avg":0.7788,"h2h_consistency":0.8979,"feature_correlation":0,"length_correlation":0.9311},"shared_challenges":12,"top_correlated_features":[]},{"model_a":"qwen3.5-35b-a3b","model_b":"qwen3.5-flash-02-23","name_a":"Qwen: Qwen3.5 35B A3B","name_b":"Qwen: Qwen3.5 Flash","provider_a":"qwen","provider_b":"qwen","composite_score":0.622,"signals":{"aggregate_similarity":0.8322,"h2h_avg":0.7894,"h2h_consistency":0.8644000000000001,"feature_correlation":0,"length_correlation":0.8745},"shared_challenges":23,"top_correlated_features":[]},{"model_a":"grok-3","model_b":"grok-4","name_a":"Grok 3","name_b":"xAI: Grok 4","provider_a":"xai","provider_b":"xai","composite_score":0.6219,"signals":{"aggregate_similarity":0.778,"h2h_avg":0.8141,"h2h_consistency":0.8671,"feature_correlation":0,"length_correlation":0.8756},"shared_challenges":14,"top_correlated_features":[]},{"model_a":"deepseek-v3-03-24","model_b":"mistral-medium-3","name_a":"DeepSeek V3 (March 2024)","name_b":"Mistral Medium 3","provider_a":"deepseek","provider_b":"mistral","composite_score":0.6216,"signals":{"aggregate_similarity":0.8004,"h2h_avg":0.7703,"h2h_consistency":0.8987,"feature_correlation":0,"length_correlation":0.9069},"shared_challenges":13,"top_correlated_features":[]},{"model_a":"mistral-large","model_b":"mistral-large-2","name_a":"Mistral Large","name_b":"Mistral Large 2","provider_a":"mistral","provider_b":"mistral","composite_score":0.6103,"signals":{"aggregate_similarity":0.7742,"h2h_avg":0.8299,"h2h_consistency":0.9016,"feature_correlation":0,"length_correlation":0.6487},"shared_challenges":10,"top_correlated_features":[]},{"model_a":"claude-opus-4.1","model_b":"qwen3-coder-plus","name_a":"Claude Opus 4.1","name_b":"Qwen3 Coder Plus","provider_a":"anthropic","provider_b":"qwen","composite_score":0.6086,"signals":{"aggregate_similarity":0.7998,"h2h_avg":0.7818,"h2h_consistency":0.8141,"feature_correlation":0,"length_correlation":0.9123},"shared_challenges":15,"top_correlated_features":[]},{"model_a":"qwen3.5-27b","model_b":"qwen3.5-flash-02-23","name_a":"Qwen: Qwen3.5 27B","name_b":"Qwen: Qwen3.5 Flash","provider_a":"qwen","provider_b":"qwen","composite_score":0.6074,"signals":{"aggregate_similarity":0.8265,"h2h_avg":0.7739,"h2h_consistency":0.8364,"feature_correlation":0,"length_correlation":0.8394},"shared_challenges":23,"top_correlated_features":[]},{"model_a":"qwen3.5-9b","model_b":"qwen3.5-flash-02-23","name_a":"Qwen3.5 9B","name_b":"Qwen: Qwen3.5 Flash","provider_a":"qwen","provider_b":"qwen","composite_score":0.6061,"signals":{"aggregate_similarity":0.838,"h2h_avg":0.7516,"h2h_consistency":0.8455,"feature_correlation":0,"length_correlation":0.8581},"shared_challenges":21,"top_correlated_features":[]},{"model_a":"qwen3.5-35b-a3b","model_b":"qwen3.5-9b","name_a":"Qwen: Qwen3.5 35B A3B","name_b":"Qwen3.5 9B","provider_a":"qwen","provider_b":"qwen","composite_score":0.6056,"signals":{"aggregate_similarity":0.7872,"h2h_avg":0.7645,"h2h_consistency":0.8217,"feature_correlation":0,"length_correlation":0.9381},"shared_challenges":21,"top_correlated_features":[]},{"model_a":"qwen3.5-397b-a17b","model_b":"qwen3.5-flash-02-23","name_a":"Qwen: Qwen3.5 397B A17B","name_b":"Qwen: Qwen3.5 Flash","provider_a":"qwen","provider_b":"qwen","composite_score":0.5985,"signals":{"aggregate_similarity":0.8265,"h2h_avg":0.7579,"h2h_consistency":0.7976,"feature_correlation":0,"length_correlation":0.8761},"shared_challenges":23,"top_correlated_features":[]},{"model_a":"glm-4.7","model_b":"glm-5","name_a":"Z.AI: GLM 4.7","name_b":"Z.ai: GLM 5","provider_a":"openrouter","provider_b":"zhipu","composite_score":0.5982,"signals":{"aggregate_similarity":0.7818,"h2h_avg":0.7564,"h2h_consistency":0.8012,"feature_correlation":0,"length_correlation":0.938},"shared_challenges":20,"top_correlated_features":[]},{"model_a":"gpt-5.1-codex-max","model_b":"o4-mini","name_a":"GPT-5.1 Codex Max","name_b":"OpenAI o4-mini","provider_a":"openai","provider_b":"openai","composite_score":0.5918,"signals":{"aggregate_similarity":0.8093,"h2h_avg":0.7172,"h2h_consistency":0.8259,"feature_correlation":0,"length_correlation":0.9005},"shared_challenges":8,"top_correlated_features":[]},{"model_a":"aurora-alpha","model_b":"gpt-oss-120b","name_a":"Aurora Alpha","name_b":"GPT OSS 120B","provider_a":"openrouter","provider_b":"openai","composite_score":0.5916,"signals":{"aggregate_similarity":0.8213,"h2h_avg":0.7122,"h2h_consistency":0.868,"feature_correlation":0,"length_correlation":0.8116},"shared_challenges":20,"top_correlated_features":[]},{"model_a":"claude-opus-4.1","model_b":"qwen3-coder","name_a":"Claude Opus 4.1","name_b":"Qwen3 Coder","provider_a":"anthropic","provider_b":"qwen","composite_score":0.5905,"signals":{"aggregate_similarity":0.7793,"h2h_avg":0.7536,"h2h_consistency":0.8144,"feature_correlation":0,"length_correlation":0.8469},"shared_challenges":15,"top_correlated_features":[]},{"model_a":"devstral-small","model_b":"gemma-3n-e2b-it-free","name_a":"Mistral Devstral Small 1.1","name_b":"Google: Gemma 3n 2B","provider_a":"mistral","provider_b":"google","composite_score":0.5896,"signals":{"aggregate_similarity":0.7829,"h2h_avg":0.7225,"h2h_consistency":0.8653,"feature_correlation":0,"length_correlation":0.8239},"shared_challenges":14,"top_correlated_features":[]}]}