Skip to content
Rival
ModelsCompareBest ForArenaPricing
Sign Up
Sign Up

We compare AI models for a living. On purpose. We chose this.

@rival_tips

Explore

  • Compare Models
  • All Models
  • Find Your Model
  • Image Generation
  • Audio Comparison
  • Leaderboard
  • Pricing
  • Challenges

Discover

  • Insights
  • Research
  • AI Creators
  • AI Tools
  • The Graveyard

Developers

  • Developer Hub
  • MCP Server
  • Rival Datasets

Connect

  • Methodology
  • Sponsor a Model
  • Advertise
  • Partnerships
  • Privacy Policy
  • Terms
  • RSS Feed
© 2026 Rival · Built at hours no one should be awake, on hardware we don't own
Rival
ModelsCompareBest ForArenaPricing
Sign Up
Sign Up

AI Leaderboard 2026 | Every Model Ranked by Community Votes

  1. Home
  2. Leaderboard

We compare AI models for a living. On purpose. We chose this.

@rival_tips

Explore

  • Compare Models
  • All Models
  • Find Your Model
  • Image Generation
  • Audio Comparison
  • Leaderboard
  • Pricing
  • Challenges

Discover

  • Insights
  • Research
  • AI Creators
  • AI Tools
  • The Graveyard

Developers

  • Developer Hub
  • MCP Server
  • Rival Datasets

Connect

  • Methodology
  • Sponsor a Model
  • Advertise
  • Partnerships
  • Privacy Policy
  • Terms
  • RSS Feed
© 2026 Rival · Built at hours no one should be awake, on hardware we don't own
Community Curated

The Arena

Reputations built and destroyed by strangers. Daily.

22,079 opinions registered
200 models in the ring
Powered by real humans (we think)
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview
google1 fan
69.375% wins
Z.AI: GLM 4.5 Air
Z.AI: GLM 4.5 Air
zhipu
70.476% wins
Z.AI: GLM 4.6
Z.AI: GLM 4.6
zhipu
67.570% wins
Jump to

Overall

200 models · All models ranked by community votes

#ModelFansWin RateScoreWin%DuelsTrend
1Z.AI: GLM 4.5 AirZ.AI: GLM 4.5 Air
—
70.475.7% ±4415
—
2Gemini 3.1 Pro PreviewGemini 3.1 Pro Preview
—
69.375.2% ±5311
—
3Z.AI: GLM 4.6Z.AI: GLM 4.6
—
67.569.9% ±4624
—
4Z.AI: GLM 4.7Z.AI: GLM 4.7
—
67.473.5% ±5249
—
5Gemini 3 Pro PreviewGemini 3 Pro Preview
+9
66.666.7% ±3964
—
6Claude Opus 4Claude Opus 4
—
64.263.7% ±3868
▲+3
7Z Image TurboZ Image Turbo
—
64.267.5% ±5342
▲+4
8Z.AI: GLM 4.5Z.AI: GLM 4.5
—
64.167.3% ±5349
—
9Claude 3.7 Thinking SonnetClaude 3.7 Thinking Sonnet
—
64.164.4% ±4713
▲+1
10Gemini 3 Flash PreviewGemini 3 Flash Preview
+2
63.972.7% ±988
▼-3

Website & Frontend

4 models · HTML, CSS, interactive web design

#ModelFansWin RateScoreWin%DuelsTrend
1Optimus AlphaOptimus Alpha
—
57.761.7% ±8149
▼-1
2DeepSeek V3 (March 2024)DeepSeek V3 (March 2024)
—
53.754.8% ±7197
▼-4
3Quasar AlphaQuasar Alpha
—
40.137.4% ±8123
—
4o1o1
—
38.637.3% ±1175
▼-2

Code Generation

149 models · Programming, algorithms, debugging

#ModelFansWin RateScoreWin%DuelsTrend
1Gemini 3.1 Pro PreviewGemini 3.1 Pro Preview
—
69.375.2% ±5311
—
2Z.AI: GLM 4.6Z.AI: GLM 4.6
—
67.569.9% ±4624
—
3Z.AI: GLM 4.7Z.AI: GLM 4.7
—
67.473.5% ±5249
—
4Gemini 3 Pro PreviewGemini 3 Pro Preview
+9
66.666.7% ±3964
—
5Claude Opus 4Claude Opus 4
—
64.263.7% ±3868
▲+3
6Z.AI: GLM 4.5Z.AI: GLM 4.5
—
64.167.3% ±5349
—
7Gemini 3 Flash PreviewGemini 3 Flash Preview
+2
63.972.7% ±988
▼-3
8Claude Opus 4.6Claude Opus 4.6
+18
62.160.4% ±3941
▲+1
9Claude Opus 4.1Claude Opus 4.1
—
62.062.7% ±4533
▲+2
10Qwen3 CoderQwen3 Coder
—
61.760.5% ±3804
▲+1

Reasoning

151 models · Logic, analysis, complex problem solving

#ModelFansWin RateScoreWin%DuelsTrend
1Z.AI: GLM 4.5 AirZ.AI: GLM 4.5 Air
—
70.475.7% ±4415
—
2Gemini 3.1 Pro PreviewGemini 3.1 Pro Preview
—
69.375.2% ±5311
—
3Z.AI: GLM 4.6Z.AI: GLM 4.6
—
67.569.9% ±4624
—
4Z.AI: GLM 4.7Z.AI: GLM 4.7
—
67.473.5% ±5249
—
5Gemini 3 Pro PreviewGemini 3 Pro Preview
+9
66.666.7% ±3964
—
6Claude Opus 4Claude Opus 4
—
64.263.7% ±3868
▲+3
7Z.AI: GLM 4.5Z.AI: GLM 4.5
—
64.167.3% ±5349
—
8Claude 3.7 Thinking SonnetClaude 3.7 Thinking Sonnet
—
64.164.4% ±4713
▲+1
9Gemini 3 Flash PreviewGemini 3 Flash Preview
+2
63.972.7% ±988
▼-3
10Claude Opus 4.6Claude Opus 4.6
+18
62.160.4% ±3941
▲+1

Creative Writing

161 models · Stories, dialogue, creative text generation

#ModelFansWin RateScoreWin%DuelsTrend
1Z.AI: GLM 4.5 AirZ.AI: GLM 4.5 Air
—
70.475.7% ±4415
—
2Gemini 3.1 Pro PreviewGemini 3.1 Pro Preview
—
69.375.2% ±5311
—
3Z.AI: GLM 4.6Z.AI: GLM 4.6
—
67.569.9% ±4624
—
4Z.AI: GLM 4.7Z.AI: GLM 4.7
—
67.473.5% ±5249
—
5Gemini 3 Pro PreviewGemini 3 Pro Preview
+9
66.666.7% ±3964
—
6Claude Opus 4Claude Opus 4
—
64.263.7% ±3868
▲+3
7Z.AI: GLM 4.5Z.AI: GLM 4.5
—
64.167.3% ±5349
—
8Claude 3.7 Thinking SonnetClaude 3.7 Thinking Sonnet
—
64.164.4% ±4713
▲+1
9Gemini 3 Flash PreviewGemini 3 Flash Preview
+2
63.972.7% ±988
▼-3
10Claude Opus 4.6Claude Opus 4.6
+18
62.160.4% ±3941
▲+1

Including Qwen3 30B A3B Thinking 2507, DeepSeek V3 (March 2024), Lyria 3, Horizon Alpha, and 156 more →

See the full rankings

160+ ranked models below. Free account, no card.

Free account. No card required. By continuing, you agree to Rival's Terms and Privacy Policy

Head-to-Head
Z.AI: GLM 4.5 Air
vs
Gemini 3.1 Pro Preview
Z.AI: GLM 4.5 Air
vs
Z.AI: GLM 4.6
Gemini 3.1 Pro Preview
vs
Z.AI: GLM 4.6
Allegiance

Where do your loyalties lie?

Pledge to your model. Rep your faction. Shape the leaderboard.

Keep going

COMPARE

Pick Your Own Matchup

Choose any two models and see their outputs side by side

PRICING

Free Models Beating Paid Ones

$0 models outranking $60/M token ones in the Arena