Compare Claude 3.7 Thinking Sonnet by Anthropic against GPT-5.1 Codex Max by OpenAI, tested across 53 shared challenges.
No community votes yet. On paper, GPT-5.1 Codex Max has the edge — bigger model tier, newer.
Claude 3.7 Thinking Sonnet uses 14.6x more headings
Compare Claude 3.7 Thinking Sonnet by Anthropic against GPT-5.1 Codex Max by OpenAI, tested across 53 shared challenges.
No community votes yet. On paper, GPT-5.1 Codex Max has the edge — bigger model tier, newer.
Claude 3.7 Thinking Sonnet uses 14.6x more headings