Claude 3.7 Sonnet vs GPT-5.1-Codex-Mini
Compare Claude 3.7 Sonnet by Anthropic against GPT-5.1-Codex-Mini by OpenAI, context windows of 200K vs 400K, tested across 55 shared challenges. Updated May 2026.
Which is better, Claude 3.7 Sonnet or GPT-5.1-Codex-Mini?
Claude 3.7 Sonnet and GPT-5.1-Codex-Mini are both competitive models. Claude 3.7 Sonnet costs $3/M input tokens vs $1.5/M for GPT-5.1-Codex-Mini. Context windows: 200K vs 400K tokens. Compare their real outputs side by side below.
Key Differences Between Claude 3.7 Sonnet and GPT-5.1-Codex-Mini
Claude 3.7 Sonnet is made by anthropic while GPT-5.1-Codex-Mini is from openai. Claude 3.7 Sonnet has a 200K token context window compared to GPT-5.1-Codex-Mini's 400K. On pricing, Claude 3.7 Sonnet costs $3/M input tokens vs $1.5/M for GPT-5.1-Codex-Mini.
Per 1M tokens
GPT-5.1-Codex-Mini is cheaper on both — 2.0× input, 2.5× output
No community votes yet. On paper, GPT-5.1-Codex-Mini has the edge — bigger model tier, newer, bigger context window.
Style Comparison
Claude 3.7 Sonnet uses 23.0x more headings
