Auto-updated
AI Coding Leaderboard
Rankings by benchmark. Scores sourced from official provider release posts and updated automatically.
Real-world GitHub issues resolved autonomously. The best proxy for agentic coding ability.
| # | Model | SWE-bench Verified |
|---|---|---|
| 🥇 | Gemini 2.5 Pro | 63.2% |
| 🥈 | Claude Sonnet 4.6 | ~49% |
| 🥉 | o1 | 48.9% |
No SWE-bench Verified data yet
Scores sourced from official provider release posts. Tilde (~) prefix indicates approximate figures. Rankings update automatically when new benchmark results are published. Data last updated 2026-05-01. View full model specs →