For Developers/Leaderboard
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.

#ModelSWE-bench Verified
🥇Claude Fable 595.0%
🥈Claude Opus 4.888.6%
🥉Claude Opus 4.787.6%
#4Claude Sonnet 5~85.2%
#5GPT-5.582.6%
#6DeepSeek V480.6%
#7Claude Sonnet 4.679.6%
#8GPT-574.9%
#9Claude Haiku 4.573.3%

Scores sourced from official provider release posts. Tilde (~) prefix indicates approximate figures. Rankings update automatically when new benchmark results are published. Data last updated 2026-07-08. View full model specs →