SWE-Bench Pro

Can the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better.

Claude Fable 5.1 by Anthropic holds the best SWE-Bench Pro result among tracked models, at 81.2% (released Sep 1 2026). Higher scores are better on this benchmark.

1. Claude Fable 5.1 (Anthropic) — 81.2%; 2. Claude Fable 5 (Anthropic) — 80.3%; 3. Claude Opus 5 (Anthropic) — 79.2%; 4. Claude Opus 4.8 (Anthropic) — 69.2%; 5. Qwen3.8-Max (Qwen) — 67.7%.

23 tracked models have a published SWE-Bench Pro score. Scores are collected from published lab reports and benchmark sources, with recorded sources credited alongside the results. We do not re-run the evaluations.

Qwen3.8-Flash-Next by Qwen is the highest-ranked model with downloadable weights on SWE-Bench Pro, scoring 62.5% at rank 9 overall.