SWE-rebench
Evaluates LLM coding agents on real-world GitHub issues sourced after each model's training cutoff, preventing benchmark contamination. Uses standardized ReAct scaffolding with 128K token context; each model is run five times per problem and the best Pass@1 resolved rate is reported.
Models ranked
14
tracked on this benchmark
Score band
79.8 – 41.6
best → lowest tracked
Snapshot trend
+21.96
May 28 → Jun 7 · 1 models
Leaderboard
Tracked models ranked by Resolved Rate (higher is better).
How to read this benchmark
This benchmark scores models where higher is better. Use scores for directional filtering and shortlisting, not universal quality ranking; then validate pricing, context window, provider availability, and fit for your workload.
Trust this score when
- There is a fresh timestamped snapshot (or multiple snapshots) for this benchmark.
- The model list covers the same version family you can actually deploy today.
- Top candidates overlap with your required routing and feature requirements.
Be cautious when
- There is only one benchmark snapshot or the dataset appears stale.
- The benchmark metric direction is opposite of your decision objective.
- The score difference between options is narrow and likely within implementation variance.
Related benchmarks
Last reviewed: May 28, 2026