SWE-bench Verified
About
500 human-validated GitHub issue resolution tasks from SWE-bench, created with OpenAI in August 2024. The standard evaluation for agentic coding systems. Top performers (2026) exceed 78% resolved.
How to read this benchmark
This benchmark uses a scoring system where higher is better. Scores are useful for directional filtering and model shortlisting, not for universal quality ranking.
Interpretation checklist: prefer benchmarks that are closest to your workload style, then validate against the linked model pages for pricing, context window, and provider availability.
Trust when:
- There is a fresh timestamped snapshot (or multiple snapshots) for this benchmark.
- Model list covers the same version family you can actually deploy today.
- Top candidates overlap with your required routing and feature requirements.
Don't trust when:
- There is only one benchmark snapshot or the dataset appears stale.
- Benchmark metric direction is opposite of your decision objective.
- The score difference between options is narrow and likely within implementation variance.
Current modeled score band for tracked entries is roughly 93.9 – 80.9.
Window
May 1 to May 21
last 3 snapshots
Mean delta
-13.10
score points
Coverage
1
models in latest snapshot
Leaderboard preview (top 5)
- 1. Claude Mythos Preview93.9
- 2. Claude Opus 4.787.6
- 3. GPT-5.3-Codex85.0
- 4. GPT-5.582.6
- 5. Claude Opus 4.580.9