Patch Performance - Combined Measurable Subset: leaderboard
Resolution on a pre-filtered measurable subset: 230 SWE-bench and 109 SWE-bench-Live tasks, mini-SWE-agent, 250 steps, trajectories August 17–18 2026. This is the full 339-task selection before the later solved-patch runtime analysis; it is not either benchmark’s full leaderboard. Percentages are computed from the printed resolved counts and their explicit denominators.
Metric: Resolved (%). Source: arxiv.org. Saturation forecast: Around January 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5 | 87.32 | #12 |
| 2 | Qwen 3.8 Max | 83.19 | #31 |
| 3 | GPT-5.6 Sol | 82.01 | #18 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=patch-performance-combined-measurable-subset · How It Works · Data refreshed daily, snapshot 2026-10-16.