Claw-SWE-Bench (OpenClaw): leaderboard
Claw-SWE-Bench (2026) compares general-purpose agent harnesses (claws) on SWE-bench-style issue resolution: 350 multilingual GitHub issues run under a fixed prompt, time budget, patch extraction and evaluator. This board is Pass@1 in percent with the OpenClaw harness; higher is better.
Metric: Pass@1 (%) on the 350 GitHub issue-resolution instances of Claw-SWE-Bench (8 languages, 43 repositories, from SWE-bench-Multilingual and SWE-bench-Verified-Mini after future-commit cleanup); full adapter, identical prompt, 60-minute per-instance budget, one run, SWE-bench evaluator; OpenClaw harness. Source: arxiv.org. Saturation forecast: Around February 2027. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 78 | #49 |
| 2 | Claude Opus 4.7 | 77.1 | #79 |
| 3 | GLM-5.1 | 73.4 | #179 |
| 4 | DeepSeek V4 Pro | 71.7 | #188 |
| 5 | DeepSeek V4 Flash | 70.3 | #258 |
| 6 | Kimi K2.6 | 66.9 | #178 |
| 7 | Qwen 3.6 Flash | 66 | #424 |
| 8 | MiniMax-M2.7 | 61.4 | #518 |
| 9 | Seed 2.0 Mini | 48.6 | #508 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=claw-swe-bench-openclaw · How It Works · Data refreshed daily, snapshot 2026-11-13.