Software Engineering on SWE-rebench January 2026 (test)
52.9Resolved RateClaude Opus 4.6
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Claude Opus 4.62026.02 | 52.9 | 1.06 | 70.8 | |
| GPT-5.2config=xhigh2026.02 | 51.7 | 1.21 | 58.3 | |
| Claude Sonnet 4.52026.02 | 47.1 | 1.69 | 60.4 | |
| Gemini 3 Pro2026.02 | 46.7 | 2.04 | 58.3 | |
| Claude Opus 4.52026.02 | 43.8 | 0.93 | 58.3 | |
| GLM-52026.02 | 42.1 | 1.21 | 50 | |
| GLM-4.72026.02 | 41.3 | 2.12 | 56.3 | |
| Kimi K2.52026.02 | 37.9 | 1.21 | 50 |