Software Engineering Issue Resolution on SWE-bench 500 (test)
72.2Resolution Scoreagyn
Evaluation Results
| Method | Links | |
|---|---|---|
| agynModel=GPT-5 / GPT-5-codex, Reasoning Level=medium reasoning2026.02 | 72.2 | |
| OpenHandsModel=GPT-52026.02 | 71.8 | |
| mini-SWE-agentModel=GPT-5.2, Reasoning Level=high reasoning2026.02 | 71.8 | |
| mini-SWE-agentModel=GPT-5, Reasoning Level=medium reasoning2026.02 | 65 |