| Benchmark | Model | Rank | Results |
|---|---|---|---|
| code-generation-on-swe-bench-multilingual | Dockerless-RL-9B (OpenHands) | – | Accuracy: 50.0 |
| code-generation-on-swe-bench-pro | Dockerless-RL-9B | – | Resolved: 35.2 |
| code-generation-on-swe-bench-verified | Dockerless-RL-9B (OpenHands) | – | Accuracy: 62.0 |