Coding Agent on RebenchT
33.13OH-p@1TDScaling
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| TDScalingCategory=Proposed Implementation2026.02 | 33.13 | 23.56 | |
| Qwen3-Coder-30B-A3B-InstructCategory=Baseline2026.02 | 31.21 | 15.84 | |
| TOUCANCategory=Tool-Learning Method2026.02 | 28.75 | 19.94 | |
| APIGen-MTCategory=Tool-Learning Method2026.02 | 27.66 | 17.22 | |
| SimiaCategory=Tool-Learning Method2026.02 | 21.39 | 7.83 |