Coding Agent on Aggregated (RebenchT, CodeCI, Bird)
34.99Overall Average ScoreTDScaling
Evaluation Results
| Method | Links | |
|---|---|---|
| TDScalingCategory=Proposed Implementation2026.02 | 34.99 | |
| Qwen3-Coder-30B-A3B-InstructCategory=Baseline2026.02 | 30.99 | |
| TOUCANCategory=Tool-Learning Method2026.02 | 29.82 | |
| APIGen-MTCategory=Tool-Learning Method2026.02 | 27.48 | |
| SimiaCategory=Tool-Learning Method2026.02 | 22.81 |