Tool Using on Live P-Mul
70.83AccuracyToolRL
Evaluation Results
| Method | Links | |
|---|---|---|
| ToolRLModel Category=Base and Expert Models2026.06 | 70.83 | |
| RESMERGEModel Category=Merged Models2026.06 | 70.83 | |
| Qwen2.5-7B-InstructModel Category=Base and Expert Models2026.06 | 66.67 | |
| MemoryAgentModel Category=Base and Expert Models2026.06 | 66.67 | |
| TAModel Category=Merged Models2026.06 | 66.67 | |
| TIESModel Category=Merged Models2026.06 | 66.67 | |
| DARE + TIESModel Category=Merged Models2026.06 | 66.67 | |
| TSV-MergeModel Category=Merged Models2026.06 | 66.67 | |
| ISO-CModel Category=Merged Models2026.06 | 66.67 | |
| ISO-CTSModel Category=Merged Models2026.06 | 66.67 | |
| RAMModel Category=Merged Models2026.06 | 66.67 | |
| General-ReasonerGroup=Qwen3-4B-Base, Category=Base and Expert Models2026.06 | 58.33 | |
| AMPOModel Category=Base and Expert Models2026.06 | 50 | |
| TAGroup=Qwen3-4B-Base, Category=Merged Models2026.06 | 37.5 | |
| RESMERGEGroup=Qwen3-4B-Base, Category=Merged Models2026.06 | 37.5 | |
| TSV-MergeGroup=Qwen3-4B-Base, Category=Merged Models2026.06 | 33.33 | |
| GRPOGroup=Qwen3-4B-Base, Category=Base and Expert Models2026.06 | 29.17 | |
| Qwen3-4BGroup=Qwen3-4B-Base, Category=Base and Expert Models2026.06 | 25 | |
| RAMGroup=Qwen3-4B-Base, Category=Merged Models2026.06 | 20.83 | |
| TIESGroup=Qwen3-4B-Base, Category=Merged Models2026.06 | 16.67 | |
| SpiralGroup=Qwen3-4B-Base, Category=Base and Expert Models2026.06 | 12.5 | |
| DARE + TIESGroup=Qwen3-4B-Base, Category=Merged Models2026.06 | 0 |