Tool Using on Non-Live P-Mul
87.5AccuracyISO-C
Evaluation Results
| Method | Links | |
|---|---|---|
| ISO-CModel Category=Merged Models2026.06 | 87.5 | |
| ISO-CTSModel Category=Merged Models2026.06 | 87.5 | |
| DARE + TIESModel Category=Merged Models2026.06 | 87 | |
| TAModel Category=Merged Models2026.06 | 86.5 | |
| TSV-MergeModel Category=Merged Models2026.06 | 86.5 | |
| RESMERGEModel Category=Merged Models2026.06 | 86.5 | |
| TIESModel Category=Merged Models2026.06 | 86 | |
| RAMModel Category=Merged Models2026.06 | 86 | |
| MemoryAgentModel Category=Base and Expert Models2026.06 | 85 | |
| ToolRLModel Category=Base and Expert Models2026.06 | 85 | |
| AMPOModel Category=Base and Expert Models2026.06 | 84 | |
| Qwen2.5-7B-InstructModel Category=Base and Expert Models2026.06 | 82.5 | |
| General-ReasonerGroup=Qwen3-4B-Base, Category=Base and Expert Models2026.06 | 81.5 | |
| TAGroup=Qwen3-4B-Base, Category=Merged Models2026.06 | 75.5 | |
| RESMERGEGroup=Qwen3-4B-Base, Category=Merged Models2026.06 | 72.5 | |
| GRPOGroup=Qwen3-4B-Base, Category=Base and Expert Models2026.06 | 72 | |
| SpiralGroup=Qwen3-4B-Base, Category=Base and Expert Models2026.06 | 71.5 | |
| TSV-MergeGroup=Qwen3-4B-Base, Category=Merged Models2026.06 | 71.5 | |
| RAMGroup=Qwen3-4B-Base, Category=Merged Models2026.06 | 61.5 | |
| TIESGroup=Qwen3-4B-Base, Category=Merged Models2026.06 | 55.5 | |
| Qwen3-4BGroup=Qwen3-4B-Base, Category=Base and Expert Models2026.06 | 28 | |
| DARE + TIESGroup=Qwen3-4B-Base, Category=Merged Models2026.06 | 27.5 |