Reasoning on GPQA-D (Score)
30.13GPQA-D ScoreAMPO
Evaluation Results
| Method | Links | |
|---|---|---|
| AMPOModel Category=Base and Expert Models2026.06 | 30.13 | |
| RESMERGEModel Category=Merged Models2026.06 | 27.61 | |
| TAModel Category=Merged Models2026.06 | 26.26 | |
| TIESModel Category=Merged Models2026.06 | 25.08 | |
| ISO-CTSModel Category=Merged Models2026.06 | 24.75 | |
| TSV-MergeModel Category=Merged Models2026.06 | 24.58 | |
| ToolRLModel Category=Base and Expert Models2026.06 | 23.91 | |
| RAMModel Category=Merged Models2026.06 | 23.74 | |
| ISO-CModel Category=Merged Models2026.06 | 23.57 | |
| DARE + TIESModel Category=Merged Models2026.06 | 23.4 | |
| Qwen2.5-7B-InstructModel Category=Base and Expert Models2026.06 | 23.23 | |
| MemoryAgentModel Category=Base and Expert Models2026.06 | 17.67 |