Mathematical Reasoning on DASD-10K
79.4AIME24 ScoreOPSD-PMI
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| OPSD-PMIModel=Qwen3-8B2026.07 | 79.4 | 71.9 | 46.7 | 66 | |
| OPSD-PMIModel=Qwen3-4B2026.07 | 76.3 | 68.3 | 46.4 | 63.7 | |
| BaseModel=Qwen3-8B2026.07 | 75.8 | 65.6 | 43.9 | 61.8 | |
| OPSD-StandardModel=Qwen3-8B2026.07 | 75.4 | 65.2 | 42.2 | 60.9 | |
| BaseModel=Qwen3-4B2026.07 | 74.9 | 66.4 | 42.2 | 61.2 | |
| OPSD-PMIModel=OLMo-7B2026.07 | 74.7 | 68.9 | 46.1 | 63.2 | |
| OPSD-StandardModel=Qwen3-4B2026.07 | 74.2 | 65.2 | 42.2 | 60.5 | |
| BaseModel=OLMo-7B2026.07 | 71.9 | 66.7 | 45.2 | 61.3 | |
| OPSD-StandardModel=OLMo-7B2026.07 | 68.1 | 66.4 | 45 | 59.8 | |
| OPSD-PMIModel=R1-Distill-7B2026.07 | 54 | 43.1 | 25.3 | 40.8 | |
| BaseModel=R1-Distill-7B2026.07 | 52 | 39.6 | 24.4 | 38.7 | |
| OPSD-StandardModel=R1-Distill-7B2026.07 | 51.9 | 39.2 | 24.4 | 38.5 |