Mathematical Reasoning on SMQA
76.74AccuracySFT+RL
Evaluation results
| Method | Links | |
|---|---|---|
| SFT+RLType=Thinking, Instant Response=×2026.05 | 76.74 | |
| InterRSType=Interleaved, Instant Response=√2026.05 | 74.43 | |
| SFTType=Interleaved, Instant Response=√2026.05 | 73.01 | |
| Zero-shotType=Thinking, Instant Response=×2026.05 | 70.11 | |
| Zero-shotType=Fast CoT, Instant Response=√2026.05 | 69.4 | |
| Mini_ORType=Interleaved, Instant Response=√2026.05 | 69.01 | |
| SFT+RLType=Fast CoT, Instant Response=√2026.05 | 53.19 | |
| Zero-shotType=Direct, Instant Response=√2026.05 | 42.15 |