Mathematical and Quantitative Reasoning on Mathematic and Quantitative (test)
51AccuracyMSFT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MSFTSize=Average, Evaluation Protocol=5-shot greedy decoding2026.03 | 51 | 4.12 | |
| SFTSize=Average, Evaluation Protocol=5-shot greedy decoding2026.03 | 48 | 3.88 | |
| IESSize=Average, Evaluation Protocol=5-shot greedy decoding2026.03 | 48 | 3.88 | |
| DynamixSFTSize=Average, Evaluation Protocol=5-shot greedy decoding2026.03 | 47.9 | 4.04 | |
| Continual SFTSize=Average, Evaluation Protocol=5-shot greedy decoding2026.03 | 47.8 | 1.71 | |
| BaseSize=Average, Evaluation Protocol=5-shot greedy decoding2026.03 | 47.6 | — |