Mathematical Reasoning on HMMT 2025 (val)
38.3AccuracyiS@1
Evaluation Results
| Method | Links | |
|---|---|---|
| iS@1Sample size (N)=32, Max length=16,000 tokens, Top-k=12026.06 | 38.3 | |
| Self-CertaintySample size (N)=32, Max length=16,000 tokens, Selection variant=best over each dataset2026.06 | 35 | |
| Self-ConsistencySample size (N)=32, Max length=16,000 tokens2026.06 | 30.8 | |
| DeepConfSample size (N)=32, Max length=16,000 tokens, Selection variant=best over each dataset2026.06 | 30.7 |