Mathematical Reasoning on Putnam
43.34ScoreDeepInsightTheorem
Evaluation Results
| Method | Links | |
|---|---|---|
| DeepInsightTheoremStages=2-stage2026.04 | 43.34 | |
| Qwen2.5-Inst-7B2026.04 | 42.39 | |
| DS-Prover-v1.5-RL-7B2026.04 | 42 | |
| DeepInsightTheoremStages=3-stage2026.04 | 41.67 | |
| DS-Prover-v2-7B2026.04 | 41.5 | |
| Qwen2.5-Math-Inst-7B2026.04 | 41.06 |