Mathematical Reasoning on FIMO
18.03ScoreDeepInsightTheorem
Evaluation Results
| Method | Links | |
|---|---|---|
| DeepInsightTheoremStages=3-stage2026.04 | 18.03 | |
| DS-Prover-v1.5-RL-7B2026.04 | 17.39 | |
| Qwen2.5-Math-Inst-7B2026.04 | 17.01 | |
| DeepInsightTheoremStages=2-stage2026.04 | 16.33 | |
| DS-Prover-v2-7B2026.04 | 16.25 | |
| Qwen2.5-Inst-7B2026.04 | 15.29 |