Formal Theorem Proving on MathOlympiadBench (MoBench)
34.44AccuracyGOEDEL VALUE
Evaluation Results
| Method | Links | |
|---|---|---|
| GOEDEL VALUESampling Budget=64, Search Strategy=Value-guided tree search2026.03 | 34.44 | |
| GOEDEL RANDOMSampling Budget=64, Search Strategy=Random search2026.03 | 30.28 | |
| GOEDEL-V2Sampling Budget=642026.03 | 14.72 | |
| GOEDEL DIRECTSampling Budget=64, Supervision Strategy=direct synthesis2026.03 | 12.5 | |
| KIMINA RANDOMSampling Budget=64, Search Strategy=Random search2026.03 | 8.61 | |
| KIMINA VALUESampling Budget=64, Search Strategy=Value-guided tree search2026.03 | 8.61 | |
| KIMINASampling Budget=642026.03 | 7.78 | |
| KIMINA DIRECTSampling Budget=64, Supervision Strategy=direct synthesis2026.03 | 7.78 |