Formal Theorem Proving on Putnam 2025
100Overall Success RateLEAP
Evaluation results
| Method | Links | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LEAPRollout count=rollout=22026.06 | 100 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| AristotleRollout count=rollout=22026.06 | 75 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HilbertRollout count=rollout=22026.06 | 33.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Gemini-3.1-proPass setting=pass@1282026.06 | 0 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Goedel-Prover-V2-32BPass setting=pass@1282026.06 | 0 | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Goedel-ArchitectNatural language guidance (+NL)=true2026.06 | — | — | — | — | — | — | — | — | — | — | — | — | — | 11 | |
| Numina-Lean-Agent2026.06 | — | — | — | — | — | — | — | — | — | — | — | — | — | 12 | |
| Seed-Prover 1.52026.06 | — | — | — | — | — | — | — | — | — | — | — | — | — | 11 |