Mathematical Proofs on miniF2F-valid

Metric: Pass@8 (higher is better)

LeaderboardDataset
Loading chart...
#ModelPass@8Extra DataPaperDateCode
1Lean GPT-f29.3YesMiniF2F: a cross-system benchmark for formal Oly...2021-08-31Code
2Metamath GPT-f2NoMiniF2F: a cross-system benchmark for formal Oly...2021-08-31Code