Automated Theorem Proving On Minif2F 1
評価指標
Pass@64
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | Pass@64 | Paper Title | Repository |
|---|---|---|---|
| Evariste | 32.1 | HyperTree Proof Search for Neural Theorem Proving | - |
| Evariste-1d | 33.6 | HyperTree Proof Search for Neural Theorem Proving | - |
| GPT-f | 30.6 | HyperTree Proof Search for Neural Theorem Proving | - |
| Evariste-7d | 42.5 | HyperTree Proof Search for Neural Theorem Proving | - |
0 of 4 row(s) selected.