| Benchmark | Model | Rank | Results |
|---|---|---|---|
| automated-theorem-proving-on-minif2f-test | DSP (540B Minerva informal) | #8 | cumulative: 38.9Pass@100: 38.9ITP: Isabelle |
| automated-theorem-proving-on-minif2f-test | Sledgehammer + heuristics | #17 | cumulative: 20.9Pass@1: 20.9ITP: Isabelle |
| automated-theorem-proving-on-minif2f-valid | DSP (62B Minerva informal) | #6 | Pass@100: 43.9 |