ProofNet
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Autoformalization | ProofNet | Compilation Pass Rate@1094.1 | 28 | |
| Formal Theorem Proving | ProofNet | Accuracy24.26 | 26 | |
| Step-level correctness assessment | ProofNet (test) | PR-AUC32.9 | 22 | |
| Step-level reasoning verification | ProofNet | PR-AUC68.2 | 19 | |
| Theorem Proving | ProofNet (test) | Pass@3247.3 | 15 | |
| Auto-formalization | ProofNet (test) | Pass@897.9 | 13 | |
| Autoformalization | ProofNet (test) | πFV44.09 | 12 | |
| Formal Theorem Proving | ProofNet (test) | Pass@144.62 | 12 | |
| Mathematical Reasoning | ProofNet | Accuracy97.2 | 11 | |
| Statement generation | ProofNet N = 186 (test) | CH@10098.4 | 11 | |
| Theorem Proving | ProofNet (val) | Accuracy25.4 | 11 | |
| Lean theorem proving | PROOFNET (186 problems) | Pass@824.73 | 9 | |
| Theorem Proving | ProofNet (all) | Accuracy25.3 | 7 | |
| Mathematical Reasoning | ProofNet (test) | Accuracy95.6 | 6 | |
| Formal Theorem Proving | ProofNet (val) | Pass Rate9.04 | 6 | |
| Formal Reasoning | ProofNet | ASR90.7 | 4 | |
| Autoformalization and Proving | ProofNet N=186 (test) | Pass@640.7849 | 4 | |
| Mathematical Reasoning | ProofNet | PPL27.9 | 3 | |
| Theorem Autoformalization | ProofNet | Objects3.67 | 1 |
Showing 19 of 19 rows