Combibench
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Formal Theorem Proving | Combibench | Solve Rate48 | 15 | |
| Theorem Proving | CombiBench | Proof Length8 | 13 | |
| Theorem Proving | CombiBench Combinatorics | Solved Problems27 | 13 | |
| Auto-formalization | CombiBench | Pass@897 | 13 | |
| Statement generation | CombiBench N = 100 | CH@1001 | 11 | |
| Theorem Proving | CombiBench | pass@3216 | 8 | |
| Automated Theorem Proving | CombiBench Easy Mode | Solved Problems (Pass@32)10 | 4 | |
| Autoformalization and Proving | CombiBench (N=100) | Pass@6496 | 4 | |
| Automated Theorem Proving | CombiBench Hard Mode | Total Solved (Pass@32)10 | 3 |
Showing 9 of 9 rows