FormalML
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Theorem Proving | FormalML Hard Level-3 | Solved Rate95 | 6 | |
| Formal Theorem Proving | FormalML Hard | Proof Length11.2 | 6 | |
| Automated Theorem Proving | FormalML-Hard (Machine Learning Theory) 1.0 (test) | Output Tokens (k)0.4 | 6 |
Showing 3 of 3 rows