Metamath
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Mathematical Reasoning | MetaMath Insufficient | Success Rate (SR)72.5 | 19 | |
| Mathematical Reasoning | MetaMath 1k | Token Count212 | 14 | |
| Automated Theorem Proving | Metamath (val) | Performance56.5 | 6 | |
| Formal Theorem Proving | Metamath set.mm (val) | Performance Score29.22 | 3 | |
| Theorem Proving | Metamath (test) | Pass@865.6 | 2 |
Showing 5 of 5 rows