Theorem QA
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Scientific and General Reasoning | Theorem QA | Pass@155.75 | 18 | |
| Scientific Reasoning | Theorem QA | Pass@160.6 | 9 | |
| Question Answering | Theorem QA | Score31.1 | 5 | |
| English | Theorem QA | Score44.4 | 5 | |
| Scientific Reasoning | Theorem QA | Scientific Reasoning QA Accuracy66.4 | 3 | |
| Question Answering | Theorem QA v1 (test) | Accuracy25.3 | 3 |
Showing 6 of 6 rows