MATH and GSM8k
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Step-level error discrimination | MATH and GSM8k (test) | AUROC (Step-level Error Discrimination)0.762 | 4 |
Showing 1 of 1 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Step-level error discrimination | MATH and GSM8k (test) | AUROC (Step-level Error Discrimination)0.762 | 4 |