Mathematical Reasoning on GSM8K VeRA-E (Avg@5)
94.85Accuracy (Avg@5, Seeds)Frontier Models (Mean)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Frontier Models (Mean)Model count=16, Seeds count=1319, Verified variants count=26382026.01 | 94.85 | 95.2 |
Loading the SOTA2 catalog…