Held-out capability suite
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| General Language Understanding | Held-out capability suite (test) | AIME-2024 Accuracy62.9 | 16 |
Showing 1 of 1 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| General Language Understanding | Held-out capability suite (test) | AIME-2024 Accuracy62.9 | 16 |