nine-benchmark suite
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Zero-shot Language Understanding and Reasoning | nine-benchmark suite (MMLU, ARC, CSQA, HellaSwag, OpenBookQA, PIQA, SocialIQA, WinoGrande) (test val) | MMLU Accuracy31.7 | 6 |
Showing 1 of 1 rows