ARC, HellaSwag, MMLU, TruthfulQA, WinoGrande
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Few-shot Language Evaluation | ARC, HellaSwag, MMLU, TruthfulQA, WinoGrande Few-shot Llama2-7B | ARC Accuracy56.06 | 6 | |
| Language Modeling Evaluation | ARC, HellaSwag, MMLU, TruthfulQA, WinoGrande | ARC Accuracy34.64 | 4 |
Showing 2 of 2 rows