ARC, MMLU, HellaSwag, TruthfulQA, and WinoGrande
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
ARC (25-shot), MMLU (5-shot), HellaSwag (10-shot), TruthfulQA (0-shot), and WinoGrande (0-shot) (test)
53.24ARC Accuracy
32
Loading the SOTA2 catalog…