Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Science Q&A and Previous Task Suite

Benchmarks

Task NameDataset NameSOTA ResultTrend
Skill LearningScience Q&A and Previous Task Suite (Hellaswag, Humaneval, IFeval, MMLU, TruthfulQA, Winogrande)
ScienceQA70.2
5
Showing 1 of 1 rows