Evaluation & BenchmarksDan Hendrycks et al.
Hendrycks et al. release MMLU (57 tasks)
Released MMLU (57 tasks)
Why it matters
Became the de facto standard for measuring the breadth of knowledge of pretrained models, and an essential metric in model announcements for the next 5 years
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2009.03300Added in Week 35, 2026 · See that week