MMLU Dataset
by UC Berkeley · open-source · Last verified 2026-03-17
Massive Multitask Language Understanding (MMLU) is a benchmark covering 57 academic subjects from STEM to humanities, with 14,000+ multiple-choice questions at undergraduate and professional level. It has become the de facto standard for measuring broad world knowledge and academic reasoning in LLMs.
https://huggingface.co/datasets/cais/mmlu ↗A
A—Great
Adoption: A+Quality: A+Freshness: B+Citations: A+Engagement: F
Specifications
- License
- MIT
- Pricing
- open-source
- Capabilities
- knowledge-evaluation, benchmark, multiple-choice-qa
- Integrations
- huggingface-datasets, lm-eval-harness
- Use Cases
- model-evaluation, benchmarking, knowledge-testing
- API Available
- No
- Tags
- benchmark, multiple-choice, knowledge, 57-subjects, academic
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
80.9Adoption
96
Quality
90
Freshness
75
Citations
98
Engagement
0
Put AI to work for your business
Deploy this dataset alongside autonomous AaaS agents that handle tasks end-to-end — no babysitting required.