language benchmark
Base version of the Massive Multitask Language Understanding benchmark, evaluating language models across 57 tasks including elementary mathematics, US history, computer science, law, and other professional and academic subjects. Designed to comprehensively measure the breadth and depth of a model's academic and professional understanding.
Updated Aug 11, 2026
Higher score ranks better on this benchmark.
| 01 | AC | 68.0% | 100.0% | 1 | C |
The leading models and scores on this benchmark.
What MMLU-Base measures and how its scores work.
Base version of the Massive Multitask Language Understanding benchmark, evaluating language models across 57 tasks including elementary mathematics, US history, computer science, law, and other professional and academic subjects. Designed to comprehensively measure the breadth and depth of a model's academic and professional understanding.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
Common questions about MMLU-Base.
Qwen2.5-Coder 7B Instruct is currently ranked first with 68.0%.
Base version of the Massive Multitask Language Understanding benchmark, evaluating language models across 57 tasks including elementary mathematics, US history, computer science, law, and other professional and academic subjects. Designed to comprehensively measure the breadth and depth of a model's academic and professional understanding.
Yes. Higher values rank better for this benchmark.
1 model results are currently shown.
No. This benchmark is shown for reference but does not contribute to the overall score.