language benchmark
MMLU-Base
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
Models1
Model coverage1
MetricScore
EvidenceB
MMLU-Base Ranking
Higher score ranks better on this benchmark.
| 1 | AC | 68.0% | 100.0% | 1 | C |
MMLU-Base Highlights
The leading models and scores on this benchmark.
What is MMLU-Base?
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.
- Family
- MMLU-Base
- Modality
- text
- Primary category
- language
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mmlu-base|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MMLU-Base.
Which model scores highest on MMLU-Base?
Qwen2.5-Coder 7B Instruct is currently ranked first with 68.0%.
What does MMLU-Base measure?
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.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.