language benchmark
MMLU Chat
Chat-format variant 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. This version uses conversational prompting format for model evaluation.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
MMLU Chat Ranking
Higher score ranks better on this benchmark.
| 1 | NV | 80.6% | 100.0% | 1 | C |
MMLU Chat Highlights
The leading models and scores on this benchmark.
What is MMLU Chat?
What MMLU Chat measures and how its scores work.
Chat-format variant 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. This version uses conversational prompting format for model evaluation.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MMLU Chat
- Modality
- text
- Primary category
- language
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mmlu-chat|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MMLU Chat.
Which model scores highest on MMLU Chat?
Llama 3.1 Nemotron 70B Instruct is currently ranked first with 80.6%.
What does MMLU Chat measure?
Chat-format variant 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. This version uses conversational prompting format for model evaluation.
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.