MMLU Pro COT

MMLU Pro COT is a benchmark for broad factual and academic knowledge. The official description says: "MMLU-Pro with chain-of-thought reasoning". Below we describe in simple words what benchmarks of this type generally examine.

MMLU Pro COT measures broad factual and academic knowledge. In detail, it checks:

• facts and concepts from many academic fields at once
• harder variants with several plausible answer options
• knowledge that goes beyond the model's training-set surface forms
• resisting the plausible-but-wrong answers deliberately included

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.

Official methodology note: MMLU-Pro with chain-of-thought reasoning. 5-shot.

What is the MMLU Pro COT benchmark?

MMLU Pro COT is a benchmark for broad factual and academic knowledge. The official description says: 'MMLU-Pro with chain-of-thought reasoning'. Below we describe in simple words what benchmarks of this type generally examine.

What does MMLU Pro COT test?

MMLU Pro COT mainly measures broad factual and academic knowledge. Concretely, it checks: facts and concepts from many academic fields at once; harder variants with several plausible answer options; knowledge that goes beyond the model's training-set surface forms.

How is the MMLU Pro COT score calculated?

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better. The declared maximum score of this benchmark is 100.0.

Where do I get MMLU Pro COT data and scores?

The official source is https://arxiv.org/abs/2009.03300. The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/mmlu-pro-cot/scores) or pull it directly from the Open LLM Radar API with any HTTP client.