MMLUPro
Benchmark website →MMLU-Pro is a harder variant of MMLU with 10-choice questions (vs 4), more reasoning-intensive problems, and reduced noise.
About this test
- What it measures
- Broad knowledge and reasoning with harder, more discriminative questions than standard MMLU.
- How it was administered
- Multiple-choice with 10 options; 12K questions across 14 domains; accuracy metric; chain-of-thought encouraged.
Model rankings
Models ranked by score on this benchmark. Higher is better.
| Rank | Model | Provider | Score | Percentile | Tags |
|---|