Back to Benchmarks
🌐
MMLU-ProX
MMLU-Pro Extended
29 typologically diverse languages MMLU-Pro
🌐 Multilingual
Best: 88.5%
2 Models Evaluated
Champion
Qwen 3.5
Alibaba
88.5%
Best Score
Model Rankings
All models ranked by score on MMLU-ProX. Scores are relative to the best score of 88.5%.
| # | Model | Provider | Score | vs Best |
|---|---|---|---|---|
| 1 | Qwen 3.5 Elo 1450 | Alibaba | 88.5% | Best |
| 2 | Claude Opus 4.6 Elo 1503 | Anthropic | 82% | -6.5% |
Score Distribution
Qwen 3.5
88.5%
Claude Opus 4.6
82%
Run This Benchmark
Learn how to evaluate your own models on MMLU-ProX.
MMLU-ProX is a standardized benchmark for evaluating AI model capabilities.
To run this benchmark on your own models, visit the official benchmark page or leaderboard for detailed instructions, code, and evaluation scripts.
Data compiled from official model cards, public leaderboards, and independent evaluations.