Multilingual benchmark
MMLU-ProX leaderboard
Every model the catalog carries a published MMLU-ProX value for, ranked by that value.
CategoryMultilingual
MeasureMultilingual multiple choice
TasksMultilingual professional QA
DifficultyProfessional multilingual
A multilingual extension of professional-level academic evaluation across many languages.
MMLU-ProX ranking
12 models with a published MMLU-ProX value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Multilingual multiple choice |
|---|---|---|---|
| 1 |  Qwen3.7 Max | Alibaba | 87 |
| 2 |  Claude Opus 4.5 | Anthropic | 85.7 |
| 3 | Qwen3.7 Plus | Alibaba | 85.4 |
| 4 | Qwen3.5 397B | Alibaba | 84.7 |
| 4 | Qwen3.6 Plus | Alibaba | 84.7 |
| 6 |  GLM-5 | Z.AI | 83.1 |
| 7 |  Nemotron 3 Ultra | NVIDIA | 83 |
| 8 |  Kimi K2.5 | Moonshot AI | 82.3 |
| 9 | Qwen3.5-122B-A10B | Alibaba | 82.2 |
| 9 | Qwen3.5-27B | Alibaba | 82.2 |
| 11 | Qwen3.5-35B-A3B | Alibaba | 81 |
| 12 | Qwen3 235B 2507 | Alibaba | 79.4 |
Evidence key: Observed
Rows are ordered by the value MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.