Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Multilingual benchmark
Every model the catalog carries a published MMLU-ProX value for, ranked by that value.
A multilingual extension of professional-level academic evaluation across many languages. 17 models in the ModelScale catalog have a published value.
Each point is a model with a published MMLU-ProX value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
17 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 | Alibaba | 87 | |
| 2 | Anthropic | 85.7 | |
| 3 | Alibaba | 85.4 |
What the benchmark measures and how its value is published, from the source’s own record.
MMLU-ProX is a multilingual benchmark published by MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation. A multilingual extension of professional-level academic evaluation across many languages. Its evaluation set is described by the source as multilingual professional QA. The source rates its difficulty as professional multilingual.
Each model's result is published by MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation as multilingual multiple choice. ModelScale prints that value exactly as published, and never converts or rescales it. This page ranks the 17 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
| 4 | Alibaba | 84.7 |
| 4 | Alibaba | 84.7 |
| 6 | Z.AI | 83.1 |
| 7 | NVIDIA | 83 |
| 8 | Moonshot AI | 82.3 |
| 9 | Alibaba | 82.2 |
| 9 | Alibaba | 82.2 |
| 11 | Alibaba | 81 |
| 11 | Alibaba | 81 |
| 13 | Alibaba | 79.4 |
| 14 | OpenAI | 72.7 |
| 15 | DeepSeek | 70.5 |
| 16 | OpenAI | 61.1 |
| 17 | Microsoft | 49.9 |
Evidence key: ObservedLast good
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.