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
Artificial Analysis Global-MMLU-Lite. Every model the catalog carries a published AA Global-MMLU-Lite value for, ranked by that value.
Global MMLU Lite is a multilingual version of MMLU with 400 questions per language, half culturally sensitive and half culturally agnostic. This page holds two independent runs: Artificial Analysis's, in the main table, and Kaggle's. 17 models in the ModelChoice catalog have a published value.
Each point is a model with a published AA Global-MMLU-Lite 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 AA Global-MMLU-Lite 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 | Accuracy |
|---|---|---|---|
| 1 | 93.2 | ||
| 2 | 92.7 | ||
| 3 | Anthropic | 92.2 |
What the benchmark measures and how its value is published, from the source’s own record.
AA Global-MMLU-Lite (Artificial Analysis Global-MMLU-Lite) is a multilingual benchmark published by Artificial Analysis Global-MMLU-Lite Benchmark Leaderboard. Global MMLU Lite is a multilingual version of MMLU with 400 questions per language, half culturally sensitive and half culturally agnostic. This page holds two independent runs: Artificial Analysis's, in the main table, and Kaggle's. Its evaluation set is described by the source as multilingual knowledge questions. The source rates its difficulty as multilingual professional knowledge.
Each model's result is published by Artificial Analysis Global-MMLU-Lite Benchmark Leaderboard as accuracy. ModelChoice prints that value to 1 decimal place, 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.
| 3 | 92.2 |
| 5 | Anthropic | 91.3 |
| 6 | OpenAI | 90.7 |
| 6 | OpenAI | 90.7 |
| 8 | OpenAI | 90.6 |
| 9 | 90.3 |
| 10 | Alibaba | 90.0 |
| 11 | xAI | 89.5 |
| 12 | OpenAI | 89.4 |
| 13 | Alibaba | 89.1 |
| 14 | Alibaba | 86.8 |
| 15 | Alibaba | 86.4 |
| 16 | DeepSeek | 86.0 |
| 17 | OpenAI | 82.8 |
Evidence key: ObservedLast good
Rows are ordered by the value Artificial Analysis Global-MMLU-Lite Benchmark Leaderboard 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.