Skip to content

Benchmark

Global-MMLU

Multilingual benchmarks compare model performance across languages. Scores are percentages. Higher is better.

Models measured
7
Scores recorded
7
Sources
1
IQ weight
1.31

Score distribution

81.3%
Mean
87.8%
Median
15.5%
Std dev
60.3%
10th percentile
94.3%
90th percentile
55.1%
Min
55.1%96%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.31 for chat models, measured over 7 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Claude Fable 5.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim96%
2Claude Opus 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim94.3%
3Claude Sonnet 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim92.1%
4Claude Haiku 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim87.8%
5MiMo V2.5 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim83.6%
6Gemma 3n E4B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim60.3%
7Gemma 3n E2b It· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim55.1%

Data credits: Data by LLM Stats