Skip to content

Benchmark

Global-MMLU-Lite

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

Models measured
12
Scores recorded
12
Sources
1
IQ weight
1.02

Score distribution

73.7%
Mean
78.2%
Median
16.2%
Std dev
54.5%
10th percentile
88.7%
90th percentile
34.2%
Min
34.2%89.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.02 for chat models, measured over 12 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Gemini 2.5 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89.2%
2Inkling FP4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim88.7%
3Gemini 2.5 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim88.4%
4Inkling Small· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim86.7%
5Gemini 2.5 Flash-Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim81.1%
6Gemini 2.0 Flash Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78.2%
7Gemma 3 27B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim75.1%
8Gemma 3 12B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim69.5%
9Gemma 3n E4B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim64.5%
10Gemma 3n E2b It· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim59%
11Gemma 3 4B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim54.5%
12Gemma 3 1b it· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim34.2%

Data credits: Data by LLM Stats