Skip to content

Benchmark

MMMLU

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

Models and systems measured
49
Scores recorded
163
Sources
2
IQ weight
2.48

Score distribution

79.8%
Mean
81.3%
Median
10.1%
Std dev
68.3%
10th percentile
89.6%
90th percentile
38.4%
Min
38.4%92.6%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.48 for chat models, measured over 45 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#Model or systemScore
101GPT OSS 20bofficial model card Table 2 · German · reasoning high · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.78.7%
102GPT OSS 120Bofficial model card Table 2 · German · reasoning low · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.78.6%
103GPT OSS 20bofficial model card Table 2 · French · reasoning medium · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.78.6%
104GPT-4.1 mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78.5%
105GPT OSS 120Bofficial model card Table 2 · Bengali · reasoning medium · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.78.3%
106GPT OSS 120Bofficial model card Table 2 · Indonesian · reasoning low · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.78.3%
107GPT OSS 20bofficial model card Table 2 · Chinese · reasoning medium · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.78%
108GPT OSS 120Bofficial model card Table 2 · Chinese · reasoning low · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.77.9%
109GPT OSS 20bofficial model card Table 2 · Korean · reasoning high · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.77.6%
110GPT OSS 20bofficial model card Table 2 · Indonesian · reasoning medium · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.77.4%
111GPT OSS 20bofficial model card Table 2 · German · reasoning medium · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.77.2%
112GPT OSS 20bofficial model card Table 2 · Bengali · reasoning high · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.77.1%
113GPT OSS 120Bofficial model card Table 2 · Japanese · reasoning low · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.77%
114GPT OSS 20bofficial model card Table 2 · Japanese · reasoning medium · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.76.9%
115Gemma 4 E4B-it· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim76.6%
116GPT OSS 20bofficial model card Table 2 · Hindi · reasoning medium · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.76.6%
117GPT OSS 20bofficial model card Table 2 · Arabic · reasoning high · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.76.3%
118Qwen3.5 4B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim76.1%
119GPT OSS 20bofficial model card Table 2 · Korean · reasoning medium · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.75.7%
120GPT OSS 20bofficial model card Table 3 · reasoning high · 14-language average · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.75.7%
121GPT OSS 120Bofficial model card Table 2 · Korean · reasoning low · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.75.2%
122GPT OSS 120Bofficial model card Table 2 · Arabic · reasoning low · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.75%
123GPT OSS 20bofficial model card Table 2 · Spanish · reasoning low · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.75%
124GPT OSS 20bofficial model card Table 2 · Bengali · reasoning medium · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.74.9%
125GPT OSS 120Bofficial model card Table 2 · Hindi · reasoning low · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.74.2%
126Mistral Large 3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim74.2%
127GPT OSS 120Bofficial model card Table 3 · reasoning low · 14-language average · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.74.1%
128GPT OSS 20bofficial model card Table 2 · Italian · reasoning low · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.73.6%
129GPT OSS 20bofficial model card Table 3 · reasoning medium · 14-language average · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.73.5%
130GPT OSS 20bofficial model card Table 2 · Arabic · reasoning medium · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.73.4%
131GPT OSS 20bofficial model card Table 2 · Portuguese · reasoning low · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.73.3%
132GPT OSS 20bofficial model card Table 2 · French · reasoning low · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.73.2%
133GPT OSS 120Bofficial model card Table 2 · Swahili · reasoning high · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.72.3%
134GPT OSS 20bofficial model card Table 2 · Chinese · reasoning low · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.72.1%
135GPT OSS 120Bofficial model card Table 2 · Bengali · reasoning low · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.71.5%
136GPT OSS 20bofficial model card Table 2 · German · reasoning low · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.71.4%
137GPT OSS 20bofficial model card Table 2 · Indonesian · reasoning low · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.71.2%
138GPT OSS 20bofficial model card Table 2 · Japanese · reasoning low · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.70.4%
139GPT OSS 20bofficial model card Table 2 · Hindi · reasoning low · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.70.2%
140phi-3.5-moe-instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim69.9%
141GPT OSS 20bofficial model card Table 2 · Korean · reasoning low · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.69.8%
142GPT OSS 120Bofficial model card Table 2 · Swahili · reasoning medium · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.69.3%
143GPT OSS 20bofficial model card Table 2 · Bengali · reasoning low · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.68.3%
144Gemma 4 E2B-it· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim67.4%
145GPT OSS 20bofficial model card Table 3 · reasoning low · 14-language average · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.67%
146GPT-4.1 nano· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim66.9%
147GPT OSS 20bofficial model card Table 2 · Arabic · reasoning low · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.65.6%
148Qwen3.5 2B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim63.1%
149GPT OSS 120Bofficial model card Table 2 · Yoruba · reasoning high · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.62.4%
150GPT OSS 20bofficial model card Table 2 · Swahili · reasoning high · translated-answer parser· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.60.7%

Showing 101–150 of 159 results.

Not ranked

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
Qwen3.5-397B-A17B-BaseQwen3.5 release/model card · base-model table· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.85.8%
Qwen3.7-Plus-BaseQwen3.8-Flash-Next release/model card · base-model table· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.84.5%
Qwen3.8-27B-BaseQwen3.8-Flash-Next release/model card · base-model table· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.79.7%
Qwen3.8-Flash-Next-BaseQwen3.8-Flash-Next release/model card · base-model table· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.84.9%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats