MMMLU
MMMLU - Multilingual MMLU benchmark evaluating knowledge across multiple languages.
Category
Multilingual
Max Score
—
Score Type
percent
Active
Yes
Model Scores
Scores for MMMLU
| Model | Score | Date | Verified |
|---|---|---|---|
| Qwen3.5-4B |
37.99%
|
01.02.2026 | Verified |
| Qwen3.5-122B-A10B |
84.28%
|
01.02.2026 | Verified |
| Qwen3.5-27B |
80.79%
|
01.02.2026 | Unverified |
| Qwen3.5-35B-A3B |
77.73%
|
01.02.2026 | Unverified |
| Qwen3-235B-A22B |
69.87%
|
01.02.2026 | Unverified |
| GPT-5-mini 2025-08-07 |
82.10%
|
01.02.2026 | Unverified |
| Gemma4-31B-it |
91.70%
|
02.07.2026 | Verified |
| Gemma4-26B-A4B |
82.53%
|
02.07.2026 | Verified |
| Gemma4-12B |
69.87%
|
02.07.2026 | Verified |
| Gemma4-E4B |
40.17%
|
02.07.2026 | Verified |
| Gemma4-E2B |
67.40
|
02.07.2026 | Verified |
| Gemma3-27B |
14.41%
|
02.07.2026 | Unverified |
| GPT-OSS-120B |
60.70%
|
08.08.2025 | Verified |
| OpenAI o3-mini |
58.08%
|
05.08.2025 | Verified |
| OpenAI o4-mini |
77.73%
|
05.08.2025 | Verified |
| OpenAI o3 |
93.45%
|
05.08.2025 | Verified |
| GPT-OSS-20B |
36.24%
|
05.08.2025 | Verified |
| DeepSeek-V3.2 |
89.52%
|
26.06.2026 | Verified |
| DeepSeek-V4-Flash |
93.45%
|
26.06.2026 | Verified |
| DeepSeek-V4-Pro |
100.00%
|
26.06.2026 | Verified |