MMMB
Models answer multiple-choice questions about images in six languages across 15 categories. The set has about 12,000 questions.
VLMEvalKit runs it as MMMB. The same repo adds a multilingual MMBench that VLMEvalKit names MTL_MMBench_DEV.
- Level
- School Students, from grade school to high school
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Multiple choice
LFM2.5-VL-3B leads with 83%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
- 1 LFM2.5-VL-3B 83%
- 2
North Micro Vision Instruct 72.8%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | LFM2.5-VL-3B | 83% | Aug 2026 | Model card | |
| 2 | North Micro Vision Instruct | 72.8% | Aug 2026 | Model card |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
2 labs put it in a launch post in the last six months
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| 12 Aug 2026 | LFM2.5-VL-3B | 83 | MMMB |
| 12 Aug 2026 | North Micro Vision Instruct | 72.8 | MMMB |
2 system cards report it, from 2 labs
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 6 Nov 2025 |  Nemotron Nano 12B v2 VL technical report | MMMB per language, reasoning off: en 86.1, zh 84.1, pt 83.5, ar 83.4, tr 77.4, ru 83.9, no overall score (Table 5) | Capabilities | |
| 25 Aug 2025 |  InternVL3.5-241B-A28B technical report | MMMB en 87.6, zh 86.4, pt 85.3, ar 84.2, tr 85.1, ru 86.0, no overall score (Table 8). Multilingual MMBench en 88.9, zh 87.7, pt 87.0, ar 86.5, tr 86.7, ru 87.6 | Capabilities |
More in Multilingual
- MMMLU In use MMLU professionally translated into 14 languages. Multiple-choice accuracy. Claude Mythos Preview 92.7%
- WMT24++ In use English-to-55-language translation of WMT24 test data. Scored with automatic metrics such as MetricX or xCOMET.
K-EXAONE 90.5% - MMLU-ProX In use MMLU-Pro translated into up to 29 languages with expert review. Multiple-choice accuracy per language.
Qwen3.7-Max 87% - CLIcK In use Models answer 1,995 multiple-choice questions on Korean language and culture. Questions come from official Korean exams and textbooks in eleven categories.
Solar Open 2 90.7% - Global MMLU Lite 3.0 In use Models answer 400 human-translated MMLU questions per language in 23 languages. Version 3.0 adds Czech, Hungarian, Oriya, Slovak and Tajik and updates Italian. Accuracy.
Inkling 88.7% - Alyah In use Models answer 1,173 four-option questions written by native Emirati speakers on greetings, idioms, figurative language, heritage and poetry in Emirati Arabic dialect.
Falcon-Emirati-7B 84.8%