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.
- Made by
- Alibaba AIDC-AI (Parrot authors)
- Released
- June 2024
- Kind
- Knowledge in many languages
- Level
- School
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Last in a launch post
- August 2026
- Last model added
- August 2026
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%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | LFM2.5-VL-3B | 83% | Aug 2026 | Lab model card | |
| 2 | North Micro Vision Instruct | 72.8% | Aug 2026 | Lab model card |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Labs’ model cards
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 |
|---|---|---|---|
| Aug 12, 2026 | LFM2.5-VL-3B | 83 | MMMB |
| Aug 12, 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 |
|---|---|---|---|---|
| Nov 6, 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 | |
| Aug 25, 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. Nemotron 3 Ultra 550B-A55B Base 90.1%
- 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.
Gemma 3 27B 74.7%