m-WildVision
Aya Vision 32B 72% Vision-language models answer WildVision bench prompts machine-translated into 23 languages. A model judge compares two models' answers and reports win rates.
Built from the English WildVision vision_bench_0617 test set with Google Translate. It is a translated copy, but labs report it as its own multilingual test.
- Made by
- Cohere For AI (Cohere Labs)
- Released
- March 2025
- Kind
- General visual questions
- Level
- Everyday
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- All public
- Last in a launch post
- March 2025, dropped before it saturated
- Last model added
- May 2025
Aya Vision 32B leads with 72%
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.
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Aya Vision 32B | 72% | Mar 2025 | 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
No launch post has listed it since March 2025
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 |
|---|---|---|---|
| Mar 4, 2025 | Aya Vision 32B | 72 | Up to 72% win rate on m-WildVision (best pairwise win rate) |
One system card reports it
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 |
|---|---|---|---|---|
| May 13, 2025 | Aya Vision 32B technical report | m-WildVision, pairwise win rates averaged over 23 languages, no overall: vs Llama-3.2-90B-Vision 73.0, vs Molmo-72B 68.8, vs Qwen-2.5-VL-72B 53.3 (Figure 7, printed labels) | Capabilities |
More in Vision
- MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy. GPT-5.1 85.4%
- MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
- CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
- MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy.
Qwen 3.8 Max 97.7% - MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy. Qwen 3.8 Max 85.9%
- ChartQA In use Models answer human-written and generated questions about chart images that need visual and arithmetic reasoning. Scored by relaxed accuracy with a 5 percent numeric tolerance. Command A Vision 90.9%