Aya Vision 32B
Aya Vision 32B.
14
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Cohere Mar 2025 Aya Vision 32B
Open weights Mid-size
No Epoch Capabilities Index score yet
- MTVQA-Test 23.5% #6 /6
- IFEval 78.5% #101 /126
- MMMU 45.1% #104 /136
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MGSM | 79.5% | #32 of 52 | Model card | |
| Flores | 37.8 | #6 of 8 | Model card | |
| IFEval | 78.5% | #101 of 126 | Model card | |
| Global MMLU Lite | 63.6% | #14 of 16 | Model card | |
| CVQA | 74.1% | #1 of 1 | Model card | |
| Kaleidoscope | 41.7% | #1 of 1 | Model card |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMMU | 45.1% | #104 of 136 | Official leaderboard | |
| Vision Arena | 1,000 | #128 of 136 | Official leaderboard | |
| MTVQA-Test | 23.5% | #6 of 6 | Model card | |
| AyaVisionBench | 64% | #1 of 1 | Model card | |
| m-WildVision | 72% | #1 of 1 | Model card | |
| MaXM | 62.3% | #1 of 1 | Model card | |
| xChatBench | 70.1 | #1 of 1 | Model card | |
| xMMMU | 45.1% | #1 of 1 | Model card |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.
Its system card
Every result in the longer documents the lab published with it. 11 of them aren't in the launch post.
Capabilities
- MaXM 62.3
- xMMMU 45.1
- CVQA 74.1
- MTVQA-Test 23.5
- Kaleidoscope 41.7
- xChatBench 70.1
- AyaVisionBench
- m-WildVision
- m-ArenaHard
- Global MMLU Lite 63.6
- MGSM 79.5
- Flores 37.8
- IFEval 78.5