← Back to models

Aya Vision

Cohere Labs (Canada) March 4 2025

Parameters

8B and 32B (2 sizes; dense)

License

Research License

Key Features

State-of-the-art multimodal research model (text + image); excels across multiple languages and modalities; outperforms leading open-weight models on language, text, and image benchmarks; supports 23 languages; introduces AyaVisionBench evaluation suite; research use only.

Paper / Source

https://arxiv.org/abs/2505.08751