GENAIWIKI

Anthropic

AnthropicVision-2024

multimodal · Release Mar 30, 2024 · License n/a

A multimodal model integrating text and image inputs for enhanced comprehension and response generation.

multimodalvision
Updated today

Modalities

What goes in and what comes out.

Inputs

text, image

Outputs

text, image

Capabilities

image captioning, text/image interaction, visual question answering

Benchmarks snapshot

Structured JSON for reproducible comparisons.

{}

Related on GenAIWiki

Same provider, tooling that cites the model, or prompts tuned for it.