Introducing ConTextual: How well can your Multimodal model jointly reason over text and image in text-rich scenes?
What changed
Introducing ConTextual: How well can your Multimodal model jointly reason over text and image in text-rich scenes? We refer to these tasks as "context-sensitive text-rich visual reasoning tasks". We also released a leaderboard, so that the community can see for themselves which models are the best at this task.
Why it matters
A concrete addition to Practical AI: Tools, Models & Frameworks: it changes what's available to builders today rather than being general commentary.
How it compares
Related prior coverage to compare against:
- Introducing SynthID Text
- Benchmarking Text Generation Inference
- GPT-4