Fuyu-Heavy
Fuyu-Heavy has model metadata, but missing tracked provider pricing keeps it from being a default production pick.
Use it for
- Teams evaluating general LLM work
Do not use it for
- Cost-sensitive launches that need sourced token pricing
- Vision or document-understanding workloads
- Strict JSON or tool-calling flows
- Family
- Fuyu
- Released
- 2024-01-24
- Architecture
- Decoder Only
- Specialization
- general
- Training
- finetuned
About
Adept's Fuyu-Heavy is a leading multimodal AI model designed as a digital agent. It ranks as the world's third most capable multimodal model, following GPT-4V and Gemini Ultra. Despite being smaller by a factor of 10-20 compared to these models, Fuyu-Heavy excels in multimodal reasoning, particularly in understanding user interfaces (UIs), and outperforms Gemini Pro on the MMMU benchmark. It delivers robust performance on text-based benchmarks, matching or surpassing models within its compute class. Developed to handle both text and image data, it powers Adept's enterprise product and supports complex calculations and long-form conversations.
Fuyu-Heavy is a model in the Fuyu family. No headline benchmark score is tracked for Fuyu-Heavy yet.
Top use-case fit
No primary decision-task fit is mapped for this model yet.
Provider price ladder
No tracked provider token pricing is available for this model yet.
Capabilities
No model capability flags are currently sourced.
Benchmark peer barsfor Coding
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.