AdeptAILabs has introduced Fuyu-Heavy, a new multimodal model that ranks as the world's third-most-capable, trailing only behind GPT4-V and Gemini Ultra, which are significantly larger in size, being 10-20 times bigger. Despite its smaller size, Fuyu-Heavy outperforms the Gemini Pro in benchmarks, excelling in both the MMLU, a text-only benchmark, and the MMMU, which includes image and text. Designed specifically for digital agents, Fuyu-Heavy is noted for its scalability, effectiveness as an AI agent on computers, and also features cute mascots.
new (heavy!) model drop from @AdeptAILabs: fuyu-heavy is a new multimodal model designed specifically for digital agents. it’s the world’s third-most-capable multimodal model, behind only GPT4-V and Gemini Ultra, which are 10-20 times bigger. https://t.co/DTOnffCIVC
Adept presents Fuyu-Heavy A new multimodal model designed specifically for digital agents. This is the world’s 3rd-most-capable multimodal model, behind only GPT4-V and Gemini Ultra, which are 10-20 times larger. https://t.co/sl3z4sTpIz
New from @AdeptAILabs: Introducing Fuyu-Heavy, a multimodal model designed specifically for digital agents. Fuyu-Heavy is the 3rd most capable multimodal model, behind the much larger GPT4-V & Gemini Ultra. Features & sample model interactions 👇 https://t.co/HVUshCqo61
Adept's Fuyu architecture scales really well! Fuyu-Heavy is the best model in its weight class and outperforms Gemini Pro :) In particular, it's super good at being an AI agent on your computer... https://t.co/FElPtV4a7p
Adept presents Fuyu-Heavy blog: https://t.co/WmxunL0YeF a new multimodal model designed specifically for digital agents. world’s third-most-capable multimodal model, behind only GPT4-V and Gemini Ultra, which are 10-20 times larger. In particular, it outperforms Gemini Pro at… https://t.co/PPkgKgmuuW
Introducing our new multimodal model Adept FUYU-HEAVY!! Beats Gemini Pro on both MMLU (text-only benchmark) and MMMU (image+text benchmark) Plus cute mascots! https://t.co/2DbeEknPhz https://t.co/bYwWGEAnj4
LETS GO! Adept has been doing great multi modal things, and this is not a small claim! World's THIRD LMM? 👏 https://t.co/Fd34B1c5p2
Introducing Fuyu-Heavy, our new multimodal model. Fuyu-Heavy is the world’s third-most-capable multimodal model, behind only GPT4-V and Gemini Ultra, which are 10-20 times larger. In particular, it outperforms Gemini Pro at both MMLU and MMMU... https://t.co/CTXHn1yTe9