ai4bharat/FERMAT download history

ai4bharat/FERMAT is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 580 times (203 in the last 7 days), and 4,115 times in total. It ranks #41,401 among datasets by monthly downloads.

🧮📐 Can VLMs Evaluate Handwritten Math? ✏️✨ 🎉 We present FERMAT, a benchmark designed to rigorously test the multimodal reasoning and auto-evaluation capabilities of Vision-Language Models (VLMs) using real-world handwritten math problems! 📝🧠 🎯 What’s Inside FERMAT? 2,24

Models trained on FERMAT

1 models list it as training data.

Open ai4bharat/FERMAT on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.