Baidu Releases Unlimited OCR Model, Tops GitHub and HuggingFace Rankings with 93.92% Benchmark Score

According to 36氪, Baidu released and open-sourced its end-to-end OCR model Unlimited OCR on June 29. The model topped GitHub Daily Trending and Python trending charts the day after release, and ranked first on both HuggingFace's global model trends leaderboard and multimodal model trends leaderboard. In the OmniDocBench v1.6 benchmark test, Unlimited OCR achieved a 93.92% comprehensive score, setting a new record for end-to-end OCR models.
Disclaimer: The information on this page may come from third-party sources and is for reference only. It does not represent the views or opinions of Gate and does not constitute any financial, investment, or legal advice. Virtual asset trading involves high risk. Please do not rely solely on the information on this page when making decisions. For details, see the Disclaimer.
Comment
0/400
No comments