Image created with Gemini. Image prompt: A horizontal 1920s Dada Merz collage on aged board, torn fragments of a vintage French Marseille weather bulletin and SNCF railway timetable swept diagonally as if blown by a strong wind, a faded vermilion-cream-slate-blue tricolor paper stripe anchoring the lower corner, a small cut paper weather-vane arrow, the word ‘Mistral’ spelled in mismatched cut-out letters from French newsprint and letterpress specimens glued at slight windswept angles across the top, visible paper fiber edges, glue stains, foxing and coffee stains, flat even scanner lighting, no digital effects.
Mistral claims SOTA performance on OlmOCRBench, a popular optical character recognition benchmark, but that isn’t the case. We have a public leaderboard on @huggingface, where Mistral OCR 4 currently ranks #3, behind open models like Chandra OCR 2 by @datalabto”
https://x.com/NielsRogge/status/2069432947711652210
Mistral OCR 4 : SOTA OCR for Document Intelligence
https://mistral.ai/news/ocr-4/
Introducing Mistral OCR 4. It creates structure with bounding boxes, block classification, and inline confidence scores in 170 languages. 🧵👇”
https://x.com/MistralAI/status/2069420263825895917
Leave a Reply