@jerryjliu0: We've provided some updated results on Mistral OCR that make use of the annotation feature for charts. The overall scor…
Summary
Jerry Liu reports updated results for Mistral OCR on ParseBench, showing it outperforms GPT-5.5 and trails only Gemini 3.1 Pro, with strong performance on content faithfulness and semantic formatting.
View Cached Full Text
Cached at: 06/26/26, 08:08 AM
We’ve provided some updated results on Mistral OCR that make use of the annotation feature for charts.
The overall score is ahead of GPT-5.5 and just behind Gemini 3.1 Pro, which is quite impressive for a model at its price range.
It does a great job on content faithfulness, semantic formatting, and visual grounding. It does an ok job on tables and an ok job (though to be fair, non-zero) on charts.
There’s been some great advancements on visual understanding capabilities lately. See screenshot below for performance, will update the main benchmark page soon: https://parsebench.ai
Jerry Liu (@jerryjliu0): We benchmarked Mistral OCR against other frontier and open-weight models on ParseBench 📊
For a model at its price point, it is quite competitive!
- It wins on semantic formatting - understanding strikethroughs, superscripts/subscripts, title hierarchy, links
- It is
Similar Articles
@VikParuchuri: In their OCR 4 launch this week, Mistral shared a significantly lower score for Chandra 2 than you get from our repo or…
Mistral launched OCR 4, but a tweet points out that they reported lower scores for Chandra 2 than its actual performance and omitted Infinity Parser (87.6%) from their olmocr comparison.
Mistral OCR 4.1
Mistral AI announces OCR 4.1, an updated OCR service with native paragraph-level bounding box extraction, structural block labels, and block-level confidence scores, now in public preview.
@noctus91: Mistral OCR 4 reading a handwritten Henri Poincaré letter from 1905. Historical manuscripts usually break OCR models. T…
Mistral AI releases Mistral OCR 4, which can read historical handwritten manuscripts and provides bounding boxes, block classification, and inline confidence scores in 170 languages.
Mistral OCR 4
Mistral AI releases Mistral OCR 4, a compact document intelligence model that provides bounding boxes, block classification, and inline confidence scores for structured text extraction. It supports 170 languages, runs in a single container for self-hosted deployment, and integrates with the Mistral Search Toolkit for enterprise search and RAG pipelines.
@lu__jasper: Some early results from playing around with search on a subsampled version of OBLIQ-bench. Mixedbread's reranker is a b…
Early results from testing search on a subsampled OBLIQ-bench show that Mixedbread's reranker achieves strong MRR, sometimes outperforming GPT 5.5 on certain metrics with faster speed, though the benchmark remains challenging.