Surya OCR 2.5 hits 80%+ accuracy in 52 languages, loops 38x less than v2
VikParuchuri · x · 2026-10-30
Developer VikParuchuri shares internal benchmark results for the open-source multilingual OCR model Surya OCR 2.5: it scores over 80% accuracy in 52 languages, remaining a strong multilingual performer.
He also notes that repetitive loops are a common failure mode in small OCR models, and the team spent significant training effort cleaning them up—on a hard test set, Surya OCR 2.5 loops 38x less than Surya OCR 2. Over the past two years Surya has been used in low-resource language research, and the author hopes it stays valuable there.
Related event: Surya OCR 2.5 released as top sub-1B open-source OCR(6 posts)→
More from Models
- Arcee CEO Bindu Reddy: X echo chamber overhypes coding models, Argon and Astra underrated — bindureddy · 2026-10-30
- Hand-written tweet flagged as AI as user cites <1/1000 measured FP rate — ctjlewis · 2026-10-30
- GPT-4o's sycophancy kept doctors out of the loop as a user died, thread reveals — ctjlewis · 2026-10-30
- Rune launches 26B-A4B 'System One' decision model: no text generation, answers in one pass — sophiamyang · 2026-10-30
- Rumor claims GPT-6.2 is imminent, based on long-rumored 'Bel' model — mark_k · 2026-10-30
- OpenAI matches Anthropic: $100-$500 ChatGPT plans now include matching monthly API credits — Simon Willison · 2026-10-30