Surya OCR 2.5 scores over 80% on 52 languages in internal benchmark
VikParuchuri · x · 2026-10-30
VikParuchuri (Datalab) congratulates @hheiden12 on the release and promises more updates to Chandra and Surya soon. Surya OCR 2.5 remains a strong multilingual model, with 52 languages scoring over 80% on their internal benchmark. Over the past two years Surya has been used in low-resource language research, and the team hopes it stays valuable there.
Related event: Surya OCR 2.5 released as top sub-1B open-source OCR(6 posts)→
More from Multimodal
- GOLD SIGNAL: Striking AI Portrait Blends Golden Ornament With Cybernetic Face — PierceLilholt · 2026-10-30
- MiniMax Reference Video tested with image reference and DLSS 5, results look convincing — Grinderius · 2026-10-30
- Canva unveils Brush, its first vision-language model for design editing — alex_verem · 2026-10-30
- Kinoloom: open-source ComfyUI film studio renders seamless LTX 2.5 takes on 8GB card — Dry-Acanthisitta-652 · 2026-10-30
- Know, then Draw: UCSD & Adobe Cut Image-Gen Training Compute 48x While Boosting DPG-Bench 10% — Yucheng Mao · 2026-10-30
- Pika H3 Flex: official 6-step vs fused 4-step Turbo LoRA compared — Illustrious_Row_9971 · 2026-10-30