OpenCodePapers

optical-character-recognition-ocr-on-ocrbench-v2

Optical Character Recognition (OCR)
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeEnglish ScoreChinese ScoreModelNameReleaseDate
Qwen3.8-Max: A New Bar for Coding and Cowork✓ Link74.268.3Qwen3.8-Max2026-08-03
Qwen3-VL Technical Report✓ Link68.4Qwen3-VL-32B-Thinking2025-11-26
Priming Base Models for Agentic Post-Training: An Open Midtraining Recipe68.1259.15NVIDIA Nemotron 3.5 Super VL 120B-A12B BF162026-10-15
Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence✓ Link67.052.7Nemotron 3 Nano Omni (Reasoning)2026-04-27
Ovis2.5 Technical Report✓ Link63.458.0Ovis2.5-9B2025-08-15
Qwen2.5-VL Technical Report✓ Link61.563.7Qwen2.5-VL-72B2025-02-19
Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale60.160.6Intern-S1-Pro2026-03-26
Qianfan-OCR: A Unified End-to-End Model for Document Intelligence✓ Link56.060.77Qianfan-OCR2026-03-11
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone40.647.3MiniCPM-V 4.6 (Instruct, 4x)2026-05-13
Qwen2.5-VL Technical Report✓ Link57.2Qwen2.5-VL-7B2025-02-19
Qwen3-VL Technical Report✓ Link63.5Qwen3-VL-235B-A22B-Thinking2025-11-26
Check out how to contribute new results. Then edit this file on GitLab or GitHub.