List your company

Grounded OCR on OCR-IDL, TabMe++, and PubMed-OCR (10.5K held-out pages)

0.202CER (text)GutenOCR-7B
0.1820.3170.4520.587Jan 20, 2026

Evaluation results

MethodLinks
GutenOCR-7BParams=7B, Backbone=Qwen2.5-VL, Training Stage=3a, Coord. boxes=Yes2026.010.2020.280.1470.1290.7870.8820.819
GutenOCR-3BParams=3B, Backbone=Qwen2.5-VL, Training Stage=3a, Coord. boxes=Yes2026.010.2240.2930.1850.1090.7980.8770.811
Qwen3-VL-8BParams=8B, Backbone=N/A, Coord. boxes=Yes2026.010.2850.4910.3060.6890.0490.0250.384
Infinity-Parser-7BParams=7B, Backbone=Qwen2.5-VL-7B, Coord. boxes=No2026.010.310.5860.3860.6130.0980.1120.386
Qwen2.5-VL-7BParams=7B, Backbone=N/A, Coord. boxes=Yes2026.010.3330.5220.6330.530.1110.2850.396
olmOCR 2Params=7B, Backbone=Qwen2.5-VL-7B, Coord. boxes=No2026.010.3650.530.5150.7450.0390.0240.318
Nanonets OCR2-3BParams=3B, Backbone=Qwen2.5-VL-3B, Coord. boxes=No2026.010.3690.5180.6450.8070.0010.0010.277
Chandra OCRParams=8B, Backbone=Qwen3-VL-8B, Coord. boxes=Yes2026.010.390.5930.8670.7210.0120.0050.241
PaddleOCR-VLParams=0.9B, Backbone=PaddleOCR-VL-0.9B, Coord. boxes=No2026.010.3990.53910.9360.0010.0020.188
Qwen2.5-VL-3BParams=3B, Backbone=N/A, Coord. boxes=Yes2026.010.5080.5840.3790.6990.1350.1210.348
DeepSeek-OCRParams=3B, Backbone=DeepSeek-3B-MoE, Coord. boxes=Yes2026.010.7020.8090.9980.940.010.0030.094