Document Parsing on OmniDocBench v1.6 benchmark leaderboard · SOTA2 Research

Document Parsing on OmniDocBench v1.6

94.74Overall ScoreHunyuanOCR-1.5

Evaluation Results

Method	Links
HunyuanOCR-1.52026.07		94.74	0.039	94.5	93.67	94.71	0.129
Unlimited-OCR2026.06		93.92	4.2	95.79	90.16	93.32	12.9
Unlimited-OCR2026.07		93.92	0.042	95.79	90.16	93.32	0.129
Qianfan-OCR2026.06		93.9	4	95.08	90.53	93.31	13
Qianfan-OCR2026.07		93.9	0.04	95.08	90.53	93.31	0.13
Ovis2.6-30B-A3B2026.07		93.7	0.035	95.17	89.44	92.4	0.135
Logics-Parsing-v22026.06		93.33	4.1	95.65	88.42	91.98	13.7
Logics-Parsing-v22026.07		93.33	0.041	95.65	88.42	91.98	0.137
ABot-OCR2026.07		93.3	0.037	94.86	88.69	91.87	0.137
FireRed-OCR2026.06		93.26	3.7	95.44	88.04	91.06	13.1
FireRed-OCR2026.07		93.26	0.037	95.44	88.04	91.06	0.131
Gemini 3 Pro2026.07		92.91	0.064	95.99	89.15	92.96	0.165
Gemini 3 Flash2026.07		92.62	0.066	95.16	89.29	93.51	0.172
HunyuanOCR2026.07		92.03	0.048	88.6	92.37	93.99	0.138
dots.ocr2026.06		90.77	4.8	89.95	87.18	90.58	13.8
dots.ocr2026.07		90.77	0.048	89.95	87.18	90.58	0.138
DeepSeek-OCR 22026.06		90.25	5	91.84	83.89	87.75	14.4
DeepSeek-OCR 22026.07		90.25	0.05	91.84	83.89	87.75	0.144
HunyuanOCR2026.06		89.95	8.8	87.68	91.01	92.23	17.1
Qwen3-VL-235B2026.07		89.78	0.063	92.55	83.07	86.75	0.166
OCRVerse2026.07		88.6	0.063	89.61	82.44	86.27	0.163
GPT-5.22026.07		86.59	0.114	88.21	82.95	87.93	0.193
olmOCR2026.07		85.74	0.139	88.1	83	87.17	0.216
Mistral OCR2026.07		85.66	0.097	89.91	76.78	80.93	0.171
Kimi K2.52026.07		84.53	0.107	83.5	80.76	84	0.211
InternVL3.5-241B2026.07		83.76	0.13	89.95	74.35	79.78	0.215