Note: Overall leaderboard rankings may not reflect true model quality — individual benchmarks give a clearer picture. ARC-Challenge MMLU GPQA GSM8K Artificial Analysis Intelligence Index v4.1
← Back to leaderboard

ParseBench

31 models

Top 5 Models Performance

Anthropic: claude-opus-5.5 ######################################## 79.85
kflai: kdl-frontier-parser-nano ###################################### 76.36
infly: infinity-parser2-pro ##################################### 74.3
infly: infinity-parser2-flash ##################################### 73.25
opendatalab: mineru2.5-pro-2605-1.2b #################################### 72.78
– 970 – 1.1T
– 2019 – 2026
Rank Model Score
🇺🇸 1 Anthropic: claude-opus-5.5 79.85
❓ 2 kflai: kdl-frontier-parser-nano 76.36
❓ 3 infly: infinity-parser2-pro 74.3
❓ 4 infly: infinity-parser2-flash 73.25
❓ 5 opendatalab: mineru2.5-pro-2605-1.2b 72.78
🇨🇳 6 Qwen: qwen3.8-27b通义千问 70.79
❓ 7 datalab-to: chandra-ocr-2 70.1
🇨🇳 8 PaddlePaddle: PaddleOCR-VL-1.6 67.43
🇨🇳 9 PaddlePaddle: PaddleOCR-VL-1.5 65.95
❓ 10 datalab-to: surya-ocr-2 64.83
🇺🇸 11 Google: Gemma 4 31B Instruct 62.4
🇨🇳 12 wan-ai: wan2.6 60.7
🇺🇸 13 Google: Gemma 4 26B A4B Instruct 58.5
❓ 14 rednote-hilab: dots.mocr 55.8
🇦🇪 15 Technology Innovation Institute: falcon-ocr 53.08
❓ 16 docling-project: docling-models 50.6
❓ 17 lightonai: lightonocr-2-1b 48
🇨🇳 18 Qwen: qwen3-vl-8b-instruct通义千问 46.8
🇨🇳 19 Baidu: qianfan-ocr百度 46.2
🇨🇳 20 Baidu: Unlimited OCR百度 46.17
❓ 21 opendatalab: mineru2.5-2509-1.2b 45.9
🇨🇳 22 Qwen: qwen3.6-35b-a3b通义千问 44.1
🇨🇳 23 DeepSeek: deepseek-ocr-2深度求索 41.2
🇨🇳 24 PaddlePaddle: PaddleOCR-VL 40.9
🇺🇸 25 Google: Gemma 4 E4B Instruct 40.5
🇺🇸 26 IBM Granite: granite-vision-4.1-4b 39.45
🇨🇳 27 Qwen: Qwen3.5 4B通义千问 35.4
🇨🇳 28 Qwen: Qwen3.5 9B通义千问 31.9
🇨🇳 29 Z.ai: glm-ocr北京智谱华章科技有限公司 29.6
🇨🇳 30 Qwen: Qwen3.5 0.8B通义千问 28.4
🇨🇳 31 Qwen: Qwen3.5 2B通义千问 27.3