| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| OCRBench | Routing | Score922 | 433 | 6d ago | |
| OCRBench (test) | Qwen3-VL-8B | Score87.2 | 49 | 1d ago | |
| OCRVQA (test) | OCRVQA Score74.87 | 38 | 3mo ago | ||
| ORB-En-SynthDog 4-class rotation | Nanonets-OCR-s | Word Error Rate (WER)2.61 | 27 | 2mo ago | |
| ORB-En-FUNSD (test) | Nanonets-OCR-s | Word ANLS99.58 | 24 | 2mo ago | |
| UPTI (val) | UTRNet | Accuracy95.97 | 22 | 3mo ago | |
| IIITH (val) | UTRNet | Accuracy88.01 | 22 | 3mo ago | |
| UTRSet-Real (val) | UTRNet | Accuracy92.97 | 22 | 3mo ago | |
| ORB-Indic (test) | GPT-4o | Word ANLS97.7 | 21 | 2mo ago | |
| ORB-Indic 4-class rotation | GPT-4o | Word Accuracy94.55 | 21 | 2mo ago | |
| OCR | Ours | Average Score64.03 | 20 | 1mo ago | |
| Bentham (test) | OCR+PAGEN | CER8.48 | 19 | 1mo ago | |
| OCRBench English v2 | Recognition73.2 | 19 | 3mo ago | ||
| Chronicle American LoCCA (eval) | Character Error Rate0.5 | 18 | 3mo ago | ||
| IAM HW, EN | CER2.2 | 17 | 1mo ago | ||
| Lens | Qwen2.5-VL | Accuracy68.51 | 16 | 20d ago | |
| Dongba Script (test) | OmniOCR | Accuracy95.32 | 16 | 3mo ago | |
| Shui Script (test) | OmniOCR | Accuracy95.95 | 16 | 3mo ago | |
| Ancient Yi (test) | Accuracy90.53 | 16 | 3mo ago | ||
| Tibetan (test) | OmniOCR | Accuracy90.37 | 16 | 3mo ago | |
| SROIE P, EN | PILOT | F1 Score93.77 | 15 | 1mo ago | |
| Ancient Greek | TrOCR (Base) | Character Error Rate2.7 | 15 | 3mo ago | |
| OCRBench v2 | Accuracy (en)68 | 14 | 1mo ago | ||
| TextOCR VL-ICL Bench | LLaVA-OneVision-72B | Average Accuracy52.2 | 14 | 3mo ago | |
| Japanese Horizontal | EffOCR-C (Base) | Character Error Rate0.6 | 12 | 3mo ago |
