OmniDocBench v1.6 Full - Text Edit: leaderboard
OmniDocBench v1.6 Full - Text Edit — Native OmniDocBench PRIMARY caption explicitly v1.6_full,1651pages. Pinned primary READMEf133a71e; update prose also mentionsv1.7 but this caption names the actual cohort. Multi-Granularity Adaptive Matching, groundtruthunchanged. Overall=((1-TextEdit)*100+TEDS+FormulaCDM)/3. Native primary cells retain fourdecimal precision; source OXRownresult extends exact v1.6_full cohort, with its README separately hashguarded. OXRcard peer copies not added as independent measurements. No fusion with existing v1.5 or unversioned othercohorts. Text/readingorder edit values remain native ratios, not percentages. No inferred model decoding settings. Metric: Normalized edit distance. Source: https://github.com/opendatalab/OmniDocBench
Metric: Normalized edit distance. Source: github.com. Saturation forecast: Around May 2027. 36 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | OXR-1.0 | 0.0251 | |
| 2 | OvisOCR2 | 0.0265 | |
| 3 | TeleOCR | 0.0267 | |
| 4 | PaddleOCR-VL-1.6 | 0.0326 | |
| 5 | Ovis2.6-30B-A3B | 0.035 | |
| 6 | MinerU2.5-Pro | 0.036 | |
| 7 | FireRed-OCR | 0.037 | |
| 8 | ABot-OCR | 0.037 | |
| 9 | PaddleOCR-VL-1.5 | 0.038 | |
| 10 | Unlimited-OCR | 0.0394 | |
| 11 | PaddleOCR-VL | 0.04 | |
| 12 | Qianfan-OCR | 0.04 | |
| 13 | Logics-Parsing-v2 | 0.041 | |
| 14 | GLM-OCR | 0.044 | |
| 15 | Youtu-Parsing | 0.044 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=omnidocbench-v1-6-full-text-edit · How It Works · Data refreshed daily, snapshot 2026-11-16.