OmniDocBench v1.6 Full - Overall: leaderboard

OmniDocBench v1.6 Full - Overall — 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: Overall (%). Source: https://github.com/opendatalab/OmniDocBench

Metric: Overall (%). Source: github.com. Saturation forecast: Estimated already saturated. 36 models tracked. Updated 16 Nov 2026.

Top models

#ModelScoreOverall rank
1OXR-1.097.18
2TeleOCR96.91
3OvisOCR296.47
4PaddleOCR-VL-1.696.34
5MinerU2.5-Pro95.75
6GLM-OCR95.22
7PaddleOCR-VL-1.594.93
8PaddleOCR-VL94.18
9Unlimited-OCR94
10Qianfan-OCR93.9
11Youtu-Parsing93.74
12Ovis2.6-30B-A3B93.7
13Logics-Parsing-v293.33
14ABot-OCR93.3
15FireRed-OCR93.26

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-overall · How It Works · Data refreshed daily, snapshot 2026-11-16.