OmniDocBench v1.6 Full - Table TEDS: leaderboard

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

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

Top models

#ModelScoreOverall rank
1TeleOCR96.82
2OXR-1.096.62
3PaddleOCR-VL-1.694.76
4OvisOCR294.58
5MinerU2.5-Pro93.42
6GLM-OCR92.83
7Youtu-Parsing92.02
8PaddleOCR-VL-1.591.67
9HunyuanOCR91.01
10PaddleOCR-VL90.65
11Qianfan-OCR90.53
12Unlimited-OCR90.21
13Ovis2.6-30B-A3B89.44
14Gemini 3 Flash89.29#163
15Gemini 3 Pro89.15#136

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