OmniDocBench v1.6 Full - Table TEDS-S: leaderboard

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

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

Top models

#ModelScoreOverall rank
1OXR-1.098.44
2TeleOCR98.18
3PaddleOCR-VL-1.697.1
4OvisOCR296.98
5MinerU2.5-Pro95.92
6GLM-OCR95.39
7Youtu-Parsing95
8PaddleOCR-VL-1.594.37
9PaddleOCR-VL93.74
10Gemini 3 Flash93.51#163
11Unlimited-OCR93.36
12Qianfan-OCR93.31
13HunyuanOCR93.23
14Gemini 3 Pro92.96#136
15Ovis2.6-30B-A3B92.4

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