OmniDocBench v1.6 Full - Formula CDM: leaderboard

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

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

Top models

#ModelSettingScoreOverall rank
1PaddleOCR-VL-1.697.53
2OvisOCR297.49
3MinerU2.5-Pro97.45
4OXR-1.097.44
5GLM-OCR97.18
6PaddleOCR-VL-1.596.89
7TeleOCR96.59
8Gemini 3 Pro95.99#136
9PaddleOCR-VL95.91
10MinerU-2.5omnidocbench_v16_primary_with_oxr run95.77
11Unlimited-OCR95.72
12Logics-Parsing-v295.65
13FireRed-OCR95.44
14Ovis2.6-30B-A3B95.17
15Gemini 3 Flash95.16#163

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