OmniDocBench
Document-parsing benchmark from OpenDataLab (Shanghai AI Lab) scoring end-to-end PDF/page parsing across text, formulas (CDM), tables (TEDS) and reading order. Overall is a 0-100 composite; the version (v1.5/v1.6/v1.7) goes in each row.
Models ranked
1
tracked on this benchmark
Score band
97.0 – 97.0
best → lowest tracked
Snapshot trend
—
need ≥2 snapshots
Leaderboard
Tracked models ranked by Overall (higher is better).
Configuration: Youtu-Parsing-Omni (5B); official OmniDocBench evaluator (Docker repro image named on card)
Notes: Tencent first-party HF card, '### OmniDocBench v1.6' table, Overall: 96.96. OmniDocBench repo moved v1.6 -> v1.7 on 2026/04/30, so version is carried in the row, not the slug. Retrieved 2026-11-02.
How to read this benchmark
This benchmark scores models where higher is better. Use scores for directional filtering and shortlisting, not universal quality ranking; then validate pricing, context window, provider availability, and fit for your workload.
Trust this score when
- There is a fresh timestamped snapshot (or multiple snapshots) for this benchmark.
- The model list covers the same version family you can actually deploy today.
- Top candidates overlap with your required routing and feature requirements.
Be cautious when
- There is only one benchmark snapshot or the dataset appears stale.
- The benchmark metric direction is opposite of your decision objective.
- The score difference between options is narrow and likely within implementation variance.
Related benchmarks
Last reviewed: Nov 2, 2026