Benchmark
OmniDocBench
What is OmniDocBench?
OmniDocBench evaluates multimodal models on document understanding tasks such as OCR, layout parsing, and structured document comprehension.
- Released
- 2024-12-10
- Modality
- multimodal
- Evaluates
- multimodal, document understanding, vision
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 2
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/omnidocbench?top_n=500
OmniDocBench results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Kimi K3 | Moonshot AI | 0.911 | 2026-07-16 | evidence |
| MiMo-V2.5 | Xiaomi | 0.872 | 2026-04-22 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.