multimodal benchmark
OmniDocBench 1.5
OmniDocBench 1.5 is a comprehensive benchmark for evaluating multimodal large language models on document understanding tasks, including OCR, document parsing, information extraction, and visual question answering across diverse document types. Lower Overall Edit Distance scores are better.
Updated Aug 11, 2026
Models17
Model coverage17
MetricScore
EvidenceB
OmniDocBench 1.5 Ranking
Higher score ranks better on this benchmark.
| 01 | MI | 91.6% | 100.0% | 17 | C | |
| 02 | AC | 91.4% | 93.8% | 17 | C | |
| 03 | AC | 91.2% | 87.5% | 17 | C | |
| 04 | AC | 89.9% | 81.3% | 17 | C | |
| 05 | AC | 89.8% | 75.0% | 17 | C | |
| 06 | AC | 89.3% | 68.8% | 17 | C | |
| 07 | OP | 89.1% | 62.5% | 17 | C | |
| 08 | AC | 88.9% | 56.3% | 17 | C | |
| 09 | MA | 88.8% | 50.0% | 17 | C | |
| 10 | OP | 87.5% | 43.8% | 17 | C | |
| 11 | OP | 87.4% | 37.5% | 17 | C | |
| 12 | OP | 75.8% | 31.3% | 17 | C | |
| 13 | ME | 75.8% | 25.0% | 17 | C | |
| 14 | GO | 31.9% | 18.8% | 17 | C | |
| 15 | GO | 16.4% | 12.5% | 17 | C | |
| 16 | GO | 12.1% | 6.3% | 17 | C | |
| 17 | GO | 11.5% | 0.0% | 17 | C |
OmniDocBench 1.5 Score Distribution
A closer view of the leading scores on this benchmark.
OmniDocBench 1.5 Highlights
The leading models and scores on this benchmark.
What is OmniDocBench 1.5?
What OmniDocBench 1.5 measures and how its scores work.
OmniDocBench 1.5 is a comprehensive benchmark for evaluating multimodal large language models on document understanding tasks, including OCR, document parsing, information extraction, and visual question answering across diverse document types. Lower Overall Edit Distance scores are better.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- OmniDocBench 1.5
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- omnidocbench-1.5|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about OmniDocBench 1.5.
Which model scores highest on OmniDocBench 1.5?
MiniMax M3 is currently ranked first with 91.6%.
What does OmniDocBench 1.5 measure?
OmniDocBench 1.5 is a comprehensive benchmark for evaluating multimodal large language models on document understanding tasks, including OCR, document parsing, information extraction, and visual question answering across diverse document types. Lower Overall Edit Distance scores are better.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
17 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.