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 7, 2026
Published models16
Registry coverage16
MetricScore
EvidenceB
OmniDocBench 1.5 leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | MI | 91.6% | 100.0% | 16 | C | |
| 2 | AC | 91.4% | 93.3% | 16 | C | |
| 3 | AC | 91.2% | 86.7% | 16 | C | |
| 4 | AC | 89.9% | 80.0% | 16 | C | |
| 5 | AC | 89.8% | 73.3% | 16 | C | |
| 6 | AC | 89.3% | 66.7% | 16 | C | |
| 7 | OP | 89.1% | 60.0% | 16 | C | |
| 8 | AC | 88.9% | 53.3% | 16 | C | |
| 9 | MA | 88.8% | 46.7% | 16 | C | |
| 10 | OP | 87.5% | 40.0% | 16 | C | |
| 11 | OP | 87.4% | 33.3% | 16 | C | |
| 12 | OP | 75.8% | 26.7% | 16 | C | |
| 13 | GO | 31.9% | 20.0% | 16 | C | |
| 14 | GO | 16.4% | 13.3% | 16 | C | |
| 15 | GO | 12.1% | 6.7% | 16 | C | |
| 16 | GO | 11.5% | 0.0% | 16 | C |
Score distribution
Top published rows on the benchmark's original scale.
OmniDocBench 1.5 highlights
The top published results on this benchmark's own scale.
What is OmniDocBench 1.5?
Definition and scoring fields from the benchmark registry.
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. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- OmniDocBench 1.5
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- omnidocbench-1.5|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
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?
16 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.