multimodal benchmark
OmniDocBench 1.5 Leaderboard
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 17, 2026
Models18
Model coverage18
MetricScore
EvidenceB
OmniDocBench 1.5 Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMI | Score91.6% | Percentile100.0% | Participants18 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score91.4% | Percentile94.1% | Participants18 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score91.2% | Percentile88.2% | Participants18 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score91.1% | Percentile82.3% | Participants18 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score89.9% | Percentile76.5% | Participants18 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score89.8% | Percentile70.6% | Participants18 | EvidenceC | Evaluated |
| Rank07 | ModelAC | Score89.3% | Percentile64.7% | Participants18 | EvidenceC | Evaluated |
| Rank08 | ModelOP | Score89.1% | Percentile58.8% | Participants18 | EvidenceC | Evaluated |
| Rank09 | ModelAC | Score88.9% | Percentile52.9% | Participants18 | EvidenceC | Evaluated |
| Rank10 | ModelMA | Score88.8% | Percentile47.1% | Participants18 | EvidenceC | Evaluated |
| Rank11 | ModelOP | Score87.5% | Percentile41.2% | Participants18 | EvidenceC | Evaluated |
| Rank12 | ModelOP | Score87.4% | Percentile35.3% | Participants18 | EvidenceC | Evaluated |
| Rank13 | ModelOP | Score75.8% | Percentile29.4% | Participants18 | EvidenceC | Evaluated |
| Rank14 | ModelME | Score75.8% | Percentile23.5% | Participants18 | EvidenceC | Evaluated |
| Rank15 | ModelGO | Score31.9% | Percentile17.6% | Participants18 | EvidenceC | Evaluated |
| Rank16 | ModelGO | Score16.4% | Percentile11.8% | Participants18 | EvidenceC | Evaluated |
| Rank17 | ModelGO | Score12.1% | Percentile5.9% | Participants18 | EvidenceC | Evaluated |
| Rank18 | ModelGO | Score11.5% | Percentile0.0% | Participants18 | EvidenceC | Evaluated |
OmniDocBench 1.5 Highlights
The leading models and scores on this benchmark.
OmniDocBench 1.5 Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for OmniDocBench 1.5
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis omnidocbench 1.5 AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01MIMiniMax M3MiniMax
- Score
- 91.6%
- Price
- $0.30 input / $1.2 output per 1M tokens
- Speed
- Up to 214 tok/s via Together
Strengths
- Ranks #1 of 18 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures OmniDocBench 1.5, not total model capability
- 02ACQwen3.7-PlusAlibaba Cloud / Qwen Team
- Score
- 91.4%
- Price
- $0.50 input / $3.0 output per 1M tokens
Strengths
- Ranks #2 of 18 compared models
- 94th percentile on this benchmark
- C evidence result
Considerations
- This result measures OmniDocBench 1.5, not total model capability
- 03ACQwen3.6 PlusAlibaba Cloud / Qwen Team
- Score
- 91.2%
- Price
- $0.50 input / $3.0 output per 1M tokens
- Speed
- Up to 16 tok/s via Together
Strengths
- Ranks #3 of 18 compared models
- 88th percentile on this benchmark
- C evidence result
Considerations
- This result measures OmniDocBench 1.5, not total model capability
- 04ACQwen3.8-27BAlibaba Cloud / Qwen Team
- Score
- 91.1%
Strengths
- Ranks #4 of 18 compared models
- 82th percentile on this benchmark
- C evidence result
Considerations
- This result measures OmniDocBench 1.5, not total model capability
- 05ACQwen3.6-35B-A3BAlibaba Cloud / Qwen Team
- Score
- 89.9%
- Price
- $0.25 input / $1.5 output per 1M tokens
Strengths
- Ranks #5 of 18 compared models
- 76th percentile on this benchmark
- C evidence result
Considerations
- This result measures OmniDocBench 1.5, not total model capability
Selection summary
Best AI Models for OmniDocBench 1.5
MiniMax M3 currently leads OmniDocBench 1.5 with 91.6%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
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?
18 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.