multimodal benchmark
MMMU-Pro Leaderboard
MMMU-Pro is a multi-discipline multimodal understanding benchmark that enhances MMMU by filtering text-only answerable questions, augmenting candidate options, and introducing vision-only input settings.
Updated Oct 23, 2026
Models73
Model coverage73
MetricScore
EvidenceB
MMMU-Pro Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelOP | Score85.95% | Percentile100.00% | Participants73 | EvidenceB | Evaluated |
| Rank02 | ModelGO | Score83.60% | Percentile98.61% | Participants73 | EvidenceC | Evaluated |
| Rank03 | ModelOP | Score83.20% | Percentile97.22% | Participants73 | EvidenceC | Evaluated |
| Rank04 | ModelOP | Score83.00% | Percentile95.83% | Participants73 | EvidenceC | Evaluated |
| Rank05 | ModelBY | Score82.70% | Percentile94.44% | Participants73 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score82.30% | Percentile93.06% | Participants73 | EvidenceC | Evaluated |
| Rank07 | ModelBY | Score82.20% | Percentile91.67% | Participants73 | EvidenceC | Evaluated |
| Rank08 | ModelMA | Score81.60% | Percentile90.28% | Participants73 | EvidenceC | Evaluated |
| Rank09 | ModelGO | Score81.20% | Percentile88.89% | Participants73 | EvidenceC | Evaluated |
| Rank10 | ModelOP | Score81.20% | Percentile87.50% | Participants73 | EvidenceC | Evaluated |
| Rank11 | ModelGO | Score81.00% | Percentile86.11% | Participants73 | EvidenceC | Evaluated |
| Rank12 | ModelOP | Score80.70% | Percentile84.72% | Participants73 | EvidenceC | Evaluated |
| Rank13 | ModelGO | Score80.50% | Percentile83.33% | Participants73 | EvidenceC | Evaluated |
| Rank14 | ModelME | Score80.40% | Percentile81.94% | Participants73 | EvidenceC | Evaluated |
| Rank15 | ModelMA | Score80.10% | Percentile80.56% | Participants73 | EvidenceC | Evaluated |
| Rank16 | ModelOP | Score79.50% | Percentile79.17% | Participants73 | EvidenceC | Evaluated |
| Rank17 | ModelAC | Score79.00% | Percentile77.78% | Participants73 | EvidenceC | Evaluated |
| Rank18 | ModelAC | Score78.80% | Percentile76.39% | Participants73 | EvidenceC | Evaluated |
| Rank19 | ModelMA | Score78.50% | Percentile75.00% | Participants73 | EvidenceC | Evaluated |
| Rank20 | ModelOP | Score78.40% | Percentile73.61% | Participants73 | EvidenceC | Evaluated |
| Rank21 | ModelOP | Score78.40% | Percentile72.22% | Participants73 | EvidenceC | Evaluated |
| Rank22 | ModelMI | Score78.10% | Percentile70.83% | Participants73 | EvidenceC | Evaluated |
| Rank23 | ModelXI | Score77.90% | Percentile69.44% | Participants73 | EvidenceC | Evaluated |
| Rank24 | ModelAN | Score77.30% | Percentile68.06% | Participants73 | EvidenceC | Evaluated |
| Rank25 | ModelGO | Score76.90% | Percentile66.67% | Participants73 | EvidenceC | Evaluated |
| Rank26 | ModelAC | Score76.90% | Percentile65.28% | Participants73 | EvidenceC | Evaluated |
| Rank27 | ModelGO | Score76.80% | Percentile63.89% | Participants73 | EvidenceC | Evaluated |
| Rank28 | ModelOP | Score76.60% | Percentile62.50% | Participants73 | EvidenceC | Evaluated |
| Rank29 | ModelOP | Score76.40% | Percentile61.11% | Participants73 | EvidenceC | Evaluated |
| Rank30 | ModelOP | Score76.00% | Percentile59.72% | Participants73 | EvidenceC | Evaluated |
MMMU-Pro Highlights
The leading models and scores on this benchmark.
MMMU-Pro Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for MMMU-Pro
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is MMMU-Pro?
What MMMU-Pro measures and how its scores work.
MMMU-Pro is a multimodal benchmark for evaluating multi-discipline understanding and extends MMMU through a three-step process.
It measures multimodal understanding performance using Score, reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MMMU-Pro
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MMMU-Pro.
Which model scores highest on MMMU-Pro?
GPT-6.1 Sol is currently ranked first with 85.95%.
What are the top three models on MMMU-Pro?
The current leaders are GPT-6.1 Sol (85.95%), Gemini 3.5 Flash (83.60%), and GPT-5.5 (83.20%).
Which MMMU-Pro model has the lowest official input price?
Qwen2.5-Omni-7B has the lowest matched official input price at $0.10 input / $0.40 output per 1M tokens.
Which models are fastest among MMMU-Pro results?
The fastest matched records are Llama 4 Maverick (638.70 tok/s via Sambanova), GPT-5.6 Luna (215.52 tok/s via OpenAI), and GPT-4o (132.00 tok/s via OpenAI).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.