multimodal benchmark
MME-RealWorld Leaderboard
MME-RealWorld is a multimodal benchmark for evaluating Multimodal Large Language Models using high-resolution images and question-answer pairs across 43 subtasks and 5 real-world scenarios.
Updated Sep 5, 2026
Models1
Model coverage1
MetricScore
EvidenceB
MME-RealWorld Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score61.60% | Percentile100.00% | Participants1 | EvidenceC | Evaluated |
MME-RealWorld Highlights
The leading models and scores on this benchmark.
The Top AI Models for MME-RealWorld
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis mme-realworld AI model leaderboard uses descending score in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01ACAlibaba Cloud / Qwen Team
- Score
- 61.60%
- Price
- $0.10 input / $0.40 output per 1M tokens
Strengths
- Ranks #1 of 1 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures MME-RealWorld, not total model capability
Selection summary
Best AI Models for MME-RealWorld
Qwen2.5-Omni-7B currently leads MME-RealWorld with 61.60%. 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 MME-RealWorld?
What MME-RealWorld measures and how its scores work.
MME-RealWorld is a multimodal evaluation benchmark containing over 13,366 high-resolution images and 29,429 question-answer pairs across 43 subtasks and 5 real-world scenarios.
It measures Multimodal Large Language Model performance on high-resolution, real-world multimodal tasks, reported as a Score ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MME-RealWorld
- 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 MME-RealWorld.
Which model scores highest on MME-RealWorld?
Qwen2.5-Omni-7B is currently ranked first with 61.60%.
What are the top three models on MME-RealWorld?
The current leaders are Qwen2.5-Omni-7B (61.60%).
Which MME-RealWorld 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 MME-RealWorld results?
No matched runtime record is currently available.
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.