Benchmark
MME-RealWorld Benchmark
What is MME-RealWorld?
A comprehensive evaluation benchmark for Multimodal Large Language Models featuring over 13,366 high-resolution images and 29,429 question-answer pairs across…
- Modality
- multimodal
- Evaluates
- multimodal, general, vision
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 1
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/mme-realworld?top_n=500
MME-RealWorld results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Qwen2.5-Omni-7B | Qwen | 0.616 | 2025-03-27 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.