Benchmark
Video-MME (long, no subtitles) Benchmark
What is Video-MME (long, no subtitles)?
Video-MME is the first-ever comprehensive evaluation benchmark for Multi-modal Large Language Models (MLLMs) in video analysis. This variant focuses on…
- Modality
- multimodal
- Evaluates
- multimodal, video, vision
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 1
Source provenance
Video-MME (long, no subtitles) results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| GPT-4.1 | OpenAI | 0.72 | 2025-04-14 | 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.