Benchmark

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
Categories
multimodal, video, vision
Openness
unknown
Source
llm_stats
Reported scores
1

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
GPT-4.1OpenAI0.722025-04-14evidence

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.