Benchmark

MMVU

Video understanding benchmark. For non-video-native models, uses 1 fps frame extraction. Scores depend on frame sampling strategy and context length.

Released
2025-06-01
Categories
vision
Openness
unknown
Source
model_reports
Reported scores
1

Reported scores

model_reports

ModelOrganizationReported valueReportedEvidence
GLM-5.3-FlashZ.ai80.52026-08-27evidence

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.