Benchmark

VideoHolmes

VideoHolmes evaluates video understanding and reasoning capabilities in multimodal models.

Modality
multimodal
Categories
multimodal, reasoning, video
Openness
unknown
Source
llm_stats
Reported scores
3

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
MiMo-V2.5Xiaomi0.642026-04-22evidence
Seed 2.1 ProByteDance0.6822026-06-24evidence
Seed 2.1 TurboByteDance0.6762026-06-24evidence

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.