Benchmark

TempCompass

TempCompass is a comprehensive benchmark for evaluating temporal perception capabilities of Video Large Language Models (Video LLMs). It constructs…

Modality
multimodal
Categories
multimodal, reasoning, vision
Openness
unknown
Source
llm_stats
Reported scores
2

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Qwen2.5 VL 72B InstructQwen0.7482025-01-26evidence
Qwen2.5 VL 7B InstructQwen0.7172025-01-26evidence

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.