multimodal benchmark
TempCompass
TempCompass is a comprehensive benchmark for evaluating temporal perception capabilities of Video Large Language Models (Video LLMs). It constructs conflicting videos that share identical static content but differ in specific temporal aspects to prevent models from exploiting single-frame bias. The benchmark evaluates multiple temporal aspects including action, motion, speed, temporal order, and attribute changes across diverse task formats including multi-choice QA, yes/no QA, caption matching, and caption generation.
Updated Aug 11, 2026
Models2
Model coverage2
MetricScore
EvidenceB
TempCompass Ranking
Higher score ranks better on this benchmark.
| 01 | AC | 74.8% | 100.0% | 2 | C | |
| 02 | AC | 71.7% | 0.0% | 2 | C |
TempCompass Score Distribution
A closer view of the leading scores on this benchmark.
TempCompass Highlights
The leading models and scores on this benchmark.
What is TempCompass?
What TempCompass measures and how its scores work.
TempCompass is a comprehensive benchmark for evaluating temporal perception capabilities of Video Large Language Models (Video LLMs). It constructs conflicting videos that share identical static content but differ in specific temporal aspects to prevent models from exploiting single-frame bias. The benchmark evaluates multiple temporal aspects including action, motion, speed, temporal order, and attribute changes across diverse task formats including multi-choice QA, yes/no QA, caption matching, and caption generation.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- TempCompass
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- tempcompass|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about TempCompass.
Which model scores highest on TempCompass?
Qwen2.5 VL 72B Instruct is currently ranked first with 74.8%.
What does TempCompass measure?
TempCompass is a comprehensive benchmark for evaluating temporal perception capabilities of Video Large Language Models (Video LLMs). It constructs conflicting videos that share identical static content but differ in specific temporal aspects to prevent models from exploiting single-frame bias. The benchmark evaluates multiple temporal aspects including action, motion, speed, temporal order, and attribute changes across diverse task formats including multi-choice QA, yes/no QA, caption matching, and caption generation.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.