multimodal benchmark
CrossVid
CrossVid evaluates cross-video reasoning, requiring models to integrate information across multiple videos.
Updated Aug 11, 2026
Models2
Model coverage2
MetricScore
EvidenceB
CrossVid Ranking
Higher score ranks better on this benchmark.
| 1 | BY | 65.0% | 100.0% | 2 | C | |
| 2 | BY | 63.2% | 0.0% | 2 | C |
CrossVid Score Distribution
A closer view of the leading scores on this benchmark.
CrossVid Highlights
The leading models and scores on this benchmark.
What is CrossVid?
What CrossVid measures and how its scores work.
CrossVid evaluates cross-video reasoning, requiring models to integrate information across multiple videos.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- CrossVid
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- crossvid|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about CrossVid.
Which model scores highest on CrossVid?
Seed 2.1 Pro is currently ranked first with 65.0%.
What does CrossVid measure?
CrossVid evaluates cross-video reasoning, requiring models to integrate information across multiple videos.
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.