multimodal benchmark
VideoHolmes
VideoHolmes evaluates video understanding and reasoning capabilities in multimodal models.
Updated Aug 11, 2026
Models3
Model coverage3
MetricScore
EvidenceB
VideoHolmes Ranking
Higher score ranks better on this benchmark.
| 1 | BY | 68.2% | 100.0% | 3 | C | |
| 2 | BY | 67.6% | 50.0% | 3 | C | |
| 3 | XI | 64.0% | 0.0% | 3 | C |
VideoHolmes Score Distribution
A closer view of the leading scores on this benchmark.
VideoHolmes Highlights
The leading models and scores on this benchmark.
What is VideoHolmes?
What VideoHolmes measures and how its scores work.
VideoHolmes evaluates video understanding and reasoning capabilities in multimodal models.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- VideoHolmes
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- videoholmes|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about VideoHolmes.
Which model scores highest on VideoHolmes?
Seed 2.1 Pro is currently ranked first with 68.2%.
What does VideoHolmes measure?
VideoHolmes evaluates video understanding and reasoning capabilities in multimodal models.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.