multimodal benchmark
VATEX
VaTeX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research. Contains over 41,250 videos and 825,000 captions in both English and Chinese, with over 206,000 English-Chinese parallel translation pairs. Supports multilingual video captioning and video-guided machine translation tasks.
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
VATEX leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AM Nova LiteAmazon | 77.8% | 100.0% | 2 | C | |
| 2 | AMNova ProAmazon | 77.8% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
VATEX highlights
The top published results on this benchmark's own scale.
What is VATEX?
Definition and scoring fields from the benchmark registry.
VaTeX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research. Contains over 41,250 videos and 825,000 captions in both English and Chinese, with over 206,000 English-Chinese parallel translation pairs. Supports multilingual video captioning and video-guided machine translation tasks.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- VATEX
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- vatex|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about VATEX.
Which model scores highest on VATEX?
Nova Lite is currently ranked first with 77.8%.
What does VATEX measure?
VaTeX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research. Contains over 41,250 videos and 825,000 captions in both English and Chinese, with over 206,000 English-Chinese parallel translation pairs. Supports multilingual video captioning and video-guided machine translation tasks.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.