multimodal benchmark
QVHighlights Leaderboard
QVHighlights is a multimodal video moment retrieval benchmark that uses natural language queries to identify relevant moments and highlights in videos.
Updated Sep 5, 2026
Models3
Model coverage3
MetricScore
EvidenceB
QVHighlights Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAM Nova 2 LiteAmazon | Score77.20% | Percentile100.00% | Participants3 | EvidenceC | Evaluated |
| Rank02 | ModelAMNova 2 OmniAmazon | Score76.70% | Percentile50.00% | Participants3 | EvidenceC | Evaluated |
| Rank03 | ModelAMNova 2 ProAmazon | Score76.70% | Percentile0.00% | Participants3 | EvidenceC | Evaluated |
QVHighlights Highlights
The leading models and scores on this benchmark.
QVHighlights Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for QVHighlights
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is QVHighlights?
What QVHighlights measures and how its scores work.
QVHighlights is a video moment retrieval benchmark in which a model localizes the start and end times of moments relevant to a natural language query.
It measures the localization of relevant video moments using metrics such as Recall@1 at a 0.5 IoU threshold.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- QVHighlights
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about QVHighlights.
Which model scores highest on QVHighlights?
Nova 2 Lite is currently ranked first with 77.20%.
What are the top three models on QVHighlights?
The current leaders are Nova 2 Lite (77.20%), Nova 2 Omni (76.70%), and Nova 2 Pro (76.70%).
Which QVHighlights model has the lowest official input price?
Nova 2 Lite has the lowest matched official input price at $0.33 input / $2.8 output per 1M tokens.
Which models are fastest among QVHighlights results?
No matched runtime record is currently available.
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.