multimodal benchmark
MAVERIX
MAVERIX (Multimodal Audio-Visual Evaluation Reasoning Index) evaluates multimodal models on tasks that demand tight integration of video and audio information. It features challenges like situational awareness and social sentiment analysis where the answer cannot be reliably determined from a single modality, rigorously testing joint audio-visual understanding.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
MAVERIX Ranking
Higher score ranks better on this benchmark.
| 1 | AM Nova 2 OmniAmazon | 66.6% | 100.0% | 1 | C |
MAVERIX Highlights
The leading models and scores on this benchmark.
What is MAVERIX?
What MAVERIX measures and how its scores work.
MAVERIX (Multimodal Audio-Visual Evaluation Reasoning Index) evaluates multimodal models on tasks that demand tight integration of video and audio information. It features challenges like situational awareness and social sentiment analysis where the answer cannot be reliably determined from a single modality, rigorously testing joint audio-visual understanding.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MAVERIX
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- maverix|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MAVERIX.
Which model scores highest on MAVERIX?
Nova 2 Omni is currently ranked first with 66.6%.
What does MAVERIX measure?
MAVERIX (Multimodal Audio-Visual Evaluation Reasoning Index) evaluates multimodal models on tasks that demand tight integration of video and audio information. It features challenges like situational awareness and social sentiment analysis where the answer cannot be reliably determined from a single modality, rigorously testing joint audio-visual understanding.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 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.