TraceAV-Bench - Visual-to-Audio Deception: leaderboard
Metric: Accuracy (%) on the 230 Visual-to-Audio Deception (V2A) questions of the multimodal hallucination dimension, four-option multiple choice over long audio-visual videos (10 to 140 minutes), exact match of the selected option set, each model at its official inference setting, with the full audio and video input; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 89.57 |
| 2 | Gemini 2.5 Pro | 79.13 |
| 3 | Gemini 3 Flash | 76.52 |
| 4 | Gemini 2.0 Flash | 74.78 |
| 5 | Gemma 4 E4B | 74.35 |
| 6 | Gemini 2.5 Flash | 60.87 |
| 7 | Qwen2.5-Omni-7B | 60.43 |
Interactive version: theaggregate.ai/benchmark?slug=traceav-bench-visual-to-audio-deception · How It Works · Data refreshed daily, snapshot 2026-10-07.