TraceAV-Bench - Visual-to-Audio Deception: leaderboard
The Visual-to-Audio Deception sub-task of TraceAV-Bench (2026), in its multimodal hallucination dimension: questions that claim a sound from what is seen in long audio-visual videos. The score is accuracy in percent with full audio and video input; higher is better.
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 February 2027. 15 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 89.57 | #102 |
| 2 | Gemini 2.5 Pro | 79.13 | #280 |
| 3 | Gemini 3 Flash | 76.52 | #180 |
| 4 | Gemini 2.0 Flash | 74.78 | #731 |
| 5 | Gemma 4 E4B | 74.35 | #2199 |
| 6 | Ming-Flash-Omni-2.0 | 71.3 | #1258 |
| 7 | MiniCPM-o-4.5 | 70.87 | #1251 |
| 8 | Qwen 3 Omni 30B A3B | 65.65 | #851 |
| 9 | Gemini 2.5 Flash | 60.87 | #466 |
| 10 | Qwen2.5-Omni-7B | 60.43 | #1888 |
| 11 | video-SALMONN 2 | 45.65 | #2695 |
| 12 | OmniVinci-9B | 42.17 | |
| 13 | VideoLLaMA2.1-7B-AV | 35.22 | #4199 |
| 14 | HumanOmni-7B | 33.91 | #3241 |
| 15 | Baichuan-Omni-1.5 | 28.26 | #3189 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=traceav-bench-visual-to-audio-deception · How It Works · Data refreshed daily, snapshot 2026-11-22.