TraceAV-Bench - Audio-to-Visual Deception: leaderboard
The Audio-to-Visual Deception sub-task of TraceAV-Bench (2026), in its multimodal hallucination dimension: questions that claim a sight from what is heard in long audio-visual videos. The score is accuracy in percent with full audio and video input; higher is better.
Metric: Accuracy (%) on the 229 Audio-to-Visual Deception (A2V) 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 2.0 Flash | 81.66 | #723 |
| 2 | Gemini 3.1 Pro (Preview) | 79.91 | #99 |
| 3 | Gemini 3 Flash | 75.55 | #175 |
| 4 | Gemini 2.5 Pro | 74.24 | #276 |
| 5 | MiniCPM-o-4.5 | 72.05 | #1252 |
| 6 | Qwen 3 Omni 30B A3B | 69.87 | #847 |
| 7 | Gemma 4 E4B | 69.43 | #2184 |
| 8 | Ming-Flash-Omni-2.0 | 67.25 | #1266 |
| 9 | Gemini 2.5 Flash | 66.81 | #463 |
| 10 | Qwen2.5-Omni-7B | 55.46 | #1884 |
| 11 | OmniVinci-9B | 44.1 | |
| 12 | Baichuan-Omni-1.5 | 41.48 | #3285 |
| 13 | video-SALMONN 2 | 39.3 | #2687 |
| 14 | HumanOmni-7B | 37.99 | #3308 |
| 15 | VideoLLaMA2.1-7B-AV | 29.69 | #4204 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=traceav-bench-audio-to-visual-deception · How It Works · Data refreshed daily, snapshot 2026-11-21.