TraceAV-Bench - Multimodal Hallucination: leaderboard
The multimodal hallucination dimension of TraceAV-Bench (2026): deceptive questions that plant a false cross-modal or temporal premise in long audio-visual videos (visual-to-audio and audio-to-visual deception, temporal splicing). The score is accuracy in percent, the mean of the three sub-tasks; higher is better.
Metric: Accuracy (%), average of the three multimodal hallucination sub-tasks (625 deceptive questions), 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) | 84.61 | #102 |
| 2 | Gemini 3 Flash | 79.81 | #180 |
| 3 | Gemini 2.0 Flash | 77.85 | #731 |
| 4 | Gemini 2.5 Pro | 76.42 | #280 |
| 5 | Qwen 3 Omni 30B A3B | 67.46 | #851 |
| 6 | Ming-Flash-Omni-2.0 | 67.07 | #1258 |
| 7 | Gemma 4 E4B | 66.6 | #2199 |
| 8 | MiniCPM-o-4.5 | 66.52 | #1251 |
| 9 | Gemini 2.5 Flash | 64.85 | #466 |
| 10 | Qwen2.5-Omni-7B | 56.5 | #1888 |
| 11 | OmniVinci-9B | 42.81 | |
| 12 | video-SALMONN 2 | 40.97 | #2695 |
| 13 | HumanOmni-7B | 33.4 | #3241 |
| 14 | Baichuan-Omni-1.5 | 30.68 | #3189 |
| 15 | VideoLLaMA2.1-7B-AV | 28.26 | #4199 |
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-multimodal-hallucination · How It Works · Data refreshed daily, snapshot 2026-11-22.