HalluAudio - Environmental Sound: leaderboard
Hallucination detection in the environmental sound domain of HalluAudio (2026): human-verified audio question-answer pairs with adversarial prompts, mixed audio and unanswerable questions probe whether an audio-language model reports sounds or content that are not there. Unweighted mean accuracy over seven task types, in percent; higher is better.
Metric: Average classification accuracy (%) over the seven environmental sound task types of HalluAudio (human-verified audio question-answer pairs with adversarial, mixed-audio and unanswerable prompts; zero-shot; outputs normalized to labels, refusals counted wrong); unweighted mean of the task accuracies; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 9 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen2.5-Omni-7B | 84.69 | #1884 |
| 2 | MiMo-Audio-7B-Instruct | 82.52 | #1336 |
| 3 | Step-Audio-2-mini | 72.64 | |
| 4 | GPT-4o Audio (Preview) | 71 | #793 |
| 5 | Qwen2-Audio-7B | 67.36 | |
| 6 | Audio Flamingo 3 | 64.79 | |
| 7 | Gemini 2.5 Flash | 39.35 | #463 |
| 8 | Kimi-Audio-7B | 38.76 | |
| 9 | Pengi | 24.69 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=halluaudio-environmental-sound · How It Works · Data refreshed daily, snapshot 2026-11-21.