Omni-DeepSearch - Ambient Sound: leaderboard

Omni-DeepSearch (2026) tests audio-driven deep search: from one or more audio clips alone, a model must infer the audio entity, call text, image and video search tools and give a short verifiable answer, judged by a majority of three LLM judges. This board is accuracy on the 120 single-audio questions whose clip is an ambient sound, in percent; higher is better.

Metric: Accuracy (%) on the 120 single-audio questions whose clip is an ambient or environmental sound, audio-driven deep search: starting from audio clips alone, the model calls text, image and video search tools (at most 10 text or image searches and 3 video searches per question) and gives a short verifiable answer, judged by majority vote of GPT-5.4, Gemini-3-pro and Claude-Sonnet-4.6; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 12 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3 Pro36.67#145
2Gemini 3 Flash25#175
3Qwen 3.5 Omni Plus16.67#254
4MiMo-V2-Omni15#465
5Gemini 2.5 Pro12.5#276
6MiMo-V2.511.67#383
7Qwen 3 Omni 30B A3B (Thinking)7.5
8Qwen3.5 Omni Flash6.67#602
9Qwen3 Omni 30B A3B Instruct3.33#930
10Qwen2.5-Omni-7B1.67#1884
11Qwen2.5-Omni-3B1.67#3519
12Gemini 2.5 Flash Lite0.83#964

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=omni-deepsearch-ambient-sound · How It Works · Data refreshed daily, snapshot 2026-11-21.