Omni-DeepSearch - Single-Audio Text Search: 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 160 questions answered from one clip through multi-hop text search, in percent; higher is better.

Metric: Accuracy (%) on the 160 single-audio text search questions (one clip, multi-hop Wikipedia knowledge-graph paths), 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 Pro57.5#145
2Gemini 3 Flash26.88#175
3Gemini 2.5 Pro20.62#276
4Qwen 3.5 Omni Plus20#254
5MiMo-V2.515#383
6MiMo-V2-Omni14.38#465
7Qwen 3 Omni 30B A3B (Thinking)9.38
8Qwen3 Omni 30B A3B Instruct6.88#930
9Qwen3.5 Omni Flash6.25#602
10Qwen2.5-Omni-7B1.88#1884
11Gemini 2.5 Flash Lite1.25#964
12Qwen2.5-Omni-3B1.25#3519

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-single-audio-text-search · How It Works · Data refreshed daily, snapshot 2026-11-21.