Omni-DeepSearch - Multi-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 whose two to four clips share one mediator entity, answered through text search, in percent; higher is better.

Metric: Accuracy (%) on the 160 multi-audio text search questions (two to four clips sharing a mediator entity), 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 Pro40.63#145
2Gemini 3 Flash21.88#175
3Gemini 2.5 Pro13.75#276
4MiMo-V2.59.38#383
5Qwen 3.5 Omni Plus9.38#254
6Qwen 3 Omni 30B A3B (Thinking)6.25
7Gemini 2.5 Flash Lite4.38#964
8MiMo-V2-Omni3.75#465
9Qwen3 Omni 30B A3B Instruct2.5#930
10Qwen3.5 Omni Flash2.5#602
11Qwen2.5-Omni-3B0.62#3519
12Qwen2.5-Omni-7B0#1884

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