Omni-DeepSearch - Music: 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 music, in percent; higher is better.

Metric: Accuracy (%) on the 120 single-audio questions whose clip is music, 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 Pro46.67#145
2Gemini 3 Flash18.33#175
3Gemini 2.5 Pro15.83#276
4Qwen 3.5 Omni Plus15.83#254
5MiMo-V2-Omni8.33#465
6Qwen 3 Omni 30B A3B (Thinking)7.5
7MiMo-V2.56.67#383
8Qwen3 Omni 30B A3B Instruct5#930
9Qwen3.5 Omni Flash4.17#602
10Qwen2.5-Omni-3B0.83#3519
11Gemini 2.5 Flash Lite0#964
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-music · How It Works · Data refreshed daily, snapshot 2026-11-21.