Omni-DeepSearch - Speech: 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 speech, in percent; higher is better.
Metric: Accuracy (%) on the 120 single-audio questions whose clip is speech, 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
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro | 55 | #145 |
| 2 | Gemini 2.5 Pro | 25 | #276 |
| 3 | Gemini 3 Flash | 20 | #175 |
| 4 | MiMo-V2.5 | 15.83 | #383 |
| 5 | Qwen 3.5 Omni Plus | 14.17 | #254 |
| 6 | MiMo-V2-Omni | 10.83 | #465 |
| 7 | Qwen 3 Omni 30B A3B (Thinking) | 5.83 | |
| 8 | Gemini 2.5 Flash Lite | 4.17 | #964 |
| 9 | Qwen3.5 Omni Flash | 4.17 | #602 |
| 10 | Qwen2.5-Omni-7B | 1.67 | #1884 |
| 11 | Qwen3 Omni 30B A3B Instruct | 1.67 | #930 |
| 12 | Qwen2.5-Omni-3B | 0 | #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-speech · How It Works · Data refreshed daily, snapshot 2026-11-21.