MusTBENCH - Temporal Source Grounding: leaderboard
MusTBench (2026) tests temporal grounding of audio-language models in full-length music tracks, zero-shot. Temporal source grounding: give the time at which a named instrument or the vocals first start or last stop. Mean of onset and offset hit rates within 3 seconds, in percent; higher is better.
Metric: Temporal Source Grounding (TSG, 400 questions): the model gives the time at which a named instrument or the vocals first start or last stop; score is the mean of onset and offset Hit@3s, the share of predicted timestamps within 3 seconds of the ground truth (%, 0-100), on the MusTBench test set (full-length MTG-Jamendo and Slakh2100 tracks, music-expert-validated questions), zero-shot with the full track and a task instruction, temperature 0, unparseable timestamps and intervals counted wrong; 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 2.5 Flash | 65.8 | #463 |
| 2 | Gemini 2.5 Pro | 57.3 | #276 |
| 3 | Gemini 3 Pro | 52.3 | #145 |
| 4 | Gemini 3 Flash | 48.8 | #175 |
| 5 | Music Flamingo | 38.5 | #866 |
| 6 | Qwen 3 Omni 30B A3B | 36 | #847 |
| 7 | Qwen2.5-Omni-7B | 21.3 | #1884 |
| 8 | GPT-Audio | 11.5 | #607 |
| 9 | AF-Next | 10 | |
| 10 | GPT-Audio 1.5 | 8.8 | #501 |
| 11 | Phi-4 Multimodal Instruct | 7.3 | #4154 |
| 12 | Qwen2.5-Omni-3B | 4.8 | #3519 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=mustbench-temporal-source-grounding · How It Works · Data refreshed daily, snapshot 2026-11-21.