MusTBENCH - Local Transition Recognition: leaderboard
MusTBench (2026) tests temporal grounding of audio-language models in full-length music tracks, zero-shot. Local transition recognition: pick the description of the musical transition at a given timestamp, with distractors from other transitions of the same song. Accuracy in percent; higher is better.
Metric: Local Transition Recognition (LTR, 208 questions): multiple-choice accuracy (%) at picking the description of the musical transition at a given timestamp, with distractors from other transitions of the same song, 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 Pro | 62.5 | #276 |
| 2 | Gemini 2.5 Flash | 56.7 | #463 |
| 3 | Music Flamingo | 56.3 | #866 |
| 4 | Gemini 3 Pro | 54.3 | #145 |
| 5 | Qwen 3 Omni 30B A3B | 53.4 | #847 |
| 6 | Gemini 3 Flash | 51.4 | #175 |
| 7 | GPT-Audio 1.5 | 51 | #501 |
| 8 | Qwen2.5-Omni-7B | 45.7 | #1884 |
| 9 | AF-Next | 44.7 | |
| 10 | GPT-Audio | 42.3 | #607 |
| 11 | Qwen2.5-Omni-3B | 32.7 | #3519 |
| 12 | Phi-4 Multimodal Instruct | 28.4 | #4154 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=mustbench-local-transition-recognition · How It Works · Data refreshed daily, snapshot 2026-11-21.