MusTBENCH - Transition-Aware Description: leaderboard

MusTBench (2026) tests temporal grounding of audio-language models in full-length music tracks, zero-shot. Transition-aware description: describe in free text the musical change around a given timestamp. Mean of METEOR against the reference and CLAP audio-text similarity, both times 100 (range -50 to 100); higher is better.

Metric: Transition-Aware Description (TAD, 208 questions): the model describes the musical change around a given timestamp in free text; score is the mean of METEOR against the reference description and CLAP score (cosine similarity of the 20-second transition clip and the generated text), both times 100: METEOR spans 0 to 100 and CLAP -100 to 100, so the mean spans -50 to 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 2031. 12 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3 Flash24.3#175
2Gemini 2.5 Pro24.1#276
3GPT-Audio 1.523.6#501
4Music Flamingo23.4#866
5Gemini 2.5 Flash22.9#463
6GPT-Audio22.5#607
7Qwen2.5-Omni-3B22.3#3519
8Qwen2.5-Omni-7B21.5#1884
9Gemini 3 Pro19.8#145
10AF-Next19.2
11Phi-4 Multimodal Instruct16.3#4154
12Qwen 3 Omni 30B A3B16#847

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=mustbench-transition-aware-description · How It Works · Data refreshed daily, snapshot 2026-11-21.