DialBGM: leaderboard

Background music selection for conversations on DialBGM (2026): for each of 1,200 everyday multi-turn dialogues the model listens to four candidate music clips and scores their fit as background music, and its top choice is compared with the clip human annotators ranked first. Full dialogue as input; Hit@1 in percent (chance 25), higher is better.

Metric: Hit@1 (%, times 100): share of dialogues where the model's top-scored clip is the human rank-1 clip (chance 25), with the full dialogue as input, on DialBGM, 1,200 everyday multi-turn dialogues each paired with four candidate music clips ranked by human annotators for suitability as background music, the model scoring each audio clip; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 7 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 2.5 Flash32.93#463
2Gemini 2.5 Pro32.33#276
3Qwen2.5-Omni31.37#1588
4GPT-Audio30.51#607
5Audio Flamingo26.51
6Music Flamingo25.96#866
7Phi-4 Multimodal Instruct25.06#4154

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

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