TraceAV-Bench - Background Music: leaderboard

The Background Music sub-task of TraceAV-Bench (2026), part of its audio-centric reasoning dimension: multiple-choice questions over long videos whose answers chain several timestamped evidence hops. The score is accuracy in percent with full audio and video input; higher is better.

Metric: Accuracy (%) on the 131 Background Music (BM) questions, four-option multiple choice over long audio-visual videos (10 to 140 minutes), exact match of the selected option set, each model at its official inference setting, with the full audio and video input; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 15 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3.1 Pro (Preview)78.63#102
2Gemini 2.5 Pro67.18#280
3Gemini 3 Flash66.41#180
4MiniCPM-o-4.564.12#1251
5Ming-Flash-Omni-2.063.36#1258
6Gemini 2.5 Flash62.6#466
7Qwen 3 Omni 30B A3B60.31#851
8Gemini 2.0 Flash58.78#731
9Gemma 4 E4B58.02#2199
10OmniVinci-9B54.2
11Qwen2.5-Omni-7B49.62#1888
12HumanOmni-7B44.27#3241
13video-SALMONN 244.27#2695
14VideoLLaMA2.1-7B-AV35.88#4199
15Baichuan-Omni-1.533.59#3189

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=traceav-bench-background-music · How It Works · Data refreshed daily, snapshot 2026-11-22.