TraceAV-Bench - Environmental Sound: leaderboard

The Environmental Sound 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 88 Environmental Sound (ES) 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 2029. 15 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 2.5 Pro65.91#280
2OmniVinci-9B65.91
3Gemini 3.1 Pro (Preview)63.64#102
4Gemini 3 Flash61.36#180
5Gemini 2.5 Flash60.23#466
6MiniCPM-o-4.559.09#1251
7Qwen 3 Omni 30B A3B59.09#851
8Ming-Flash-Omni-2.056.82#1258
9Gemini 2.0 Flash55.68#731
10Gemma 4 E4B54.55#2199
11Qwen2.5-Omni-7B52.27#1888
12HumanOmni-7B51.14#3241
13video-SALMONN 247.73#2695
14Baichuan-Omni-1.542.05#3189
15VideoLLaMA2.1-7B-AV39.77#4199

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-environmental-sound · How It Works · Data refreshed daily, snapshot 2026-11-22.