FMSU-Bench - Background Sound (English): leaderboard

FMSU-Bench (2026) tests fine-grained speech understanding in Chinese and English with multiple-choice questions whose distractors include subtle acoustic confusions and text-only semantic traps, plus a tagged transcription task. This board is accuracy on identifying the background sound in the English subset; percent, higher is better.

Metric: Accuracy (%) of identifying the background sound (BS), on the FMSU-Bench English subset (500 to 1,000 manually verified items per task, from audiovisual sources), multiple-choice questions whose distractors include fine-grained acoustic confusions and text-only semantic traps; higher is better. Source: arxiv.org. Saturation forecast: Around January 2028. 10 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3.1 Pro (Preview)61.4#99
2Qwen 3 Omni 30B A3B61#847
3Kimi-Audio58.5#1735
4Gemini 3 Flash55.9#175
5Gemini 2.5 Flash51.1#463
6MiMo-Audio50.3#931
7Qwen2.5-Omni-7B48.7#1884
8Audio Flamingo 348.5
9FMSU-Bench Step-Audio 2 (checkpoint unspecified)36.8
10Qwen2-Audio (FMSU-Bench checkpoint unspecified)20.9

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

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