FMSU-Bench - Age (Chinese): 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 perceived age group of the speaker in the Chinese subset; percent, higher is better.

Metric: Accuracy (%) of identifying the perceived age group of the speaker (AGE), on the FMSU-Bench Chinese 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 2029. 10 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Qwen 3 Omni 30B A3B70.4#851
2Gemini 3 Flash63.3#180
3Gemini 3.1 Pro (Preview)62.4#102
4Qwen2.5-Omni-7B61#1888
5MiMo-Audio59.9#934
6Gemini 2.5 Flash53.4#466
7Kimi-Audio42.4#1722
8FMSU-Bench Step-Audio 2 (checkpoint unspecified)42.4
9Audio Flamingo 341.6
10Qwen2-Audio (FMSU-Bench checkpoint unspecified)15.3

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

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