FMSU-Bench - Contextual Inference (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 context inferred from the vocal performance in the Chinese subset; percent, higher is better.

Metric: Accuracy (%) of identifying the context inferred from the vocal performance (CI), 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: Estimated already saturated. 10 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3.1 Pro (Preview)93.1#99
2Gemini 3 Flash86.9#175
3Gemini 2.5 Flash85.5#463
4Qwen 3 Omni 30B A3B80.1#847
5Qwen2.5-Omni-7B79.5#1884
6MiMo-Audio76.1#931
7FMSU-Bench Step-Audio 2 (checkpoint unspecified)69.4
8Audio Flamingo 365.8
9Kimi-Audio56#1735
10Qwen2-Audio (FMSU-Bench checkpoint unspecified)44.3

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-contextual-inference-chinese · How It Works · Data refreshed daily, snapshot 2026-11-21.