SpeechParaling-Bench (Chinese): leaderboard

SpeechParaling-Bench (2026) tests paralinguistic-aware speech generation by audio-language models; a Gemini 3 Pro judge compares each spoken response with the response of a fixed baseline model, ties counting half, and the baseline itself scores its strength-weighted result against the others. This board covers all three tasks of the Chinese subset against the Doubao Realtime Voice baseline. Pairwise score in percent; higher is better.

Metric: Pairwise score (%) on all three tasks (paralanguage control, dynamic variation and situational adaptation), Chinese subset: a Gemini 3 Pro judge compares each spoken response with the fixed baseline's (Doubao Realtime Voice; ties count half), and the baseline's own row is its strength-weighted average against the candidates (the paper's Eq. 3); higher is better. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 5 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Doubao Realtime Voice Model70.84
2GPT-Audio (2025-08-28)39.09
3Gemini 2.5 Flash Audio28.18
4Qwen3-Omni-Flash-2025-12-0122.58
5Qwen3 Omni Realtime14.34

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