ParaPairAudioBench - Gender: leaderboard
ParaPairAudioBench (Jeon et al., Interspeech 2026) tests audio language models as pairwise judges: given two recordings and a speech-generation instruction, the model picks the one that fulfils it better or declares a tie, and accuracy in percent is averaged over both presentation orders; higher is better. This board is 1,000 Sonos Voice Control and LibriTTS pairs judged on sounding like a requested gender, with ties allowed, so chance is one third.
Metric: Pairwise judgment accuracy (%; mean of both A/B orders; A better, B better or tie; 1,000 Sonos and LibriTTS pairs, target gender). Source: arxiv.org. Saturation forecast: Around February 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Flash | 64.2 | #452 |
| 2 | Qwen2.5-Omni-7B | 47.4 | #1797 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=parapairaudiobench-gender · How It Works · Data refreshed daily, snapshot 2026-11-12.