StyleBench (Speaking Style) - Volume (Turn 2): leaderboard
Metric: Valid sample percentage (%): share of the 160 volume test dialogues whose turn-2 response shows the distinct, intended change in RMS energy of the waveform, in three-turn spoken dialogues of StyleBench's 10% evaluation split, a neutral first turn followed by two conversational instructions that strengthen or weaken the style; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen2.5-Omni-7B | 46.25 | #601 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=stylebench-speaking-style-volume-turn-2 · How It Works · Data refreshed daily, snapshot 2026-10-11.