StanceBench - Power Orientation: leaderboard
StanceBench tests whether audio-capable models can read interpersonal stance from conversational speech: for each stance dimension, speakers were role-prompted toward a positive or a negative pole, and the judge must tell them apart from the audio. This board covers accommodating versus dominating behaviour toward the partner. The score is the area under the ROC curve of the signed stance score the judge gives, against the role-derived poles, so 0.5 is chance.
Metric: AUROC (0-1 scale) of the judge's conversation-level signed stance score in separating the 233 role-prompted positive-pole and negative-pole interaction (target plus partner context) instances of the Power Orientation dimension (S7), 25 percent sample of the Seamless Interaction Improvised subset; binary pole choice asked in both pole orders, malformed outputs dropped. Source: arxiv.org. Saturation forecast: Around February 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Flash (Thinking) | 0.86 | #453 (Gemini 2.5 Flash) |
| 2 | Qwen2.5-Omni-7B | 0.56 | #1789 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=stancebench-power-orientation · How It Works · Data refreshed daily, snapshot 2026-11-13.