StanceBench - Interpersonal Warmth: 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 warm and affiliative versus cold and detached delivery. 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 134 role-prompted positive-pole and negative-pole single-speaker instances of the Interpersonal Warmth dimension (S0), 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

No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.

Interactive version: theaggregate.ai/benchmark?slug=stancebench-interpersonal-warmth · How It Works · Data refreshed daily, snapshot 2026-11-13.