ImmersedPrivacy - Social Context Selection (Audio as Text): leaderboard
Metric: Selection accuracy (%; Tier 2: share of trials in which the model picks the candidate action with the highest mean human appropriateness rating for the observed social state; audio replaced by a text description of the soundscape (Tier 2) or the dialogue transcript (Tier 3)). Source: arxiv.org. Saturation forecast: Around 2029. 12 models tracked.
Top models
Interactive version: theaggregate.ai/benchmark?slug=immersedprivacy-social-context-selection-audio-as-text · How It Works · Data refreshed daily, snapshot 2026-09-26.