ImmersedPrivacy - Social Context Rating Error (Native Audio): leaderboard

Metric: Mean absolute error (Tier 2: the model's 1-5 appropriateness rating of each candidate action against the mean human rating; social-state audio or dialogue given as raw audio; lower is better). Source: arxiv.org. Saturation forecast: Around May 2028. 6 models tracked.

Top models

#ModelScore
1Gemini 3 Flash (Preview) (High)1.35
2Gemini 3 Flash (Preview) (Low)1.41
3Gemini 3.1 Pro (Preview) (High)1.74
4Gemini 3.1 Pro (Preview) (Low)1.78

Interactive version: theaggregate.ai/benchmark?slug=immersedprivacy-social-context-rating-error-native-audio · How It Works · Data refreshed daily, snapshot 2026-09-26.