ImmersedPrivacy - Social Context Rating Error (Native Audio): leaderboard
Social-context privacy norms in ImmersedPrivacy (Wang et al., 2026), Tier 2 rating mode: the agent sees egocentric images of a simulated room, hears the scene's ambient audio directly, and rates each candidate action's appropriateness for the current social state on a 1-5 scale. Mean absolute error against the mean human rating (0-4); lower is better.
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 February 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash (Preview) (High) | 1.35 | #141 (Gemini 3 Flash (Preview)) |
| 2 | Gemini 3 Flash (Preview) (Low) | 1.41 | #141 (Gemini 3 Flash (Preview)) |
| 3 | Gemini 3.1 Pro (Preview) (High) | 1.74 | #91 (Gemini 3.1 Pro (Preview)) |
| 4 | Gemini 3.1 Pro (Preview) (Low) | 1.78 | #91 (Gemini 3.1 Pro (Preview)) |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=immersedprivacy-social-context-rating-error-native-audio · How It Works · Data refreshed daily, snapshot 2026-11-12.