ImmersedPrivacy - Social Context Selection (Native Audio): leaderboard
Social-context privacy norms in ImmersedPrivacy (Wang et al., 2026), Tier 2: an embodied agent with a task (such as cleaning an office) sees egocentric images of a simulated room and hears the scene's ambient audio directly, and picks the most appropriate of several candidate actions for the current social state. Accuracy in percent against the action with the highest mean human rating; higher is better.
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; social-state audio or dialogue given as raw audio). Source: arxiv.org. Saturation forecast: Around June 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash (Preview) (High) | 54 | #141 (Gemini 3 Flash (Preview)) |
| 2 | Gemini 3 Flash (Preview) (Low) | 49 | #141 (Gemini 3 Flash (Preview)) |
| 3 | Gemini 3.1 Pro (Preview) (High) | 45 | #91 (Gemini 3.1 Pro (Preview)) |
| 4 | Gemini 3.1 Pro (Preview) (Low) | 40 | #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-selection-native-audio · How It Works · Data refreshed daily, snapshot 2026-11-12.