AgentSocialBench - Information Abstraction: leaderboard
Metric: Information Abstraction Score (0-1; 0, 0.5 or 1 per cross-boundary message for no, partial or full use of an acceptable abstraction) averaged over scenarios, under the L0 (unconstrained) privacy instruction level, judged by Claude Opus 4.6; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.6 | 0.85 |
| 2 | Claude Sonnet 4.5 | 0.79 |
| 3 | DeepSeek V3.2 | 0.76 |
| 4 | GPT-5 Mini | 0.75 |
| 5 | Claude Haiku 4.5 | 0.75 |
| 6 | Qwen 3 235B A22B | 0.75 |
| 7 | MiniMax-M2.1 | 0.75 |
| 8 | Kimi K2.5 | 0.69 |
Interactive version: theaggregate.ai/benchmark?slug=agentsocialbench-information-abstraction · How It Works · Data refreshed daily, snapshot 2026-10-07.