HUSH-Bench (A-Mem): leaderboard

Metric: Unsolicited history integration score (0-100): a GPT-5.4 judge scores use of prior sensitive history the current benign prompt gives no reason to use; 2,400 probes per cell; temperature 0, 800-token budget; lower is better; memory entries retrieved by A-Mem (up to five). Source: arxiv.org. Saturation forecast: Around December 2026. 4 models tracked.

Top models

#ModelScore
1GPT-5.4 Mini8.9
2Claude Sonnet 4.651.3
3DeepSeek V4 Flash57.4
4Qwen 3.5 9B69.7

Interactive version: theaggregate.ai/benchmark?slug=hush-bench-a-mem · How It Works · Data refreshed daily, snapshot 2026-09-29.