HUSH-Bench (Full Context): 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; the full fixed-budget history is in context. Source: arxiv.org. Saturation forecast: Around August 2027. 4 models tracked.

Top models

#ModelScore
1GPT-5.4 Mini11.2
2Claude Sonnet 4.670.9
3Qwen 3.5 9B82.2
4DeepSeek V4 Flash83

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