When Context Flips, Safety Breaks — leaderboard

Metric: PacifAIst BSR (self-reported). Source: benchmarklist.com. 12 models tracked.

Top models

#ModelScore
1Llama 3.1 8B77.6
2Claude Sonnet 4.643.8
3Llama 3.3 70B Instruct38
4Mistral Small 3.135.9
5DeepSeek V3.135.9
6phi-4-14B35.9
7Gemma 3 27B27.8
8GPT-5.422.8
9Grok 4.2018.2
10Gemini 3.1 Pro (Preview)17.2
11Qwen 3 32B16.2

Interactive version: theaggregate.ai/benchmark?slug=when-context-flips-safety-breaks · How the rankings work · Data refreshed daily, snapshot 2026-07-22.