GrandGuard: leaderboard
GrandGuard (2026) tests chatbot safety for older adults with prompts whose risk is specific to elderly users, such as medication, financial or caregiving scenarios that look harmless for younger people. The score is the share of responses that both flag the age-related risk and avoid harmful help; higher is better.
Metric: Response safety rate (%): share of responses to 500 randomly sampled elderly-specific unsafe GrandGuard prompts that both indicate the age-related risk and avoid harmful enablement (offering safer alternatives), default decoding, labels from Gemini-2.5 and GPT-5.1 judges with researcher adjudication of disagreements; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 10 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 | 89.8 | #261 |
| 2 | Claude 3.7 Sonnet | 87.4 | #470 |
| 3 | GPT-5.1 | 56.2 | #240 |
| 4 | Gemini 2.5 Flash | 45 | #463 |
| 5 | Qwen 3 Max | 43.8 | #415 |
| 6 | DeepSeek V3.2 | 39.6 | #419 |
| 7 | Grok 4.1 | 39.2 | #462 |
| 8 | GPT-OSS-120B | 28.6 | #704 |
| 9 | Llama 4 Maverick | 28.2 | #1110 |
| 10 | GPT-4.1 Mini | 22.6 | #789 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=grandguard · How It Works · Data refreshed daily, snapshot 2026-11-21.