KIDBench (No Cue) - Self-harm and Mental Health: leaderboard
KIDBench No Cue Self-harm and Mental Health covers the 50 questions from children aged 7 to 11 in the Self-harm and Mental Health category of KIDBench (2026), asked so that the prompts give no sign that the user is a child. A DeepSeek-V4-Pro judge rates each answer on five child-safety dimensions from 1 to 5; the board shows their mean, higher is better.
Metric: Category score (1-5): mean of the five child-safety dimensions, each rated 1-5 by a DeepSeek-V4-Pro judge with the KIDBench rubric and category-specific rules, temperature 0 for responder and judge, over the 50 Self-harm and Mental Health prompts of KIDBench for children aged 7 to 11, single-turn, no-cue prompts (no sign that the user is a child); higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 13 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.6 27B | 2.66 | #351 |
| 2 | Llama 3.3 70B Instruct | 2.62 | #1385 |
| 3 | Qwen 3 8B | 2.6 | #1873 |
| 4 | DeepSeek V4 Flash | 2.59 | #267 |
| 5 | Llama 3.1 8B Instruct | 2.56 | #4600 |
| 6 | GPT-5 Mini | 2.56 | #364 |
| 7 | Qwen 3.5 4B | 2.53 | #1241 |
| 8 | KIDBench Llama-3.2-3B (checkpoint unspecified) | 2.52 | |
| 9 | Gemini 3.1 Flash Lite | 2.42 | #371 |
| 10 | Claude Haiku 4.5 | 2.37 | #583 |
| 11 | Gemma 3 4B | 2.3 | #5339 |
| 12 | Gemma 4 31B (IT) | 2.22 | #350 |
| 13 | Gemma 3 12B | 2.08 | #2059 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=kidbench-no-cue-self-harm-and-mental-health · How It Works · Data refreshed daily, snapshot 2026-11-21.