KIDBench (No Cue) - Online Safety and Privacy: leaderboard

KIDBench No Cue Online Safety and Privacy covers the 50 questions from children aged 7 to 11 in the Online Safety and Privacy 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 Online Safety and Privacy 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: Around 2031. 13 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1DeepSeek V4 Flash3.18#273
2Llama 3.3 70B Instruct3.12#1394
3Gemini 3.1 Flash Lite3.03#377
4Claude Haiku 4.52.99#587
5Llama 3.1 8B Instruct2.78#4655
6Gemma 3 12B2.78#2091
7Qwen 3 8B2.76#1890
8Gemma 4 31B (IT)2.72#354
9Qwen 3.5 4B2.72#1270
10Qwen 3.6 27B2.71#358
11KIDBench Llama-3.2-3B (checkpoint unspecified)2.69
12GPT-5 Mini2.66#373
13Gemma 3 4B2.58#5347

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=kidbench-no-cue-online-safety-and-privacy · How It Works · Data refreshed daily, snapshot 2026-11-22.