KIDBench (No Cue) - Family, Peers, and Relationships: leaderboard

KIDBench No Cue Family, Peers, and Relationships covers the 50 questions from children aged 7 to 11 in the Family, Peers, and Relationships 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 Family, Peers, and Relationships 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 2029. 13 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1DeepSeek V4 Flash3.59#267
2Llama 3.3 70B Instruct3.54#1385
3Qwen 3.6 27B3.36#351
4Claude Haiku 4.53.34#583
5Gemini 3.1 Flash Lite3.13#371
6Qwen 3 8B3.12#1873
7Llama 3.1 8B Instruct3.1#4600
8Gemma 4 31B (IT)3.03#350
9GPT-5 Mini3.01#364
10KIDBench Llama-3.2-3B (checkpoint unspecified)2.94
11Gemma 3 12B2.92#2059
12Qwen 3.5 4B2.83#1241
13Gemma 3 4B2.73#5339

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-family-peers-and-relationships · How It Works · Data refreshed daily, snapshot 2026-11-21.