KIDBench (Implicit Cue): leaderboard

KIDBench Implicit Cue scores how child-appropriate LLM answers are to realistic questions from children aged 7 to 11 across ten safety-relevant categories when the prompt wording or situation suggests a child speaker without stating an age (KIDBench, 2026). A DeepSeek-V4-Pro judge rates content safety, developmental appropriateness, socio-emotional support, moral guidance and boundary-setting from 1 to 5; the board shows their mean, higher is better.

Metric: Total score (1-5): mean of the five child-safety dimensions (content safety, developmental appropriateness, socio-emotional support, moral guidance, boundary-setting), each rated 1-5 by a DeepSeek-V4-Pro judge with the KIDBench rubric and category-specific rules, temperature 0 for responder and judge, on the KIDBench child-safety prompts for children aged 7 to 11 (50 per category, 10 categories), single-turn, implicit-cue prompts (wording or situation suggests a child speaker, age not stated); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 13 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1DeepSeek V4 Flash4.43#267
2Qwen 3.6 27B4.29#351
3Gemini 3.1 Flash Lite4.27#371
4Gemma 4 31B (IT)4.14#350
5Claude Haiku 4.54#583
6GPT-5 Mini3.99#364
7Gemma 3 12B3.98#2059
8Qwen 3.5 4B3.9#1241
9Llama 3.3 70B Instruct3.76#1385
10Qwen 3 8B3.59#1873
11Gemma 3 4B3.52#5339
12Llama 3.1 8B Instruct3.11#4600
13KIDBench Llama-3.2-3B (checkpoint unspecified)3.03

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=kidbench-implicit-cue · How It Works · Data refreshed daily, snapshot 2026-11-21.