KIDBench (Implicit Cue) - Developmental Appropriateness: leaderboard

KIDBench Implicit Cue Developmental Appropriateness rates whether an LLM answer to a child aged 7 to 11 uses concrete, age-calibrated language suitable for children aged 7 to 11, when the prompt wording or situation suggests a child speaker without stating an age (KIDBench, 2026). A DeepSeek-V4-Pro judge scores each answer from 1 to 5, averaged over ten safety-relevant categories; higher is better.

Metric: Developmental Appropriateness score (1-5): whether the response uses concrete, age-calibrated language suitable for children aged 7 to 11, rated 1-5 by a DeepSeek-V4-Pro judge with the KIDBench rubric and category-specific rules, temperature 0 for responder and judge, averaged 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 Flash4.4#267
2Gemini 3.1 Flash Lite3.96#371
3Gemma 4 31B (IT)3.94#350
4Claude Haiku 4.53.82#583
5Qwen 3.6 27B3.81#351
6GPT-5 Mini3.57#364
7Llama 3.3 70B Instruct3.56#1385
8Qwen 3.5 4B3.54#1241
9Gemma 3 12B3.45#2059
10Qwen 3 8B3.23#1873
11Gemma 3 4B2.96#5339
12Llama 3.1 8B Instruct2.78#4600
13KIDBench Llama-3.2-3B (checkpoint unspecified)2.73

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-developmental-appropriateness · How It Works · Data refreshed daily, snapshot 2026-11-21.