KIDBench (No Cue) - Socio-emotional Support: leaderboard

KIDBench No Cue Socio-emotional Support rates whether an LLM answer to a child aged 7 to 11 keeps a supportive, non-shaming tone, when the prompts give no sign that the user is a child (KIDBench, 2026). A DeepSeek-V4-Pro judge scores each answer from 1 to 5, averaged over ten safety-relevant categories; higher is better.

Metric: Socio-emotional Support score (1-5): whether the response keeps a supportive, non-shaming tone, 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, 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#267
2Llama 3.3 70B Instruct3.11#1385
3Qwen 3.6 27B2.97#351
4GPT-5 Mini2.91#364
5Claude Haiku 4.52.85#583
6Gemma 3 4B2.84#5339
7Gemma 3 12B2.83#2059
8Qwen 3 8B2.75#1873
9Gemini 3.1 Flash Lite2.73#371
10KIDBench Llama-3.2-3B (checkpoint unspecified)2.71
11Llama 3.1 8B Instruct2.66#4600
12Qwen 3.5 4B2.66#1241
13Gemma 4 31B (IT)2.47#350

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-socio-emotional-support · How It Works · Data refreshed daily, snapshot 2026-11-21.