KIDBench (Implicit Cue) - Socio-emotional Support: leaderboard
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, implicit-cue prompts (wording or situation suggests a child speaker, age not stated); higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V4 Flash | 4.55 |
| 2 | Qwen 3.6 27B | 4.41 |
| 3 | Gemini 3.1 Flash Lite | 4.38 |
| 4 | Gemma 3 12B | 4.28 |
| 5 | Gemma 4 31B (IT) | 4.17 |
| 6 | GPT-5 Mini | 4.1 |
| 7 | Gemma 3 4B | 4.09 |
| 8 | Claude Haiku 4.5 | 4.08 |
| 9 | Qwen 3.5 4B | 4.03 |
| 10 | Llama 3.3 70B Instruct | 3.93 |
| 11 | Qwen 3 8B | 3.92 |
| 12 | Llama 3.1 8B Instruct | 3.14 |
Interactive version: theaggregate.ai/benchmark?slug=kidbench-implicit-cue-socio-emotional-support · How It Works · Data refreshed daily, snapshot 2026-10-07.