KIDBench (No Cue) - Moral Reasoning: leaderboard

KIDBench No Cue Moral Reasoning covers the 50 questions from children aged 7 to 11 in the Moral Reasoning 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 Moral Reasoning 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 2031. 13 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Llama 3.3 70B Instruct3.38#1385
2DeepSeek V4 Flash3.34#267
3Claude Haiku 4.53.04#583
4Qwen 3.6 27B2.92#351
5KIDBench Llama-3.2-3B (checkpoint unspecified)2.92
6GPT-5 Mini2.9#364
7Gemma 3 12B2.89#2059
8Llama 3.1 8B Instruct2.88#4600
9Qwen 3.5 4B2.84#1241
10Qwen 3 8B2.8#1873
11Gemini 3.1 Flash Lite2.8#371
12Gemma 4 31B (IT)2.74#350
13Gemma 3 4B2.56#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-moral-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-21.