The Age of Curiosity Meets the Age of AI: Benc: leaderboard
Children increasingly have access to Large Language Models (LLMs), which may expose them to responses that are developmentally inappropriate or require age-sensitive safety, guidance, and boundaries. Existing LLM safety evaluations largely focus on harmful-content avoidance and do not explicitly target child-facing safety. We introduce KIDBench, a benchmark for evaluating child-facing LLM safety f
Metric: Total (self-reported). Source: benchmarklist.com. Saturation forecast: Around April 2027. 13 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.6 27B | 4.98 | #170 |
| 2 | GPT-5 Mini | 4.87 | #186 |
| 3 | DeepSeek V4 Flash | 4.87 | #137 |
| 4 | Gemini 3.1 Flash Lite | 4.87 | #191 |
| 5 | Gemma 4 31B | 4.85 | #200 |
| 6 | Gemma 3 12B | 4.83 | #671 |
| 7 | Claude Haiku 4.5 | 4.76 | #280 |
| 8 | Qwen 3 8B | 4.68 | #674 |
| 9 | Qwen 3.5 4B | 4.61 | #475 |
| 10 | Llama 3.3 70B | 4.59 | #579 |
| 11 | Gemma 3 4B | 4.4 | #1089 |
| 12 | Llama 3.1 8B | 4.01 | #1151 |
| 13 | Llama 3.2 3B | 3.87 | #1396 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=the-age-of-curiosity-meets-the-age-of-ai-benc · How It Works · Data refreshed daily, snapshot 2026-10-20.