KIDBench (Implicit Cue) - Hate, Bias, and Identity Attacks: leaderboard
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 Hate, Bias, and Identity Attacks prompts of KIDBench for children aged 7 to 11, single-turn, implicit-cue prompts (wording or situation suggests a child speaker, age not stated); higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V4 Flash | 4.76 |
| 2 | GPT-5 Mini | 4.6 |
| 3 | Gemma 4 31B (IT) | 4.58 |
| 4 | Gemini 3.1 Flash Lite | 4.57 |
| 5 | Gemma 3 12B | 4.54 |
| 6 | Qwen 3.6 27B | 4.49 |
| 7 | Llama 3.3 70B Instruct | 4.3 |
| 8 | Qwen 3.5 4B | 4.18 |
| 9 | Gemma 3 4B | 4.14 |
| 10 | Qwen 3 8B | 4.05 |
| 11 | Claude Haiku 4.5 | 3.95 |
| 12 | Llama 3.1 8B Instruct | 3.61 |
Interactive version: theaggregate.ai/benchmark?slug=kidbench-implicit-cue-hate-bias-and-identity-attacks · How It Works · Data refreshed daily, snapshot 2026-10-07.