KIDBench (No Cue, Urdu): leaderboard

KIDBench No Cue Urdu asks the 500 KIDBench child-safety questions, translated into Urdu and without any sign that the user is a child, and has the model answer in Urdu (KIDBench, 2026). A DeepSeek-V4-Pro judge rates five child-safety dimensions from 1 to 5; the board shows their mean, higher is better.

Metric: Total 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, on the 500 no-cue KIDBench prompts translated into Urdu by GPT-5.5 (system instruction sets the response language), averaged over the 10 categories, single-turn; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 13 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemma 4 31B (IT)3.34#350
2Qwen 3.6 27B3.27#351
3DeepSeek V4 Flash3.26#267
4Gemini 3.1 Flash Lite3.25#371
5Claude Haiku 4.53.18#583
6Gemma 3 12B3.02#2059
7GPT-5 Mini2.9#364
8Qwen 3.5 4B2.7#1241
9Llama 3.3 70B Instruct2.63#1385
10Gemma 3 4B2.33#5339
11Qwen 3 8B2.23#1873
12Llama 3.1 8B Instruct1.61#4600
13KIDBench Llama-3.2-3B (checkpoint unspecified)1.27

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-urdu · How It Works · Data refreshed daily, snapshot 2026-11-21.