LexRubric - Ethics and Safety: leaderboard

Metric: Dimension score rate (%): points earned from expert-written atomic rubric items of the ethics and safety dimension (weighted -10 to +10; negative items subtract) divided by the maximum positive score, averaged over instances; a Qwen3.6-27B judge checks each item, temperature 0.6, 16k output tokens; can fall below 0; higher is better (instances without a positive item in the dimension are left out). Source: arxiv.org. Saturation forecast: Around September 2027. 18 models tracked.

Top models

#ModelScore
1Claude Sonnet 4.672.74
2Qwen 3 Max69.64
3DeepSeek V3.261.16
4Qwen 3.6 Max Preview59.82
5Qwen 3.5 397B A17B56.67
6DeepSeek V4 Flash54.72
7Kimi K2.642.55
8Kimi K2.540.86
9DeepSeek R140.64
10GPT-5.234.7
11DeepSeek V4 Pro27.59
12GLM-5.126.84
13GLM-522.03

Interactive version: theaggregate.ai/benchmark?slug=lexrubric-ethics-and-safety · How It Works · Data refreshed daily, snapshot 2026-09-29.