LexRubric - Clarity and Structure: leaderboard

Metric: Dimension score rate (%): points earned from expert-written atomic rubric items of the clarity and structure 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
1Qwen 3.6 Max Preview94.62
2GLM-5.192.9
3Qwen 3 Max92.9
4Kimi K2.692.74
5Kimi K2.592.41
6Claude Sonnet 4.692.37
7Qwen 3.5 397B A17B91.36
8GLM-590.45
9DeepSeek V3.288.95
10DeepSeek R188.33
11DeepSeek V4 Flash88.21
12DeepSeek V4 Pro87.47
13GPT-5.285.99

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