LexRubric - Reasoning and Logic: leaderboard

Metric: Dimension score rate (%): points earned from expert-written atomic rubric items of the reasoning and logic 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
1Kimi K2.679.08
2Qwen 3.6 Max Preview77.14
3Qwen 3 Max77.07
4Kimi K2.576.5
5GLM-5.174.72
6Claude Sonnet 4.672.24
7Qwen 3.5 397B A17B72.17
8GLM-568.24
9DeepSeek V4 Pro65.86
10DeepSeek V4 Flash65.71
11GPT-5.263.87
12DeepSeek R162.43
13DeepSeek V3.261.36

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