LexRubric - Legal Consultation: leaderboard

Metric: Legal consultation (473 instances) score rate (%): points earned from expert-written atomic rubric items (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. Source: arxiv.org. Saturation forecast: Around August 2027. 18 models tracked.

Top models

#ModelScore
1Qwen 3.6 Max Preview73.17
2Kimi K2.672.84
3Qwen 3 Max71.88
4Kimi K2.570.79
5Claude Sonnet 4.670.09
6GLM-5.167.57
7Qwen 3.5 397B A17B65.85
8DeepSeek V4 Flash62.64
9GLM-560.02
10DeepSeek V4 Pro58.24
11DeepSeek R158.23
12GPT-5.257.22
13DeepSeek V3.255.96

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