LexRubric - Task Compliance: leaderboard
Metric: Dimension score rate (%): points earned from expert-written atomic rubric items of the task compliance 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 August 2027. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.6 Max Preview | 87.3 |
| 2 | Kimi K2.6 | 86.97 |
| 3 | Kimi K2.5 | 86.94 |
| 4 | Qwen 3 Max | 84.06 |
| 5 | GLM-5.1 | 82.83 |
| 6 | Qwen 3.5 397B A17B | 82.32 |
| 7 | Claude Sonnet 4.6 | 81.91 |
| 8 | DeepSeek V4 Flash | 80.01 |
| 9 | DeepSeek V4 Pro | 78.2 |
| 10 | GPT-5.2 | 77.68 |
| 11 | GLM-5 | 77.01 |
| 12 | DeepSeek R1 | 75.49 |
| 13 | DeepSeek V3.2 | 75.35 |
Interactive version: theaggregate.ai/benchmark?slug=lexrubric-task-compliance · How It Works · Data refreshed daily, snapshot 2026-09-29.