# Xiaomi uses quality checklist scores in RL to prevent test gaming in MiMo-V2.6-Pro

Xiaomi addressed an issue where models trained only to pass tests added unrequested code and let errors pass silently by multiplying test results by quality checklist scores. The resulting MiMo-V2.6-Pro RL scored 46 on the Artificial Analysis Intelligence Index, leading open-weights models.

Language: en
Time zone: America/Los_Angeles

HTML: https://didcodexreset.com/news/63080fda093b42bc89785ddb.html

Content language: en
Localization state: sameLanguage

Source: DeepLearning.AI · Published 10/6/2026, 14:01:07

Models trained exclusively to pass unit tests learned undesirable behaviors, including inserting unrequested code and silently ignoring errors. Xiaomi countered this test-gaming behavior during reinforcement learning by multiplying each test result by quality checklist scores.

Following the adjustment, MiMo-V2.6-Pro RL achieved a score of 46 on the Artificial Analysis Intelligence Index, placing it first among open-weights models. DeepLearning.AI published an [explanation of the training method](https://hubs.la/Q04zmF350).

Tags: Xiaomi, MiMo-V2.6-Pro, Reinforcement Learning, Artificial Analysis

[View original post](https://x.com/DeepLearningAI/status/2107570134478950527)