DeepChecks

Open-source testing framework for ML models and LLMs

Data & AnalyticsFreemium

DeepChecks is an open-source Python library for testing machine learning models and LLMs during research, CI, and production monitoring. For ML, it validates training data, model performance, and distribution drift. For LLMs, it evaluates output quality on dimensions like relevance, coherence, toxicity, and groundedness. DeepChecks integrates into ML pipelines via pytest-style test suites, making model quality a first-class part of the development lifecycle rather than an afterthought.

Key Features

• ✓ML testing suite
• ✓LLM evaluation
• ✓Data validation
• ✓Drift detection
• ✓pytest integration
• ✓Open source