Skip to main content

Model Evaluations

Feature no longer available

AI Studio no longer offers model evaluations. It cannot be used from the console or the API, and this page is kept for reference only. See AI Studio for what is available.

AI Studio provides tools for evaluating fine-tuned models at every stage of the development lifecycle.

Custom Evaluations

Create custom evaluation workflows to assess your model on defined criteria using selected logs and comparison models.

Benchmark Evaluations

Run standardized tests to evaluate your model across core domains such as math, reasoning, and factual knowledge.

Training Metrics

Monitor training and validation loss in real time or after training to understand your model's learning progress.