Benchmarking¶

This section covers how to evaluate OpenSage/SAGE-X agents and measure performance across tasks.

What you'll find here¶

• How to run built-in evaluations (entry point + workflow)
• How to add a new evaluation/benchmark to the repo
• Recommended reporting and reproducibility practices

Entry points¶

• Evaluation Entry: Batch evaluation workflow and lifecycle.
• Adding Evaluations: How to integrate a new benchmark.