Commits
Click on a commit to change the comparison rangefeat: Add evaluate_samples benchmark with improved random_samples API
- Add comprehensive benchmark tests for evaluate_samples method with configurations (1,1), (10,10), (10,100)
- Improve random_samples API: make max_sample_id default to None and use num_samples as fallback
- Use pytest fixture params pattern for cleaner parametrized benchmarks
- Enable keyword-only arguments for random_samples to prevent parameter confusion
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>