Skip to main content

Ctrl+K

eval-toolkit

Getting Started
What’s new
Examples
Worked example: metrics + bootstrap CIs
Worked example: slice-aware evaluate harness

GitHub
PyPI

GitHub
PyPI

Section Navigation

eval_toolkit.harness.DEFAULT_BOOTSTRAP_RESAMPLES
eval_toolkit.harness.RUN_RESULT_SCHEMA_VERSION
eval_toolkit.harness.EvalSlice
eval_toolkit.harness.RunResult
eval_toolkit.harness.evaluate
eval_toolkit.harness.evaluate_folded
eval_toolkit.harness.evaluate_scorer_on_slice
eval_toolkit.harness.with_claim_report
eval_toolkit.harness.write_run_result

eval_toolkit.harness
eval_toolkit.harness.with_claim_report

eval_toolkit.harness.with_claim_report#

.. currentmodule:: eval_toolkit.harness

.. autofunction:: with_claim_report

previous

eval_toolkit.harness.evaluate_scorer_on_slice

next

eval_toolkit.harness.write_run_result

© Copyright 2026, Brandon Behring.

Created using Sphinx 9.1.0.

Built with the PyData Sphinx Theme 0.17.1.