<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
  <url><loc>https://modelraters.com/</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/api.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/leaderboard.html</loc><lastmod>2026-10-13</lastmod></url>
  <url><loc>https://modelraters.com/readme.html</loc><lastmod>2026-10-06</lastmod></url>
  <url><loc>https://modelraters.com/slices.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-baseline-needs-a-version-label.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-benchmark-needs-a-baseline-window.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-benchmark-needs-a-held-out-split.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-brier-score-needs-a-reliability-diagram.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-calibration-plot-needs-a-binning-scheme.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-confusion-matrix-needs-a-class-balance.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-dataset-card-needs-a-license-field.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-gain-chart-needs-a-cumulative-lift.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-good-example-makes-the-rule-portable.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-good-rubric-names-the-boundary-case.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-kappa-score-needs-a-chance-baseline.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-leaderboard-needs-a-sample-size-note.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-lift-chart-needs-a-decile-table.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-log-loss-needs-a-calibration-curve.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-map-score-needs-a-relevance-grade.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-mcc-score-needs-a-class-prior.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-metric-card-needs-a-confidence-interval.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-precision-recall-curve-needs-a-threshold.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-prompt-suite-needs-a-version-pin.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-rating-needs-an-evidence-window.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-regression-set-needs-a-freeze-date.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-roc-curve-needs-an-operating-point.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-rubric-change-needs-a-changelog.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-rubric-needs-a-tie-break-rule.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-rubric-needs-examples.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-score-needs-a-disconfirming-example.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-scorecard-needs-a-confidence-band.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/a-scorecard-needs-an-abstain-rule.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/agreement-needs-a-disagreement-log.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/an-ablation-needs-a-control-arm.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/an-auc-score-needs-a-prevalence-note.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/an-ece-score-needs-a-reliability-bin.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/an-eval-harness-needs-a-seed-lock.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/an-f1-score-needs-a-support-weight.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/an-ndcg-score-needs-a-cutoff-k.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/baseline-before-benchmark.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/buyer-eval-checklist.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/calibration-notes-should-name-the-exception.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/calibration-starts-with-shared-examples.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/confidence-without-calibration.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/contamination-checks-beat-averages.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/edge-cases-belong-in-the-rubric.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/evaluation-notes-are-data.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/examples-make-a-rubric-operational.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/examples-should-explain-the-boundary.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/holdout-sets-are-sacred.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/index.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/reviewer-agreement-needs-a-rule.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/rubrics-need-examples.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/run-a-blind-sample-first.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/sample-size-before-you-brag.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/score-the-failure-modes.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/soft-lander-home.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/the-example-should-mark-the-edge.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/the-rubric-should-show-what-changes.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/the-rubric-should-survive-the-surprise.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/version-pin-your-evals.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/articles/what-leaderboards-measure.html</loc><lastmod>2026-10-27</lastmod></url>
  <url><loc>https://modelraters.com/slices.html</loc><lastmod>2026-10-27</lastmod></url>
</urlset>
