{"query":"Rubric Points and Benchmark Scores","corpusVersion":"local","generatedAt":"2026-11-02T05:44:17.742Z","results":[{"blockId":"correctness.scoring#rubric-points-and-benchmark-scores","pageId":"correctness.scoring","title":"Rubric Points and Benchmark Scores","pageTitle":"Rubric Points and Benchmark Scores","url":"https://teammately.ai/docs/correctness-governance/scoring.md","humanUrl":"https://teammately.ai/docs/correctness-governance/scoring#rubric-points-and-benchmark-scores","markdownUrl":"https://teammately.ai/docs/correctness-governance/scoring.md","sectionId":"rubric-points-and-benchmark-scores","kind":"reference","productArea":"correctness_governance","score":2907.0855151219234,"reasons":["search_match","title_match","term_match","prefix_or_fuzzy_match"],"markdown":"# Rubric Points and Benchmark Scores"},{"blockId":"correctness.scoring#fields-states-or-lifecycle-rules","pageId":"correctness.scoring","title":"Fields, states, or lifecycle rules","pageTitle":"Rubric Points and Benchmark Scores","url":"https://teammately.ai/docs/correctness-governance/scoring.md","humanUrl":"https://teammately.ai/docs/correctness-governance/scoring#fields-states-or-lifecycle-rules","markdownUrl":"https://teammately.ai/docs/correctness-governance/scoring.md","sectionId":"fields-states-or-lifecycle-rules","kind":"reference","productArea":"correctness_governance","score":2106.1893059169724,"reasons":["search_match","page_title_match","term_match"],"markdown":"## Fields, states, or lifecycle rules\n\n- Positive points are earned when the relevant Rubric passes.\n- Penalty points are deducted when its Rubric fails.\n- A mandatory gate determines eligibility in a gated framework.\n- Missing or incompatible judgments remain incomplete.\n- Exact recorded fractions are displayed as percentages."},{"blockId":"correctness.scoring#history-and-configuration","pageId":"correctness.scoring","title":"History and configuration","pageTitle":"Rubric Points and Benchmark Scores","url":"https://teammately.ai/docs/correctness-governance/scoring.md","humanUrl":"https://teammately.ai/docs/correctness-governance/scoring#history-and-configuration","markdownUrl":"https://teammately.ai/docs/correctness-governance/scoring.md","sectionId":"history-and-configuration","kind":"reference","productArea":"correctness_governance","score":1750.4788859528833,"reasons":["search_match","page_title_match","term_match","prefix_or_fuzzy_match"],"markdown":"## History and configuration\n\nProject Settings → Regime configures point ranges, increments and guidance. New settings affect future captured work. Earlier Benchmark Versions retain their accepted scoring configuration; historical scaling rules are interpreted under that configuration.\n\nUse **Correct judgment** for an attributable correction to an exact result. Use the governing Policy, Rubric or Regime settings when the intended standard is what needs to change."},{"blockId":"benchmark-evaluations.overview#scores-and-completeness","pageId":"benchmark-evaluations.overview","title":"Scores and completeness","pageTitle":"Benchmark Evaluations","url":"https://teammately.ai/docs/benchmark-evaluations.md","humanUrl":"https://teammately.ai/docs/benchmark-evaluations#scores-and-completeness","markdownUrl":"https://teammately.ai/docs/benchmark-evaluations.md","sectionId":"scores-and-completeness","kind":"concept","productArea":"benchmark_evaluations","score":1733.7838343994897,"reasons":["search_match","term_match"],"markdown":"## Scores and completeness\n\nBinary rubric judgments feed the configured Regime. Positive points, penalties and mandatory gates have different effects. Negative scores can be valid. A missing judgment is incomplete rather than a pass, failure or zero. Results retain the full planned Case and Trial population.\n\nRead cost, tokens and latency only when recorded. Missing telemetry stays unknown. Submitted trajectories describe captured execution steps; they do not disclose private model reasoning."},{"blockId":"correctness.scoring#definition","pageId":"correctness.scoring","title":"Definition","pageTitle":"Rubric Points and Benchmark Scores","url":"https://teammately.ai/docs/correctness-governance/scoring.md","humanUrl":"https://teammately.ai/docs/correctness-governance/scoring#definition","markdownUrl":"https://teammately.ai/docs/correctness-governance/scoring.md","sectionId":"definition","kind":"reference","productArea":"correctness_governance","score":1635.7279862381915,"reasons":["search_match","page_title_match","term_match","prefix_or_fuzzy_match"],"markdown":"## Definition\n\nA binary rubric judgment describes observed behavior. The Regime determines how that judgment contributes to a Case and Benchmark score. Positive points, penalties and mandatory gates have distinct meanings."},{"blockId":"correctness.scoring#case-score","pageId":"correctness.scoring","title":"Case score","pageTitle":"Rubric Points and Benchmark Scores","url":"https://teammately.ai/docs/correctness-governance/scoring.md","humanUrl":"https://teammately.ai/docs/correctness-governance/scoring#case-score","markdownUrl":"https://teammately.ai/docs/correctness-governance/scoring.md","sectionId":"case-score","kind":"reference","productArea":"correctness_governance","score":1623.4280990585448,"reasons":["search_match","page_title_match","term_match","prefix_or_fuzzy_match"],"markdown":"## Case score\n\nFor current point-based configuration, the Case score is:\n\n```text\n(earned positive points - triggered penalty points)\n  / total applicable positive points\n```\n\nIf there are no applicable positive points, the denominator is the total applicable penalty points. If that denominator is also zero, the Case is unscored.\n\nA penalty-only Case ranges from 0% when no penalty triggers to -100% when all trigger. A mixed Case can score below -100%. There is no per-Case floor, cap or output scaling in the current configuration.\n\n{% example-demo title=\"A valid negative score\" %}\nA Case has 2 applicable positive points and 6 penalty points. It earns both positive points and triggers every penalty. Its score is (2 - 6) / 2, or -200%. The negative result preserves the configured consequence rather than being clamped to zero.\n{% /example-demo %}"},{"blockId":"benchmark-evaluations.inspect#scores-and-missing-results","pageId":"benchmark-evaluations.inspect","title":"Scores and missing results","pageTitle":"Inspect Evaluation Results","url":"https://teammately.ai/docs/benchmark-evaluations/inspect-results.md","humanUrl":"https://teammately.ai/docs/benchmark-evaluations/inspect-results#scores-and-missing-results","markdownUrl":"https://teammately.ai/docs/benchmark-evaluations/inspect-results.md","sectionId":"scores-and-missing-results","kind":"task","productArea":"benchmark_evaluations","score":1618.729291922135,"reasons":["search_match","term_match","prefix_or_fuzzy_match"],"markdown":"## Scores and missing results\n\nPoint scores can be negative, including below -100% for mixed positive/penalty Cases. A completed mandatory-gate failure contributes zero to the benchmark score. Missing or incompatible judgments stay incomplete even when another gate has failed.\n\nThe full planned population remains the denominator. An incomplete evaluation cannot be made comparable by ignoring its difficult or failed executions."},{"blockId":"correctness.scoring#gates-and-incomplete-judgments","pageId":"correctness.scoring","title":"Gates and incomplete judgments","pageTitle":"Rubric Points and Benchmark Scores","url":"https://teammately.ai/docs/correctness-governance/scoring.md","humanUrl":"https://teammately.ai/docs/correctness-governance/scoring#gates-and-incomplete-judgments","markdownUrl":"https://teammately.ai/docs/correctness-governance/scoring.md","sectionId":"gates-and-incomplete-judgments","kind":"reference","productArea":"correctness_governance","score":1537.071376555595,"reasons":["search_match","page_title_match","term_match","prefix_or_fuzzy_match"],"markdown":"## Gates and incomplete judgments\n\nA completed mandatory-gate failure contributes zero to the benchmark score. Its rubric calculation remains available for diagnosis. Missing judgments do not become zero merely because another gate failed.\n\nBenchmark and repeated-Trial means retain the entire frozen population. An unresolved Case or Trial makes the evaluation incomplete and unrankable. Technical execution failure is not a valid rubric failure."}]}