This tab synthesizes the filtered evaluation scope into ranking KPIs and final standings, enabling direct assessment of comparative performance under the active scoring rule.
This tab supports exploratory aggregation of the filtered runs by restructuring observations across methods, teams, instances, and metrics to reveal distributional patterns.
This tab provides run-level diagnostic evidence, allowing users to inspect statuses, failures, excerpts, and winning runs within the current analytical scope.
This tab compares teams under a lexicographic objective hierarchy, showing where ties persist and which KPI first separates competing solutions.
This tab profiles relative percentage deviation at the case level, helping readers examine how performance varies across instances, methods, time windows, and teams.