ResearchTasksQuery-guided evaluationQuery-guided evaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedHeurekaBenchBiomni3.57G-Eval Score4Jun 11, 2026BixBench V50StatefulDiscovery-QG80V50 Accuracy4Jun 11, 2026