ResearchTasksReal-World AgentFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedClaw-EvalGPT-5.480.6Average Score22Jun 2, 2026PinchBenchClaude Opus 4.682.3Average Score15Jun 2, 2026