ResearchTasksComposing auto-generated skillsComposing auto-generated skillsFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedBrowseComp+OLMo-3-7B61.4Skill Step Percentage9Jun 19, 2026WebArenaGPT-557.6Skill Step Percentage9Jun 19, 2026IWLlama-3.1-70B30Skill-Step Percentage9Jun 19, 2026