ResearchTasksSkill Performance EvaluationSkill Performance EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedSkill-X Code-inclusive skillsSkills-Coach84.2Average Score2May 1, 2026Skill-X Instruction-only skillsSkills-Coach83.9Average Score2May 1, 2026Skill-X All skillsSkills-Coach84Average Score2May 1, 2026