ResearchTasksTool-using ReasoningTool-using ReasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedReasoning Domain Suite (AIME2024, AIME2025, HotpotQA, 2WikiMultihopQA, Musique)TEPOdense42.39Average Accuracy13Feb 26, 2026
Reasoning Domain Suite (AIME2024, AIME2025, HotpotQA, 2WikiMultihopQA, Musique)TEPOdense42.39Average Accuracy13Feb 26, 2026