ResearchTasksMulti-hop numeric reasoning QAFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMuSiQue 200 samplesDeepSeek-R1-0528638.03Average Tokens10Feb 26, 2026HotpotQA Dynamic Numeric Reasoning suite (randomly sampled 200 multi-hop numeric reasoning questions)Qwen-Plus2,252Tokens (No-adv)5Feb 26, 2026
HotpotQA Dynamic Numeric Reasoning suite (randomly sampled 200 multi-hop numeric reasoning questions)Qwen-Plus2,252Tokens (No-adv)5Feb 26, 2026