ResearchDatasets7-benchmark suite7-benchmark suiteFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsInstruction Following7-benchmark suite SFT on Alpaca71.5Accuracy25Mathematical Reasoning7-benchmark suite (MATH, AIME 2025, AMC, MINERVA, KAOYAN, OlympiadBench, CN_MATH24)72.6Average Accuracy10
Mathematical Reasoning7-benchmark suite (MATH, AIME 2025, AMC, MINERVA, KAOYAN, OlympiadBench, CN_MATH24)72.6Average Accuracy10