ResearchTasksDomain-level accuracy estimationDomain-level accuracy estimationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedSTEM benchmarks (GSM8K, OlympiadBench, MATH, SciBench, etc.) (held-out)PHI-3.5-MINI100External Score9Feb 26, 2026
STEM benchmarks (GSM8K, OlympiadBench, MATH, SciBench, etc.) (held-out)PHI-3.5-MINI100External Score9Feb 26, 2026