ResearchTasksSTEM Knowledge and ReasoningSTEM Knowledge and ReasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedGPQA Diamond MMLU ReducedTeacher58.86GPQA Diamond Accuracy7Jun 2, 2026MMLU STEMQwen2.5-Math-72B-Instruct82.3Pass@13Feb 26, 2026