ResearchTasksAggregate LLM EvaluationFor AI assistantsMarkdownContent indexAggregate LLM EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedAggregate (MATH, GSM8K, H_Eval, MMLU, CEVAL, CMMLU, BoolQ, CSQA)Qwen3-30B-A3B81.41Aggregate Accuracy26May 15, 2026
Aggregate (MATH, GSM8K, H_Eval, MMLU, CEVAL, CMMLU, BoolQ, CSQA)Qwen3-30B-A3B81.41Aggregate Accuracy26May 15, 2026