ResearchTasksGeneral TasksGeneral TasksFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMMLU-ProQwen3-Next-80B-A3B-Instruct82.93Accuracy23May 20, 2026MMLU-reduxQwen2.5-72B86.8Accuracy15May 20, 2026MMLU-Redux2UCPO91.67PAQ14Feb 26, 2026GPQA DiamondUCPO0.677PAQ Score14Feb 26, 2026LiveBench 2024-11-25Qwen3-Next-80B-A3B75.9Accuracy5Apr 6, 2026LiveBench 0831Qwen2.5-VL-72B0.57Accuracy5Feb 26, 2026