ResearchTasksMeta-evaluationMeta-evaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedAggregated Benchmarks (AIME, ARC, GSM8K, HE, MMLU, IT, RU, BFCL)GPT-5 nano2.4Overall Average Rank16May 11, 2026SummEvalBARTSCORE-CNN0.448Spearman Correlation (COH)10Feb 26, 2026AgentEvalBench 1.0 (test)EvalAgent85URF8May 13, 2026AgentEvalBenchEvalAgent83.8URF8May 13, 2026Overall AverageUltra-Dense Prompting9.7Accuracy Improvement5Apr 21, 2026
Aggregated Benchmarks (AIME, ARC, GSM8K, HE, MMLU, IT, RU, BFCL)GPT-5 nano2.4Overall Average Rank16May 11, 2026