ResearchTasksPredictive LLM RoutingFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedOpenLLMOracle64.11LLaMA3 Score26May 18, 2026HELM LiteOracle64.3OpenAI Performance26May 18, 2026AlpacaEvalOracle63.17Score (vs OpenAI)26May 18, 2026RouterBenchOracle91.91AUC14May 18, 2026