ResearchTasksTool-calling for Clinical Question AnsweringTool-calling for Clinical Question AnsweringFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedAgentBench FHIR (val)QWEN3-8B + RL76.7Score8May 15, 2026