Domain on the map · as Health and bio

Medical LLM benchmarks and RL environments for healthcare

Clinical and health-data tasks, such as working with patient records in standard formats and answering medical questions.

RL environments
2
AI benchmarks
148
Shares entries with
22 categories

Snapshot 2026-11-05. How categories are built · Where the data comes from

The galaxy could not load. See every vendor on the board.

Health and bio, live from the universe. Hover a star for its name; click to open it. Open it in the universe

In short

What are RL environments for healthcare?
A simulated workplace where an AI agent practises a task (a code repository, a browser, business software) and an automatic grader scores each attempt. Labs train on thousands of these attempts. Bought to improve models. For healthcare, that means clinical and health-data tasks, such as working with patient records in standard formats and answering medical questions.
Who builds RL environments for healthcare?
Surge AI and Anthromind.
What are the main medical LLM benchmarks?
Medmarks, ReXrank, BRIDGE Medical Leaderboard, Histopath-C, LABBench2 Clinical Trials and MEDIC Benchmark, among 142 confirmed below.

RL environments 2

  1. Surge AI
  2. Anthromind

AI benchmarks 148

  1. MedmarksMedARC, Sophont
  2. ReXrank
  3. BRIDGE Medical Leaderboard
  4. Histopath-C
  5. LABBench2 Clinical TrialsFutureHouse / Edison Scientific
  6. MEDIC BenchmarkM42
  7. Open Medical-LLM LeaderboardOpen Life Science AI
  8. CLEAR
  9. ASD-Bench
  10. CardioLens
  11. CHI-Bench
  12. DentalGPT Dental Eval SuiteFreedomIntelligence, Chinese University of Hong Kong, Shenzhen
  13. DrVD-Bench
  14. EHRBench
  15. FAM-Bench
  16. InvisibleBenchGiveCare
  17. VariantBenchLatchBio
  18. AgentRx
  19. BanglaMedVQA
  20. BLURBMicrosoft
  21. CareQA-Vision
  22. ClinicalMC
  23. CURE-Med
  24. DeepTumorVQA
  25. DermoBenchDermoGPT, Jinghan Ru et al
  26. DIYHealth Suite
  27. EpiQAL
  28. HealthBench-BR and PCDT-QAFilipe Rocha Lopes, Hugo Abonizio, Rodrigo Nogueira, Roberto Lotufo
  29. IHBench
  30. JMed48k
  31. LingLanMiDianTCMAI-BJTU
  32. LiveMedBench
  33. Med-RewardBench
  34. MedConsultBench
  35. MedCTA
  36. MedGUIDE
  37. MedLayXPlain
  38. MHGraphBench
  39. NeuroAtlas
  40. PubMedQA
  41. RxEval
  42. SycoEval-EM
  43. MMLU Medical GeneticsDan Hendrycks et al, UC Berkeley
  44. AcuityBenchColumbia University
  45. AgentClinicJohns Hopkins University
  46. AutoMedBenchNVIDIA, University of California, Santa Cruz
  47. BCoughBench
  48. CaseReportBench
  49. Checkup2Action
  50. CheXpercept
  51. ChronoMedKG
  52. ClinConsensus
  53. EHR-Complex
  54. Enhancing Pathological VLMs with Cross-scale Reasoning
  55. EpiBenchLabRAI
  56. EQUITRIAGE
  57. HiMed: Incentivizing Hindi Reasoning in Medical LLMsFreedomIntelligence
  58. MedAgentBenchStanford ML Group
  59. MedHELMStanford Center for Research on Foundation Models, Stanford Healthcare, Microsoft, Life Sciences
  60. MultiMedQAGoogle Research
  61. Omi SOAP Note Safety BenchmarkOmi Health
  62. PhysicianBench
  63. R2MED
  64. RXL-RADSetRadioX Labs
  65. ABRA: Agent Benchmark for Radiology Applications
  66. AgentEHR
  67. AIPatient Arena
  68. Causal Sensitivity Score
  69. CBT-Audio
  70. Clinical Reasoning GraphsUniversity of California, San Francisco
  71. ClinicalBenchAlex Stinard
  72. ClinPivot
  73. CodeClinic
  74. CPCD-Bench
  75. DrugAudit
  76. GlobalDentBench
  77. HealthAdminBenchStanford, Stanford Healthcare, Kinetic Systems
  78. ICU-Bench
  79. IMCBench
  80. LifeAgentBench
  81. LLMEval-Med
  82. LungCURE
  83. Med-HALT
  84. MedBench v5
  85. MedFrameQA
  86. Medical Chronology LLM BenchmarkSuperinsight, Inc
  87. Medical Information Response Audit
  88. MedMCQA
  89. MedMemoryBench
  90. MedMeta
  91. MedMosaic
  92. MedRedFlag
  93. MedRepBench
  94. MedSafe-DxCortico Health Technologies
  95. MedStruct-S
  96. MLB
  97. MMed-Bench-IR
  98. MRI-Eval
  99. MTBBench
  100. Oncology Report-Derived VQA
  101. PlaceboBench
  102. PMC-VQA
  103. Pocket-Dentist
  104. PsychEthicsBench
  105. UCSF-PDGM-VQA
  106. VERA-MH
  107. VietMed-MCQ
  108. When Cases Get Rare
  109. When Multiple Scripts MatterAITRICS
  110. MedHal-Loc
  111. RSPC
  112. FHIR-AgentBench
  113. Are LLMs Ready to Assist Physicians? PhysAssistBench for Interactive Doctor-Patient-EHR Assistance
  114. ART (Action-based Reasoning Task)
  115. BioASQ
  116. DALPHINComputational Pathology Group
  117. Efficient Multimodal Clinical Question Answering for Pulmonary Embolism Risk Assessment
  118. Health Memory Arena
  119. MedVidBenchUII-AI
  120. PulseMindAQ-MedAI
  121. Active Evidence-Seeking and Diagnostic Reasoning in Large Language Models for Clinical Decision Support
  122. CounselBench
  123. EHRStruct
  124. Evaluating the Pre-Consultation Ability of LLMs using Diagnostic Guidelines
  125. Generating synthetic computed tomography for radiotherapy
  126. HAO / TBFact
  127. Large Language Models Lack Temporal Awareness of Medical Knowledge
  128. MedBrowseComp
  129. MedCase-Structured
  130. MultiTurnPSB
  131. RealICUTechnical University of Munich
  132. RubricsTree
  133. SlakeVQA
  134. SuiChat-CN
  135. SurgGoal
  136. Synthesis and Evaluation of Long-term History-aware Medical Dialogue
  137. Veterinary Clinical Summarization Eval
  138. WBCMor VQA
  139. What Does the AI Doctor Value? Auditing Pluralism in the Clinical Ethics of Language Models
  140. When Audio-Language Models Fail to Leverage Multimodal Context for Dysarthric Speech Recognition
  141. When Symptoms Are Not Enough
  142. Towards Error-Free EHRs
6 not yet confirmedListed in the catalog; no line from its own site or paper confirms it yet.
  1. MMLU Professional Medicine
  2. HELM MedQA
  3. EmplifAI
  4. RadLIT-9
  5. MIMIC-IV-Ext-Bench
  6. Galileo Agent Leaderboard

Data 13

  1. Paretobased here
  2. AfterQueryalso covers it
  3. Align AIalso covers it
  4. Apturaalso covers it
  5. Mercoralso covers it
  6. ReasonCorealso covers it
  7. Refreshalso covers it
  8. Scale AIalso covers it
  9. Surge AIalso covers it
  10. Symbalalso covers it
  11. Thetaalso covers it
  12. Turingalso covers it
  13. Vetto AIalso covers it

Domains that overlap with Healthcare

Next: pick another domain. Tags come from the RL Research daily scrape, canonicalized nightly.