Directory label

Knowledge benchmarks for LLMs and RL environments

A label other catalogs put on entries, not one of the domains on our map. On the map, each entry here sits in the domain its own site or paper leads with.

Factual and expert knowledge across many subjects, tested with closed-book questions that each have one verifiable answer.

AI benchmarks
144
Shares entries with
1 category

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

In short

What are the main knowledge benchmarks for LLMs?
GPQA-D, MMLU-Pro, GPQA, HLE-Verified, SimpleQA and ARC-AGI v2, among 129 confirmed below.

Only benchmarks use the Knowledge tag: the RL environment directories file their vendors under other categories. Browse all RL environments.

AI benchmarks 144

  1. GPQA-D
  2. MMLU-Pro
  3. GPQA
  4. HLE-Verified
  5. SimpleQA
  6. ARC-AGI v2
  7. HELM MMLUStanford Center for Research on Foundation Models
  8. CorpFin v2Vals AI
  9. CaseLaw v2Vals AI, Jurisage
  10. HealthBenchOpenAI
  11. HealthBench ProfessionalOpenAI
  12. SpatialBench Verified
  13. SingleCellBenchLatchBio
  14. ProteinGym HardMarks lab at Harvard
  15. LABBench2FutureHouse / Edison Scientific
  16. HealthBench HardOpenAI
  17. MMMLUOpenAI
  18. C-Eval
  19. MedCodeVals AI
  20. MedScribeVals AI
  21. LegalBench
  22. TaxEval v2Vals AI
  23. MedQAMIT Computer Science, Artificial Intelligence Laboratory, Jin et al
  24. BoolQ
  25. FutureEvalMetaculus
  26. GQAStanford
  27. HELM
  28. HELM Lite
  29. SEED-BenchAILab-CVC
  30. SQuAD 2.0Stanford
  31. VCRAI2, University of Washington
  32. HotpotQACarnegie Mellon University, Université de Montréal, Stanford
  33. Natural Questions
  34. NYT Connections Extended
  35. ObviousBench
  36. ZebraLogicAllen AI
  37. FACTS GroundingGoogle DeepMind, Google Research
  38. CMMLU
  39. SuperGPQAM-A-P, ByteDance, 2077AI
  40. OpenBookQA
  41. MultiNRCScale AI
  42. PRBench FinanceScale AI
  43. PRBench LegalScale AI
  44. SciPredictScale AI
  45. TutorBench
  46. Balrog
  47. BIG-benchGoogle
  48. MMBench-CN
  49. OK-VQA
  50. POPERUCAIBox
  51. SEED-Bench-2
  52. SuperGLUE
  53. TableBench
  54. VQAv2Yash Goyal, Virginia Tech, Tejas Khot, Douglas Summers-Stay
  55. Altered RiddlesMarco De Santis
  56. BIG-Bench Extra HardGoogle DeepMind
  57. ChartBench
  58. EgoSchemaUC Berkeley
  59. InfographicVQA
  60. IntentGraspUBC NLP Group, University of British Columbia
  61. LingOly-TOO
  62. MSRVTT-QAauthors of "Video Question Answering via Gradually Refined Attention over Appearance, Dejing Xu et al, ACM Multimedia 2017, Motion"
  63. OJBench
  64. WikiSQLSalesforce
  65. MMLU
  66. MMLU-Redux
  67. AGIEval
  68. TruthfulQA
  69. TriviaQAUniversity of Washington
  70. AI2DAllen AI, PRIOR
  71. AIR-BenchOFA-Sys
  72. ARC Challenge
  73. ARC EasyAllen AI
  74. AudioBench
  75. Clotho-AQAAudio Research Group, Tampere University
  76. CommonsenseQA
  77. Global PIQAMRL, Multilingual Representation Learning, Workshop shared task
  78. MMBench
  79. QASCAllen AI
  80. StrategyQA
  81. YouCook2University of Michigan
  82. Artificial Intelligence Quotient (AIQ) Benchmark
  83. AutoLogi
  84. COPAUniversity of Southern California, Roemmele, Andrew S. Gordon, Bejan
  85. ECLeKTic
  86. FINAL Bench MetacognitiveVIDraft
  87. Gaokao-BenchOpenLMLab
  88. LLaVA-Bench in the Wild
  89. MEGA XCOPA
  90. MVBenchOpenGVLab, Shanghai AI Lab, General Vision Group
  91. NPHardEval
  92. PlotQA
  93. Social IQa
  94. HLE-DiamondScale AI, Center for AI Safety
  95. AA-HLEArtificial Analysis
  96. Chinese-SimpleQA
  97. HLE w/o tools
  98. SimpleQA VerifiedGoogle DeepMind, Google Research
  99. HLE Extended
  100. FACTS Benchmark SuiteGoogle DeepMind, Kaggle
  101. AA Openness IndexArtificial Analysis
  102. Artificial Analysis Intelligence Index
  103. DrugDiscoveryBench
  104. FORTRESSScale AI
  105. GaRAGe
  106. Protein DesignBytedance Research
  107. Morphology-to-molecule matchingAxiom Bio
  108. Protein Design library ranking
  109. FrontierScience
  110. AA-Omniscience Index
  111. AA-Omniscience AccuracyArtificial Analysis
  112. Kimi Hallu BenchMoonshot AI
  113. FrontierScience Research
  114. MultiLoKo
  115. FACTS Parametric
  116. Immigration BenchVals AI, Talent Mobility Fund
  117. SUPERChem
  118. ActivityNet-QAZhejiang University, MILVLG, Hangzhou Dianzi University
  119. AIIQ Composite IQaiiq.org
  120. CAIS Text Capabilities IndexCenter for AI Safety
  121. FEVER
  122. HELM InstructStanford Center for Research on Foundation Models
  123. OpenAI Evals
  124. WikiTableQuestionsPanupong Pasupat, Percy Liang, Stanford
  125. GeoQA
  126. HANS
  127. LLaVA-BenchHaotian Liu, Chunyuan Li et al
  128. MEGA XStoryCloze
  129. ST-VQA
15 not yet confirmedListed in the catalog; no line from its own site or paper confirms it yet.
  1. HLE
  2. HLE (Mercor)
  3. SimpleQA Net Score
  4. SQA
  5. 100Q-Hard Net Score
  6. FinanceArena
  7. RAGTruth
  8. ConvRe
  9. InteractiveBench Logic
  10. Protocols
  11. De novo protein-binder design
  12. Medicinal chemistry
  13. Organic chemistry V2
  14. AA-Omniscience Hallucination Rate
  15. YALL Nous Leaderboard

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