Category

Decision Models: RL environments and AI benchmarks

AI benchmarks
74
Shares entries with
0 categories

Snapshot 2026-10-11. How categories are built · Where the data comes from

In short

What are RL environments for decision models?
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.

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

AI benchmarks 74

None confirmed yet.

74 not yet confirmedListed in the catalog; no line from its own site or paper confirms it yet.
  1. BBH (Perplexity panel)
  2. RAGTruth
  3. Cloudflare Decision Index 0.2.1: GPQA Diamond
  4. Cloudflare Decision Index 0.2.1: GSM8K
  5. Cloudflare Decision Index 0.2.1: HLE
  6. Cloudflare Decision Index 0.2.1: MMLU-Pro
  7. Cloudflare Decision Index 0.2.1: MMLU
  8. JudgeBench
  9. Knowledge
  10. Language
  11. Retrieval
  12. Tools
  13. Arts
  14. JevBench
  15. Cloudflare Decision Index 0.2.1
  16. Cloudflare Decision Index 0.2.1: BPoMP
  17. Cloudflare Decision Index 0.2.1: Humicroedit
  18. Cloudflare Decision Index 0.2.1: POP909-CL
  19. Cloudflare Decision Index 0.2.1: cfcolor
  20. Cloudflare Decision Index 0.2.1: ForecastBench
  21. Cloudflare Decision Index 0.2.1: Habermas Machine
  22. Cloudflare Decision Index 0.2.1: New Yorker
  23. Cloudflare Decision Index 0.2.1: ChessBench
  24. Cloudflare Decision Index 0.2.1: MuSR
  25. Cloudflare Decision Index 0.2.1: SATA-Bench
  26. Cloudflare Decision Index 0.2.1: CRUXEval
  27. Cloudflare Decision Index 0.2.1: CLadder
  28. Cloudflare Decision Index 0.2.1: BBH
  29. Cloudflare Decision Index 0.2.1: ContractNLI
  30. Cloudflare Decision Index 0.2.1: ANLI
  31. Cloudflare Decision Index 0.2.1: WinoGrande
  32. Cloudflare Decision Index 0.2.1: HellaSwag
  33. Cloudflare Decision Index 0.2.1: ACOS
  34. Cloudflare Decision Index 0.2.1: FinEntity
  35. Cloudflare Decision Index 0.2.1: iSarcasmEval
  36. Cloudflare Decision Index 0.2.1: VAST
  37. Cloudflare Decision Index 0.2.1: NLI4CT
  38. Cloudflare Decision Index 0.2.1: RAGTruth
  39. Cloudflare Decision Index 0.2.1: BANKING77
  40. Cloudflare Decision Index 0.2.1: CLINC150+OOS
  41. Cloudflare Decision Index 0.2.1: BRIGHT
  42. Cloudflare Decision Index 0.2.1: Amazon ESCI
  43. Cloudflare Decision Index 0.2.1: HoVer
  44. Cloudflare Decision Index 0.2.1: BFCL
  45. Cloudflare Decision Index 0.2.1: ToolRet
  46. Cloudflare Decision Index 0.2.1: API-Bank
  47. Cloudflare Decision Index 0.2.1: Home appliance simulator
  48. Cloudflare Decision Index 0.2.1: When2Call
  49. Cloudflare Decision Index 0.2.1: RouterBench
  50. Cloudflare Decision Index 0.2.1: SGD/SGD-X
  51. Cloudflare Decision Index 0.2.1: ARC-Easy
  52. Cloudflare Decision Index 0.2.1: ARC-Challenge
  53. Cloudflare Decision Index 0.2.1: OpenBookQA
  54. Cloudflare Decision Index 0.2.1: CommonsenseQA
  55. Cloudflare Decision Index 0.2.1: Support-ticket calibration
  56. Cloudflare Decision Index 0.2.1: Email spam classification
  57. FinancialPhraseBank
  58. Circa
  59. JevBench public hard
  60. TruthfulQA binary
  61. Perplexity Decision Panel
  62. Decision Index 0.2.1
  63. Knowledge and Reasoning
  64. Language Understanding
  65. Retrieval and Classification
  66. Tools and Automation
  67. Arts and Human Taste
  68. CLadder
  69. Decision Index 0.3 Full Score
  70. Decision Index 0.3 Knowledge
  71. Decision Index 0.3 Language
  72. Decision Index 0.3 Retrieval
  73. Decision Index 0.3 Tools
  74. Decision Index 0.3 Arts

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