Category

Legal: RL environments and AI benchmarks

RL environments
2
AI benchmarks
57
Shares entries with
14 categories

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

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

Legal across the universe: its 2 confirmed entries are lit. Hover a star for its name; click to open it.

In short

What are RL environments for legal?
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.
Who builds RL environments for legal?
Surge AI and Rise Data Labs.

RL environments 2

  1. Surge AI
  2. Rise Data Labs

AI benchmarks 57

None confirmed yet.

57 not yet confirmedListed in the catalog; no line from its own site or paper confirms it yet.
  1. HELM LegalBench
  2. CaseLaw v2
  3. LegalBench
  4. LawBench
  5. CanLegalRAGBench
  6. Professional Reasoning Bench - Legal
  7. TRLawBench
  8. CVGEvalKit
  9. Harvey LAB-AA
  10. Korean Canonical Legal Benchmark
  11. LegalCiteBench
  12. Magis-Bench
  13. PLawBench
  14. Harvey's Legal Agent Benchmark
  15. LEXam
  16. J1-ENVS
  17. Chinese Labor Law Large Language Model Benchmark
  18. CUAD
  19. ALARB
  20. BenGER
  21. Citation Grounding
  22. ContractNLI
  23. German Statutory QA Benchmark
  24. LaborBench
  25. LexGenius
  26. MASLegalBench
  27. Multi-Legal-Bench
  28. OpenExempt
  29. PDP-Bench
  30. PrivacyQA
  31. TriBench-Ko
  32. TW-LegalBench: Measuring Taiwanese Legal Understanding
  33. UA-Legal-Bench
  34. Ukrainian Legal Text Benchmark
  35. LexGLUE
  36. CaseHOLD
  37. IslamicLegalBench
  38. PrivacyGLUE
  39. Gavel
  40. AppellateGen
  41. JudgmentBench
  42. LegalWorld
  43. ClaimRAG-LAW
  44. L-MARS
  45. Legal RAG Bench
  46. LegalBench-BR v2
  47. LegalBench-RAG
  48. LegalRikai: Open Benchmark
  49. Measuring & Mitigating Over-Alignment for LLMs in Multilingual Criminal Law Courts
  50. VLegal-Bench
  51. Harvey Legal Agent Benchmark
  52. PatentBench
  53. Realm Warren
  54. MAUD
  55. Legal Hallucination Detection Benchmark
  56. Can You Trust What You See? Human and AI Detection of Synthetic Legal Evidence
  57. PAS (Police Action Scenarios)

Domains that overlap with Legal

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