Category

Generalization: RL environments and AI benchmarks

AI benchmarks
34
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 generalization?
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 Generalization tag: the RL environment directories file their vendors under other categories. Browse all RL environments.

AI benchmarks 34

None confirmed yet.

34 not yet confirmedListed in the catalog; no line from its own site or paper confirms it yet.
  1. NarrativeQA
  2. AlpacaEval
  3. EQ-Bench
  4. HELM AIR-Bench
  5. HELM Safety
  6. AgentHarm
  7. RealToxicityPrompts
  8. WeirdML
  9. AgentDojo
  10. Arena-Hard
  11. LongBench v2
  12. MoralChoice
  13. AdvBench
  14. BOLD
  15. CTFBench
  16. FreshQA
  17. MT-Bench
  18. Generalization Spectrum
  19. Generalized Zero-Shot Benchmark for Facial Age Estimation
  20. Cybench
  21. ETHICS
  22. InfiniteBench
  23. CyberSecEval
  24. NeedleBench
  25. RGB
  26. StereoSet
  27. HELM Long Context
  28. CrowS-Pairs
  29. HH-RLHF
  30. MultiHop-RAG
  31. Needle In A Haystack
  32. RAGAS
  33. LMArena Text Arena
  34. L-Eval

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