Category

Video: RL environments and AI benchmarks

AI benchmarks
36
Shares entries with
1 category

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

In short

What are RL environments for video?
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 Video tag: the RL environment directories file their vendors under other categories. Browse all RL environments.

AI benchmarks 36

None confirmed yet.

36 not yet confirmedListed in the catalog; no line from its own site or paper confirms it yet.
  1. EvalVerse
  2. Flat-Pack Bench
  3. RealStreamEval
  4. CG-Bench
  5. Video Understanding Reward Modeling
  6. Your One-Stop Solution for AI-Generated Video Detection
  7. NEST
  8. FineBench
  9. Minerva-Ego
  10. PhyGround
  11. CapRiCorn-1K
  12. DistractionBench
  13. Do Joint Audio-Video Generation Models Understand Physics?
  14. DramaDirector: Geometry-Guided Short Drama Generation
  15. iWorld-Bench
  16. KARMA-MV
  17. MotionHalluc
  18. StreamPro-Bench
  19. VideoNet
  20. AVGen-Bench
  21. Sparkle
  22. WBench
  23. CoCoVideo
  24. EgoPro-Bench
  25. GroundShot
  26. Molmo2
  27. NarrativeTrack
  28. VERHallu
  29. VNU-Bench
  30. Quantitative Video World Model Evaluation for Geometric-Consistency
  31. Chehre
  32. EvalCrafter
  33. OpenVLM Video Leaderboard
  34. Lumos-Nexus
  35. Decoupling Spatio-Temporal Adapter for Fine-Grained Badminton Action Localization
  36. DrivingGen

Domains that overlap with Video

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