Category

Vision: RL environments and AI benchmarks

AI benchmarks
35
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 vision?
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 Vision tag: the RL environment directories file their vendors under other categories. Browse all RL environments.

AI benchmarks 35

None confirmed yet.

35 not yet confirmedListed in the catalog; no line from its own site or paper confirms it yet.
  1. HieroglyphBench
  2. timm ImageNet Robustness
  3. C3-Bench: A Context-Aware Change Captioning Benchmark
  4. CV-Arena
  5. DiffCap-Bench
  6. MTRefSeg-21K
  7. SenseBench
  8. SwordBench
  9. WildRoadBench
  10. PerceptionBench
  11. GEO-Bench 2
  12. AUDITS
  13. GAP
  14. AgroVG
  15. DiffSpot
  16. GAVEL: Grounded Caption Error Verification and Localization
  17. Gen-Arena
  18. TECCI
  19. VisualNeedle
  20. Roboflow Vision Evals - Detection
  21. Roboflow Vision Evals - Visual Understanding
  22. HallusionBench
  23. ODinW
  24. DRBench
  25. Rethinking Continual Anomaly Detection on the Edge
  26. Seg-Agent
  27. Evaluating and Enhancing Negation Comprehension in Remote Sensing MLLMs
  28. Focusable Monocular Depth Estimation
  29. Robusto-2
  30. CAIS Vision Capabilities Index
  31. Roboflow Vision Evals - OCR
  32. Roboflow Vision Evals - Segmentation
  33. VSD Fashion
  34. KamonBench
  35. Who Generated This 3D Asset? Learning Source Attribution for Generative 3D Models

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