0

Paprika3d Backrooms

Fresh

Computer-use eval frontier agents fail (0/3 each: Opus, Sonnet, Haiku): cross a 3D maze by reading real clues past decoys, no wrong doorway

Type
RL Env
License
cc-by-nc-4.0
Size
v0.1.9
Published
Nov 2026
Updated
Nov 2026

Cite

Notes

Only stored in your browser.

Contributors

1