Spaces:
Sleeping
Sleeping
Commit History
-
Update benchmark display: Add clarification on score accuracy and adjust score formatting
dc54ec6
-
updating benchmarks
971d57f
-
benchmarks and readme
965722a -
updating benchmarks
182b62d
-
updating benchmarks
1bd522f -
feat: add very hard difficulty tier and interactive demo UI
Add new "very_hard" task pack with adversarial content and benchmark results. Introduce playable demo UI with server endpoints (/demo, /demo/reset, /demo/step) for human testing. Enhance models with reward/done fields and improve inference error handling. BREAKING CHANGE: Entry point changed from `server.app:create_app` to `server.app:app` in openenv.yaml4559388 -
refactoring, polish, and adding very hard data
bf76643