Skip to content

The first exam for code agents in the physical world: frozen robot tasks from many benchmark suites, each answered with a program and verified in a separate sandbox. Runs on Harbor.

NameLast commit date
..
roboengineer-anycar-compact-lap-monaco-6-i00-standard
roboengineer-anycar-compact-lap-monaco-6-i01-standard
roboengineer-anycar-compact-lap-silverstone-8-i00-standard
roboengineer-anycar-compact-lap-silverstone-8-i01-standard
roboengineer-anycar-drift-park-i00-standard
roboengineer-anycar-drift-park-i01-standard
roboengineer-anycar-tight-drift-park-i00-standard
roboengineer-anycar-tight-drift-park-i01-standard
roboengineer-anycar-tracking-i00-standard
roboengineer-anycar-tracking-i01-standard
roboengineer-g1-terrain-walk-i00-standard
roboengineer-g1-terrain-walk-i01-standard
roboengineer-go2-attitude-i00-standard
roboengineer-go2-attitude-i01-standard
roboengineer-go2-forward-jump-i00-standard
roboengineer-go2-forward-jump-i01-standard
roboengineer-go2-weave-i00-standard
roboengineer-go2-weave-i01-standard
roboengineer-go2-yaw-jump-i00-standard
roboengineer-go2-yaw-jump-i01-standard
roboengineer-landing-random-pad-i00-standard
roboengineer-landing-random-pad-i01-standard
roboengineer-neuralfly-eight-i00-standard
roboengineer-neuralfly-eight-i01-standard
roboengineer-neuralfly-general-i00-standard
roboengineer-neuralfly-general-i01-standard
roboengineer-neuralfly-general-skydio-i00-standard
roboengineer-neuralfly-general-skydio-i01-standard
roboengineer-neuralfly-vector-wind-i00-standard
roboengineer-neuralfly-vector-wind-i01-standard
anycar.md
control-transfer.md
g1.md
go2.md
neuralfly.md
policy.md
quadrotor-landing.md
README.md
validation.md