Organization collection

Ryan Marten

@ryanmarten · Datasets published by this organization.

Organization inventory

DatasetAccessTasks
ryanmarten/terminal-bench-4-no-prebuild

Terminal Bench 4 No Prebuild: Terminal-Bench 4.0.0 tasks from the v4.0.0 GitHub release source, published without prebuilt Docker image pins.

Public
66
ryanmarten/tb-test

Terminal-Bench is a benchmark for measuring agents' abilities to complete tasks using a terminal.

Public
1
ryanmarten/tb4-preview

Terminal-Bench is a benchmark for measuring agents' abilities to complete tasks using a terminal.

Public
66

3 datasets