Agents & Tool Use
AppWorld
AppWorld: interactive coding agent benchmark. Per-(agent, task) pass/fail decrypted from the public leaderboard's experiment bundles; real per-task natural-language instructions from the released task data.
585items
18subjects
Apache-2.0license
agents_and_tool_usedomain
textmodality
gui_screenshotmodality
item-level responses released
Saturation status: No
Response matrix
Loading response matrix…
Correct (1)Incorrect (0)Unobserved
Scale: 1 = correct · 0 = incorrect