Spaces:
Running
Running
File size: 295 Bytes
22de727 | 1 2 3 4 | """MiniWeb, the benchmark: 65 synthetic websites (sites/) on one Flask server (app/), the annotation tool that wrote
and verified the 376 human tasks (annotation/), and the task verifiers and agent runs that grade them (evaluation/).
scripts/ holds the database seeds and the task-set tools."""
|