WebsiteBench tested by Argusic Runner

Attempt 1 of 3 · Runs · Argusic Score 100.0 of 100

all runs of WebsiteBenchagent-evaluationaiai-agentsbenchmarkbenchmarkingbrowser-automation

Session recording

Loading recording...

Download the original recording · fingerprint 4dc76093e1bb7ed4...

What the test found

Full Python environment installed with uv; all 54 unit tests pass; ruff linter clean; all 70 task definitions pass static validation; websitebench CLI responds with version and help, lists all 70 tasks, and downloads real tasks from Harbor Hub without any credentials.

uv installed via astral.sh script. All dependencies synced with --locked --group dev. No credentials needed for Harbor Hub download or Hugging Face (unauthenticated, rate-limited). All 54 unit tests pass, ruff passes, 70 task definitions pass static validation, CLI reports version and lists tasks, and a real task downloaded successfully from Harbor Hub.

Argusic installed WebsiteBench in 0.5 minutes and launched it; verification reached Verified running for real.

Runsall runs of WebsiteBench

This summary is drawn from the agent's recorded report for this run. Every figure traces to the log and recording above; nothing here is authored.

Error and fix timeline

No errors were recorded for this run.

Discussion