WebPageBench / app.py

Commit History

  1. add fixes ui Running

    cdb54bf

  1. update ui

    826c04d
  2. update ui

    3874098
  3. update results

    c65a116
  4. add new results

    b53774c

  1. Replace 51-task pilot runs with 152-task REPORT results and show harness input modality.⁠

    ai-forever +1: Cursor
    78b04f0

  1. fix cost

    1efaba3
  2. fix speed

    a593bad

  1. fix vision

    d285155
  2. fix vision

    7990e30
  3. fix vision

    51e815c
  4. fix cost

    fda2871
  5. fix cost

    bb01fd2

  1. fix traces

    d9920c5
  2. fix traces

    88cab61
  3. try add traces

    9ab3637
  4. Import Web Agent Bench leaderboard from agent-bench

    3c19b11