P-Bench / app.py

Commit History

  1. adding new model mode

    Minette Kaunismäki
    0ad4e9b
  2. log scale (#3)⁠

    minette-kaunismaki +1: begumcig
    1dd19c2

  1. ui-updates (#1)⁠

    minette-kaunismaki +1: begumcig
    e680130

  1. add: p-image-2-ideogram-benchmarking-results

    5fc63f1

  1. feat: format numeric columns in app.py to display up to 4 decimal places for improved data presentation

    f502278
  2. feat: enhance data processing in app.py to handle URL formatting and compute aggregate GenEval scores; update sorting logic for leaderboard metrics

    c123568

  1. chore: cleanup unnecessary code for runnign benchmark

    fd08cbd