All workflows

Workflow runs

• Initial commit

  completed successfully:
  Test ProbabilityBench#9:Commitb376befpushedbytakashiishida
  main

  Oct 15, 202634s
  More actions for workflow run 9

• Give each case its ID directly and drop internal metadata

  completed successfully:
  Test ProbabilityBench#8:Commit829877cpushedbytakashiishida
  main

  Oct 14, 202633s
  More actions for workflow run 8

• Present only the memo as model input in the README

  completed successfully:
  Test ProbabilityBench#7:Commit79f054cpushedbytakashiishida
  main

  Oct 14, 202633s
  More actions for workflow run 7

• Support only OpenRouter models in the decision-model evaluation

  completed successfully:
  Test ProbabilityBench#6:Commit67a6134pushedbytakashiishida
  main

  Oct 14, 202635s
  More actions for workflow run 6

• Add the OpenRouter key template

  completed successfully:
  Test ProbabilityBench#5:Commit525e54dpushedbytakashiishida
  main

  Oct 14, 202637s
  More actions for workflow run 5

• Report how long each model's run takes

  completed successfully:
  Test ProbabilityBench#4:Commit75fb1d6pushedbytakashiishida
  main

  Oct 14, 202639s
  More actions for workflow run 4

• Evaluate decision models on OpenRouter and plot cost against KL

  completed successfully:
  Test ProbabilityBench#3:Commit18f5ac3pushedbytakashiishida
  main

  Oct 14, 202640s
  More actions for workflow run 3

• Remove the Scope section from the README

  completed successfully:
  Test ProbabilityBench#2:Commit19714e7pushedbytakashiishida
  main

  Oct 14, 202623s
  More actions for workflow run 2

• initial release

  completed successfully:
  Test ProbabilityBench#1:Commit66f8be5pushedbytakashiishida
  main

  Oct 14, 202629s
  More actions for workflow run 1