jp-full-gemini · status: completed

Bench results

capability fixture model status score cost($) dur(s)
refresh jp-1 google/gemini-3.1-pro-preview error - 0.000000 207.2
refresh jp-10 google/gemini-3.1-pro-preview error - 0.000000 204.2
refresh jp-2 google/gemini-3.1-pro-preview error - 0.000000 201.1
refresh jp-3 google/gemini-3.1-pro-preview error - 0.000000 225.2
refresh jp-4 google/gemini-3.1-pro-preview error - 0.000000 276.3
refresh jp-5 google/gemini-3.1-pro-preview error - 0.000000 198.3
refresh jp-6 google/gemini-3.1-pro-preview error - 0.000000 198.2
refresh jp-7 google/gemini-3.1-pro-preview error - 0.000000 210.2
refresh jp-8 google/gemini-3.1-pro-preview error - 0.000000 180.1
refresh jp-9 google/gemini-3.1-pro-preview error - 0.000000 120.1

Winners

  • score:
  • cost:
  • speed:
  • overall: