SiteOS / Round 0Evidence record C-6121

OpenAI

GPT-5.6 Sol

Frozen one-attempt benchmark evidence. The live build is reproduced from the untouched model worktree using deployment-path adaptations recorded in its manifest.

View live buildDownload frozen source
Total49/100
Raw77.25/100
Automated41/60
Visual19/20
Code7.25/10
GateFail

Responsive captures

360 / 768 / 1440
GPT-5.6 Sol at 360 pixels
360 px
GPT-5.6 Sol at 768 pixels
768 px
GPT-5.6 Sol at 1440 pixels
1440 px

Interaction evidence

Run facts

Status
completed
Duration
8.9 minutes
Cost
$1.4915 USD
Agent steps
18
Candidate
C-6121

Failed automated checks

  • F04[F04|4][GATE] dialog traps focus, closes with Escape and returns focushard gate
  • F05[F05|4][GATE] the native-select form has errors and deterministic successhard gate
  • R01-tablet[R01-tablet|3][GATE] no horizontal overflow at 768pxhard gate
  • A01[A01|8][GATE] base page has no serious or critical axe violationshard gate