SiteOS / Round 0Evidence record C-0782

Moonshot AI

Kimi K2.7 Code

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
Raw74.75/100
Automated40/60
Visual17.75/20
Code8/10
GateFail

Responsive captures

360 / 768 / 1440
Kimi K2.7 Code at 360 pixels
360 px
Kimi K2.7 Code at 768 pixels
768 px
Kimi K2.7 Code at 1440 pixels
1440 px

Interaction evidence

Run facts

Status
completed
Duration
9.2 minutes
Cost
$0.3175 USD
Agent steps
40
Candidate
C-0782

Failed automated checks

  • F04[F04|4][GATE] dialog traps focus, closes with Escape and returns focushard gate
  • R02[R02|5] long copy is not clamped or clipped and missing media has a fallback5 points
  • A01[A01|8][GATE] base page has no serious or critical axe violationshard gate
  • A03[A03|3] reduced motion suppresses long animations and transitions3 points