Measured harness ledgerPublic result
Grok 4.7

High-voxel-density Jungle Temple diorama — Grok 4.7 xhigh

Create a complete inspectable Blender voxel diorama of a jungle temple at a fixed 0.05-unit voxel resolution through the Blender MCP workflow.

xhigh reasoningHeadline result
Workflow cost
$5.88
Wall-clock
3304.6s wall-clock
Processed tokens
14.17M processed
Record state
complete_internal_model_verdict_with_viewport_only_quality_caveat
Public summary

Grok 4.7 xhigh complete_internal_model_verdict_with_viewport_only_quality_caveat ledger: 3304.6s wall-clock, 14.17M processed, and $5.88 Provider-recorded usage estimate, not an itemized subscription cash charge.

Run identity and stack
  • Result ID: jungle-temple-grok-4.7-xhigh
  • Technical model: Grok 4.7
  • Provider: xAI Grok Build
  • Client: official Grok CLI 1.0.41
  • Stack: xAI Grok Build
  • Stack: official Grok CLI 1.0.41
  • Stack: Technical model/configuration: Grok 4.7
  • Stack: Blender MCP
  • Stack: 0.05-unit voxel grid
  • Stack: Inspectable .blend artifact
Primary artifact integrity
  • Kind: manifest-verified-artifact
  • Path: artifacts/jungle-temple-grok-4.7-xhigh/jungle_temple.blend
  • SHA-256: bee9dbbcdf204a43667c2f76cde12e76ed774116fc3bbc45b81a0c981161da02
Recorded caveats
  • The model's internal completion verdict governs this diorama by user direction; no external judge was run.
  • Viewport captures and static inventory establish presence and file integrity, not independent asset-quality acceptance.
  • The frozen metrics operator prompt expects Grok 4.6 / CLI 1.0.3, whereas this run used Grok 4.7 / CLI 1.0.41; stack validation is therefore PARTIAL even though benchmark usage extraction passed.
  • The $5.87672252 amount is a Grok-recorded usage estimate, not evidence of the user's marginal subscription cash charge.
  • An independent API-equivalent total is unavailable because the exact grok-4.7-build rate row and request-level long-context thresholds were not published in the receipt.
Public result only

This result keeps its public summary and evidence, but it does not currently have a matching Builder test with prompts, projects, Harness workflows or skills.

RemakeBenchResearch console