Measured harness ledgerPublic result
Claude Fable 5.1

High-voxel-density Oasis Outpost diorama — Claude Fable 5.1 Max

Create a complete inspectable Blender voxel diorama of an oasis outpost at a fixed 0.05-unit voxel resolution through the Blender MCP workflow.

Max reasoningHeadline result
Workflow cost
$20.73
Wall-clock
58m (rounded provider display) wall-clock
Processed tokens
Not recorded
Record state
partial_artifact_and_rounded_usage_ledger
Public summary

Claude Fable 5.1 Max partial_artifact_and_rounded_usage_ledger ledger: 58m (rounded provider display) wall-clock, Not recorded, and $20.73 provider-reported session cost; not independently recomputable from the rounded display.

Run identity and stack
  • Result ID: oasis-outpost-fable-5.1-max
  • Technical model: claude-fable-5.1
  • Provider: Anthropic Claude Code
  • Stack: Anthropic Claude Code
  • Stack: Technical model/configuration: claude-fable-5.1
  • Stack: Blender MCP
  • Stack: 0.05-unit voxel grid
  • Stack: Inspectable .blend artifact
Cost basis
  • No raw session export, exact input-token values, cache TTL, or per-line price receipt was supplied.
Primary artifact integrity
  • Kind: blender-scene
  • Path: artifacts/oasis-outpost-fable-5.1-max/oasis_outpost.blend
  • SHA-256: 25e9fc5e694a836674c136a9d35f1a02f92a10aef589c3379eb189e13bce2618
Recorded caveats
  • Wall-clock and API duration are both 58-minute values displayed by the provider; they are not raw timestamps.
  • The provider abbreviated several token values, so the recorded 28,762,332 processed-token total is an approximation from displayed components.
  • The $20.73 total is provider-reported and is not a verified API-equivalent cost calculation.
  • The rolling local-activity request totals in the report are excluded because they are not session-attributed model-call counts.
  • The supplied preview is model-provided evidence; the packaging host had no Blender binary for independent scene inspection or rerendering.
Visible evidence gaps
  • raw Claude Code session export or exact machine-readable token receipt
  • per-line pricing and cache-TTL receipt sufficient to recompute cost
  • independent Blender scene inspection and final rerender metadata
  • blind-evaluation record
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