Measured harness ledgerPublic result
Claude Fable 5High-voxel-density Jungle Temple diorama — Claude Fable 5 Max
Create a complete inspectable Blender voxel diorama of a jungle temple at a fixed 0.05-unit voxel resolution through the Blender MCP workflow.
Max reasoningHeadline result
- Workflow cost
- $79.76
- Wall-clock
- 50:23 wall-clock
- Processed tokens
- 12.71M processed
- Record state
- partial_token_timing_and_artifact_ledger
Public summary
Claude Fable 5 Max partial_token_timing_and_artifact_ledger ledger: 50:23 wall-clock, 12.71M processed, and $79.76 API-equivalent estimate, not a subscription invoice.
Run identity and stack
- Result ID: jungle-temple-fable-5-max
- Technical model: claude-fable-5
- Provider: Anthropic Claude Code
- Stack: Anthropic Claude Code
- Stack: Technical model/configuration: claude-fable-5
- Stack: Blender MCP
- Stack: 0.05-unit voxel grid
- Stack: Inspectable .blend artifact
- Stack: Requested tool profile: blender-mcp
Cost basis
- Primary cost uses 1-hour cache writes (supplied session TTL; primary calculation).
- All-5-minute cache-write alternative: $62.09.
Primary artifact integrity
- Kind: blender-scene
- Path: artifacts/jungle-temple-fable-5-max/jungle_temple_voxel.blend
- SHA-256: e796bb08b0d8990614fdb725ab81e94ec0b0fdffef474730f23e954b6a7dbddb
Recorded caveats
- Wall-clock is end-to-end latency including Blender MCP tool execution, renders, file I/O, and waits—not model-only compute time.
- Output tokens include hidden reasoning, generated code, and tool-call JSON.
- Cache reads are billed at a deep discount, so total processed tokens overstate effective cost.
- The session receipt states a one-hour prompt-cache TTL; the primary estimate therefore uses the one-hour cache-write rate. The all-five-minute alternative is retained for comparison.
- The supplied Blender scene was archived without an independent Blender run in this environment; initial/optimized FPS, render hardware, final capture metadata, RTX final render, and blind evaluation remain unavailable.
Visible evidence gaps
- independent Blender scene validation
- final capture metadata including renderer, hardware, and resolution
- initial and optimized local performance measurements
- RTX Pro 6000 final render
- 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.