Measured harness ledgerPublic result
Claude Fable 5MacBook-class cinematic ad scene — Claude Fable 5 Max
Create one polished MacBook-class product-ad shot in Blender with a modeled device, legible industrial detail, intentional materials, lighting, camera movement, and a validator-ready scene.
Max reasoningHeadline result
- Workflow cost
- $75.18
- Wall-clock
- 1:01:04.8 wall-clock
- Processed tokens
- 35.18M processed
- Record state
- partial_token_timing_artifact_validation_ledger
Public summary
Claude Fable 5 Max partial_token_timing_artifact_validation_ledger ledger: 1:01:04.8 wall-clock, 35.18M processed, and $75.18 API-equivalent estimate, not a subscription invoice.
Run identity and stack
- Result ID: macbook-cinematic-blender-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: Cinematic product scene
- Stack: Harness v1 MacBook validator
- Stack: Requested tool profile: blender-mcp
Cost basis
- The primary total uses the official 5-minute cache-write rate because the supplied transcript aggregates cache writes without recording TTL.
- All-1-hour cache-write alternative: $81.28.
- Primary cost assumes 5-minute cache writes because the supplied usage does not record TTLs.
Primary artifact integrity
- Kind: blender-cinematic-product-ad-scene
- Path: artifacts/macbook-cinematic-blender-fable-5-max/macbook_cinematic_final.blend
- SHA-256: defac2dbd14fb117cbd44d5c014b1b6b99c2631cb8ae02511ffc643290e2c91e
Validation evidence
- Result: PASS, 49/49 checks
- Verification: Supplied result evidence. The current archival environment has no Blender executable, so this log was JSON-validated and matched to the canonical task fixture but was not freshly rerun headlessly.
- Path: artifacts/macbook-cinematic-blender-fable-5-max/validation_log.json
- SHA-256: b4b30be679fab2a3065597c4ea9aa53b9bfcfaccdc5f54e6ba4df1863dd16d2c
- Validator SHA-256: 54591de8d4ef2953c6f7e2fe3e4f4b3d9407b953049cc858b1012afaf9424d51
Recorded caveats
- Wall-clock is end-to-end workflow latency, not model-only compute; the supplied record says Blender-side Cycles renders, boolean evaluation, and BVH sweeps account for a substantial portion of the session time.
- Output tokens include hidden reasoning, tool-bound code, and tool-call JSON, not just visible prose.
- Cache reads are billed at a deep discount, so 35.2M processed tokens substantially overstate cost; most processed tokens were cache reads.
- The supplied metrics ledger reports the base model claude-fable-5. The Max reasoning configuration is user-specified metadata.
- The cache-creation aggregate does not identify TTL. If every cache write used the official one-hour rate, the total would be $81.28 rather than $75.18.
- The supplied validation log reports PASS 49/49, but it was not independently rerun during archival because Blender is unavailable in this environment.
- No final 4K film render, render-hardware identity, Blender MCP tool-use transcript, or blind-evaluation record was supplied.
Visible evidence gaps
- independent headless validator rerun
- render-hardware identity
- Blender MCP tool-use transcript or disclosure
- final capture or rubric stills
- blind-evaluation record
Builder test available
This result is part of a Builder test. Open it for the exact prompt and any released projects, RemakeBench Harness workflows and production skills. Public proof and known evidence gaps stay visible here.
- Kimi K3 Launch 002 · v1