Measured harness ledgerPublic result
Claude Fable 5.1Campfire under the stars — Claude Fable 5.1 Max
Build a polished interactive Three.js campfire scene under a starry night with convincing fire, lighting, environmental detail, and camera motion.
Max reasoningHeadline result
- Workflow cost
- $18.89
- Wall-clock
- 59m (rounded provider display) wall-clock
- Processed tokens
- Not recorded
- Record state
- partial_artifact_static_serve_and_rounded_usage_ledger
Public summary
Claude Fable 5.1 Max partial_artifact_static_serve_and_rounded_usage_ledger ledger: 59m (rounded provider display) wall-clock, Not recorded, and $18.89 Provider-reported session cost; not independently recomputable from the rounded display..
Run identity and stack
- Result ID: campfire-threejs-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: Three.js interactive scene
- Stack: Harness v1 campfire prompt
Cost basis
- No raw session export, exact token counts, cache TTL, or per-line price receipt was supplied.
Primary artifact integrity
- Kind: interactive-threejs-campfire-scene-entry-module
- Path: artifacts/campfire-threejs-fable-5.1-max/source/src/main.js
- SHA-256: e6f7c25eca3f9031682325c06260b3f60036bf8899aa69474910df0dfc470fc5
Recorded caveats
- API duration and wall-clock values are rounded provider displays, not raw timestamps.
- Fresh-input, cache-read, and cache-write values are abbreviated by the provider; total processed tokens are an approximate sum of displayed components.
- The $18.89 total is provider-reported and is not a verified API-equivalent cost calculation.
- Rolling local-activity request totals in the report are excluded because they are not session-attributed benchmark model-call counts.
- The supplied image is model-provided evidence, not an independent RemakeBench browser replay.
- Static serving and JavaScript syntax were checked, but no local FPS, browser/WebGL visual replay, audio-interaction validation, hardware environment, or blind evaluation was supplied.
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
- exact candidate-prompt delivery and protocol evidence
- browser, hardware, viewport, and local-FPS receipt
- independent browser/WebGL replay and final-capture 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.