Measured harness ledgerPublic result
Claude Fable 5.1Off-road Mud Game — Claude Fable 5.1 Max
Build a one-request procedural off-road driving game with vehicle physics, independent suspension, streamed terrain, mud feedback, and multiple cameras.
Max reasoningHeadline result
- Workflow cost
- $113.27
- Wall-clock
- 1h 52m 10s wall-clock
- Processed tokens
- 132.41M processed
- Record state
- partial_token_timing_source_build_ledger
Public summary
Claude Fable 5.1 Max partial_token_timing_source_build_ledger ledger: 1h 52m 10s wall-clock, 132.41M processed, and $113.27 Official Anthropic API-list-price equivalent from the supplied receipt, not an itemized Claude Code subscription charge..
Run identity and stack
- Result ID: off-road-driving-game-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 vehicle workflow
- Stack: Harness v1 off-road prompt
Cost basis
- The supplied receipt reports that it fetched and verified the listed rate card from the official Anthropic pricing page on 2026-09-02; the archive preserves that provenance claim.
- All-5-minute cache-write alternative: $103.37.
Primary artifact integrity
- Kind: manifest-verified-artifact
- Path: artifacts/off-road-driving-game-threejs-fable-5.1-max/source/src/main.js
- SHA-256: c1918998f4d219210fb6396cad43991bba7708992e38ecf7385d5f2c8d32beb3
Validation evidence
- Result: PASS
- Path: artifacts/off-road-driving-game-threejs-fable-5.1-max/validation/build.public.json
- SHA-256: ef56df2b154b7cb8733464307bf75358e12e297a600c8e49bab1f4b0948f0c66
Recorded caveats
- Wall-clock is end-to-end workflow latency, including tool execution and waits; it is not model-only compute time.
- Output tokens include hidden reasoning, generated code, and tool-call JSON, not only visible prose.
- Cache-read tokens are billed at a discount, so total processed tokens materially overstate effective cost.
- The cache-write TTL split is not independently reconstructible from the public artifact. The primary calculation follows the supplied receipt's one-hour TTL declaration and retains an all-five-minute alternative.
- The archived source and clean production build establish reproducibility of the static project, not gameplay quality or benchmark completion.
- The supplied screenshot is retained as evidence but was not independently evaluated as a standardized final capture.
Visible evidence gaps
- independent browser acceptance run
- local FPS, browser, viewport, and hardware receipt
- multi-minute sustained-drive and generation-seam receipt
- four-corner suspension-articulation receipt
- standardized final gameplay capture
- 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.