Measured harness ledgerPublic result
Claude Fable 5

Infinite cathedral corridor shader — Claude Fable 5 Medium

Generate an infinite stained-glass cathedral corridor shader with convincing depth, architectural repetition, light, and motion.

Medium reasoningHeadline result
Workflow cost
$19.17
Wall-clock
15:38.1 wall-clock
Processed tokens
6.95M processed
Record state
partial_token_timing_and_artifact_ledger
Public summary

Claude Fable 5 Medium partial_token_timing_and_artifact_ledger ledger: 15:38.1 wall-clock, 6.95M processed, and $19.17 user-supplied report using live official Anthropic API rates.

Run identity and stack
  • Result ID: infinite-cathedral-shadertoy-fable-5-medium
  • Technical model: claude-fable-5
  • Provider: Anthropic Claude Code
  • Stack: Anthropic Claude Code
  • Stack: Technical model/configuration: claude-fable-5
  • Stack: ShaderToy fragment shader
  • Stack: Harness v1 infinite cathedral prompt
Cost basis
  • Primary cost uses 5-minute cache writes.
Primary artifact integrity
  • Kind: shadertoy-fragment-shader
  • Path: artifacts/infinite-cathedral-shadertoy-fable-5-medium/cathedral.glsl
  • SHA-256: f83d3ef003e9513ba41df3e0b261464a88a5b72f7342d636d50fc3158aadc8eb
Recorded caveats
  • Wall-clock is end-to-end latency including tool execution and waits, not model-only compute.
  • Output tokens include hidden reasoning, code, and tool-call JSON, not just visible text.
  • Cache-read is billed at a deep discount, so total processed tokens overstate effective cost.
  • The primary total assumes the supplied five-minute cache-write rate; a one-hour cache write would increase the cost.
  • Initial and optimized FPS, GPU environment, final capture, and blind-evaluation evidence have not been supplied.
Visible evidence gaps
  • initial local FPS
  • optimized local FPS
  • 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.

  • Tech Review 001 · v1
RemakeBenchResearch console