Measured harness ledgerPublic result
GLM 5.2Infinite cathedral corridor shader — GLM 5.2 Max
Generate an infinite stained-glass cathedral corridor shader with convincing depth, architectural repetition, light, and motion.
Max reasoningHeadline result
- Workflow cost
- $0.27
- Wall-clock
- 6m 28.0s wall-clock
- Processed tokens
- 351K processed
- Record state
- partial_one_shot_token_timing_and_shader_ledger
Public summary
GLM 5.2 Max partial_one_shot_token_timing_and_shader_ledger ledger: 6m 28.0s wall-clock, 351K processed, and $0.27 OpenCode-recorded API-equivalent usage accounting, not a subscription marginal-cash invoice.
Run identity and stack
- Result ID: infinite-cathedral-shadertoy-glm-5.2-max
- Technical model: glm-5.2
- Provider: OpenCode Go
- Stack: OpenCode Go
- Stack: Technical model/configuration: glm-5.2
- Stack: ShaderToy fragment shader
- Stack: Harness v1 infinite cathedral prompt
Primary artifact integrity
- Kind: shadertoy-image-pass-fragment-shader
- Path: artifacts/infinite-cathedral-shadertoy-glm-5.2-max/source/cathedral_corridor.glsl
- SHA-256: 484580b36389b3bc642238a119e0ddae0eddebf4bb683247f355c1ddc63fb344
Recorded caveats
- Wall-clock is end-to-end workflow latency, including tool execution and idle gaps; it is not model-only compute.
- One OpenCode agent turn can contain multiple billable requests; this one-shot benchmark window contains eight assistant/API requests.
- Visible output is output-priced; recorded reasoning tokens are zero.
- Cache reads are discounted, so total processed tokens overstate cost.
- OpenCode Go does not itemize a marginal per-run cash charge; the reported cost is API-equivalent usage accounting.
- Static compilation is not a Shadertoy runtime, visual-quality, or frame-rate measurement.
- No initial/optimized local FPS pair, RTX Pro 6000 1080p60 final capture, or blind evaluation is archived.
Visible evidence gaps
- initial local FPS
- optimized local FPS
- RTX Pro 6000 1080p60 final 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.