Measured harness ledgerPublic result
GLM 5.3 FlashHigh-voxel-density Shrine Village diorama — GLM 5.3 Flash Max
Create a complete inspectable Blender voxel diorama of a shrine village at a fixed 0.05-unit voxel resolution through the Blender MCP workflow.
Max reasoningHeadline result
- Workflow cost
- $1.89
- Wall-clock
- 2h 9m 22.311s wall-clock
- Processed tokens
- 4.07M processed
- Record state
- partial_multi_user_turn_artifact_ledger
Public summary
GLM 5.3 Flash Max partial_multi_user_turn_artifact_ledger ledger: 2h 9m 22.311s wall-clock, 4.07M processed, and $1.89 OpenCode Go API-equivalent usage accounting, not an itemized subscription marginal-cash invoice.
Run identity and stack
- Result ID: shrine-village-glm-5.3-max
- Technical model: glm-5.3-flash
- Provider: opencode-go
- Client: OpenCode
- Stack: opencode-go
- Stack: OpenCode
- Stack: Technical model/configuration: glm-5.3-flash
- Stack: Blender MCP
- Stack: 0.05-unit voxel grid
- Stack: Inspectable .blend artifact
Primary artifact integrity
- Kind: blender-scene
- Path: artifacts/shrine-village-glm-5.3-max/shrine_village.blend
- SHA-256: 396d0680fb50596d6a80631c4628450ea18103f491ac804c57b19b3ef08e706f
Validation evidence
- Result: PASS_WITH_CAVEATS
- Path: artifacts/shrine-village-glm-5.3-max/validation/scene-inspection.public.json
- SHA-256: 860e94c41594940310828876a930a2830289fd8dd0b67980cbac0f2fc136e617
Recorded caveats
- This is a 17-user-turn recovery record, not a strict one-shot benchmark result.
- The metrics sidecar is operator-generated from the canonical bounded extractor after the same-session metrics stream and its exact continuation stalled; the underlying raw records remain private.
- Six tool errors were recorded in the bounded creation ledger; the final scene, builder, and render were nevertheless produced and independently reopened.
- The public archive has no render-hardware or local-FPS evidence.
- The final scene was reopened read-only but the supplied final render was not independently rerendered or blind-evaluated.
Visible evidence gaps
- A strict one-user-turn rerun without recovery continuations
- A no-tool-error creation ledger
- Render-hardware metadata and a local performance capture where relevant
- Independent rerender evidence and a 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.