Measured harness ledgerPublic result
Kimi K3High-voxel-density Shrine Village diorama — Kimi K3 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
- $2.23
- Wall-clock
- 35:53.5 wall-clock
- Processed tokens
- 2.58M processed
- Record state
- partial_token_timing_and_artifact_ledger
Public summary
Kimi K3 Max partial_token_timing_and_artifact_ledger ledger: 35:53.5 wall-clock, 2.58M processed, and $2.23 API-equivalent estimate, not an itemized subscription cash charge.
Run identity and stack
- Result ID: shrine-village-kimi-k3-max
- Technical model: kimi-k3
- Provider: Kimi Code CLI
- Stack: Kimi Code CLI
- Stack: Technical model/configuration: kimi-k3
- Stack: Blender MCP
- Stack: 0.05-unit voxel grid
- Stack: Inspectable .blend artifact
- Stack: Requested tool profile: blender-mcp
Cost basis
- Kimi Code ran on an Allegretto subscription ($39/month); the marginal per-run cash cost was not itemized.
Primary artifact integrity
- Kind: blender-scene
- Path: artifacts/shrine-village-kimi-k3-max/ShrineVillage.blend
- SHA-256: e0088d67823b72f4001371a89063eb4ec716377f5bbd8df03979e6a2eae46626
Recorded caveats
- Wall-clock is end-to-end workflow latency and includes tools, Blender renders, approval waits, and idle time.
- Kimi Code CLI 0.26.0 does not expose separate reasoning-token counts; output includes provider-accounted reasoning, visible prose/code, and tool-call JSON.
- Cache reads are discounted, so total processed tokens overstate effective cost.
- The raw private session ZIP has not been published; the stable benchmark-window receipt and its hash are retained.
- The archived preview was visually inspected, but Blender is unavailable in the archival environment, so the scene and build script were not independently rerun.
- No render-hardware identity, initial/optimized FPS measurement, RTX final render, or blind-evaluation record was supplied.
Visible evidence gaps
- independent Blender scene and build-script validation
- final capture metadata including renderer, hardware, and resolution
- initial and optimized local performance measurements
- RTX Pro 6000 final render
- 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.
- Kimi K3 Launch 002 · v1