Measured harness ledgerPublic result
DeepSeek V4 Pro

High-voxel-density Oasis Outpost diorama — DeepSeek V4 Pro Max

Create a complete inspectable Blender voxel diorama of an oasis outpost at a fixed 0.05-unit voxel resolution through the Blender MCP workflow.

Max reasoningHeadline result
Workflow cost
$0.11
Wall-clock
28m 54.5s wall-clock
Processed tokens
5.15M processed
Record state
complete_token_timing_artifact_and_render_ledger
Public summary

DeepSeek V4 Pro Max complete_token_timing_artifact_and_render_ledger ledger: 28m 54.5s wall-clock, 5.15M processed, and $0.11 API-equivalent accounting, not itemized subscription cash.

Run identity and stack
  • Result ID: oasis-outpost-deepseek-v4-pro-max
  • Technical model: DeepSeek V4 Pro
  • Provider: OpenCode Go
  • Client: OpenCode
  • Stack: OpenCode Go
  • Stack: OpenCode
  • Stack: Technical model/configuration: DeepSeek V4 Pro
  • Stack: Blender MCP
  • Stack: 0.05-unit voxel grid
  • Stack: Inspectable .blend artifact
Primary artifact integrity
  • Kind: blender-scene
  • Path: artifacts/oasis-outpost-deepseek-v4-pro-max/oasis_outpost.blend
  • SHA-256: 3f5c68fc5a6b61deb222bf556de7624900123315b60713e3404844cb8eab67b9
Validation evidence
  • Result: artifact_and_render_supplied
Recorded caveats
  • Wall-clock includes Blender MCP/tool execution and is not model-only compute.
  • The required continue recovery makes this a disclosed two-user-turn protocol deviation.
  • The ordered source payloads preserve the session's Blender MCP scripts with local absolute paths sanitized for publication.
  • No independent second Blender process was run during archival because Blender benchmarks are serialized against one local app.
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.

RemakeBenchResearch console