Measured harness ledgerPublic result
MiMo V2.6 ProEiffel Tower Drawing — MiMo V2.6 Pro Highest
Draw the Eiffel Tower with a friction-held pencil on a Marvin arm and Wuji hand in MuJoCo.
Highest reasoningHeadline result
- Workflow cost
- $0.15
- Wall-clock
- 36m 58.0s wall-clock
- Processed tokens
- 2.19M processed
- Record state
- judge_pass_independently_replayed
Public summary
MiMo V2.6 Pro Highest judge_pass_independently_replayed ledger: 36m 58.0s wall-clock, 2.19M processed, and $0.15 Provider-recorded usage estimate, not an itemized subscription cash charge.
Run identity and stack
- Result ID: dex-draw-mujoco-mimo-v2.6-pro-max-opencode-go-2026-09-23
- Technical model: Xiaomi MiMo v2.6 Pro
- Provider: OpenCode Go
- Client: OpenCode 1.18.23
- Variant: max
- Stack: OpenCode Go
- Stack: OpenCode 1.18.23
- Stack: Technical model/configuration: Xiaomi MiMo v2.6 Pro
- Stack: Requested variant: max
- Stack: MuJoCo pencil-drawing fixture
- Stack: Harness drawing prompt
- Stack: Requested tool profile: python-mujoco-headless
Primary artifact integrity
- Kind: open-loop-1khz-actuator-log
- Path: artifacts/dex-draw-mujoco-mimo-v2.6-pro-max-opencode-go-2026-09-23/evidence/model-supplied/ctrl.npy
- SHA-256: fd223337375c170cec6af5cf9f8d2b17818c67b32fec4e74d3e59d1296f19fb5
Validation evidence
- Result: pass
- Path: artifacts/dex-draw-mujoco-mimo-v2.6-pro-max-opencode-go-2026-09-23/validation/judge-replay.public.json
- SHA-256: 5489d5e330622b5a98ee504eb1bfb579fbe69387645ca207703d0e3b14295dd5
- Validator SHA-256: 5c7af1a85044163afefca6abcd1ea9a19b109bf045ed8be40b4d5796098b738d
Recorded caveats
- The judge measures task completion only; there is no visual quality or blind evaluation for this task.
- The replay clips are rendered by the operator's viewer from the judge's own trajectory export with a fixed camera; they are presentation evidence, not a measurement.
- Wall clock is end-to-end workflow latency including the solver's own simulation and judge runs, not model-only compute.
- Cost is the OpenCode-recorded figure. OpenCode Go subscription ($0 charged). OpenRouter-list API-equivalent at $0.435 in / $0.87 out per MTok equals the recorded figure.
- provenance/orchestrator-results.md is the task project's own result section copied with absolute local paths and session ids replaced.
- The raw OpenCode receipts carry the session id, the reasoning transcript and local paths; they are not committed, only their sha256 commitments in provenance/source-receipt-hashes.json.
- A Blender Cycles HERO RE-RENDER of this judged replay is pinned in provenance/clips.public.json as presentation: cycles-hero. Poses identical, visual layer only; pipeline ~/hero-render; two RTX 4090 Secure pods EUR-IS-1 + US, 62.7 + 77.4 min, $0.77 + $0.95, plus a third RTX 4090 Secure (US) for draw (~161 min, $1.99, operator-killed) = $3.71 total. FAIL episodes rendered as-is. It is not a new run, adds no measurement and cannot change a verdict. It is not committed; it is pinned by name, sha256, bytes, frames and duration.
- Nudge disclosure: none.
- The harness self-check archive under evidence/sim-attempts/ is committed exactly as the harness wrote it, so its attempt records still carry the operator's workspace path in their cwd field.
- The first draw launch died on step_finish reason=length and is pinned in provenance/interrupted-2026-09-23.json; it is not scored.
Visible evidence gaps
- hardware and interpreter receipt from the solver session (only the operator's replay environment is recorded)
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.