Measured harness ledgerPublic result
GPT-6 AstraDex Cube — 3 Move — GPT-6 Astra Max
Complete the three-move Rubik's cube sequence D, F', U2 with regrasp, using two dexterous hands in MuJoCo.
Max reasoningHeadline result
- Workflow cost
- $15.97
- Wall-clock
- 43m 04s wall-clock
- Processed tokens
- 10.45M processed
- Record state
- judge_pass_independently_replayed
Public summary
GPT-6 Astra Max judge_pass_independently_replayed ledger: 43m 04s wall-clock, 10.45M processed, and $15.97 Standard API-equivalent estimate from the Codex wrapper receipt, not a subscription invoice: this was a ChatGPT-subscription run, $0 was charged and Codex emits no cost field..
Run identity and stack
- Result ID: dex-cube-turn-mujoco-stage-2-three-moves-gpt-6-astra-max-codex-2026-09-19
- Technical model: GPT-6 Astra
- Provider: OpenAI Codex
- Client: codex-sub wrapper (detached, headless, -l dexcube3-astra -m gpt-6-astra -e max -s danger-full-access -t 13500), Codex CLI 0.154.0; ran to its own end_turn
- Stack: OpenAI Codex
- Stack: codex-sub wrapper (detached, headless, -l dexcube3-astra -m gpt-6-astra -e max -s danger-full-access -t 13500), Codex CLI 0.154.0; ran to its own end_turn
- Stack: Technical model/configuration: GPT-6 Astra
- Stack: MuJoCo dexterous-hand fixture
- Stack: Harness cube-turn stage-2 prompt
- Stack: Requested tool profile: python-mujoco-headless
Cost basis
- actual marginal subscription charge usd: $0.00 USD.
Primary artifact integrity
- Kind: open-loop-1khz-actuator-log
- Path: artifacts/dex-cube-turn-mujoco-stage-2-three-moves-gpt-6-astra-max-codex-2026-09-19/evidence/model-supplied/ctrl.npy
- SHA-256: 2151970d9c59ff806d1a4e67bfd4b4b2dfe4607dc2e2d2262a5f6f54d374f4b6
Validation evidence
- Result: PASS
- Path: artifacts/dex-cube-turn-mujoco-stage-2-three-moves-gpt-6-astra-max-codex-2026-09-19/validation/judge-replay.public.json
- SHA-256: 319ed31d7cbced9724a38da7fca78ab00d340fc50920fead7382fbb4b02857dc
- Validator SHA-256: 329a7f94ec9d9a37edbb94b6fcad5a2e48e32aca160e93e683f5de2763f4ab34
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.
- Output tokens include hidden reasoning, visible prose and tool-call JSON; cache reads are discounted, so processed-token volume overstates effective cost.
- This was a ChatGPT-subscription Codex run, so there is no dollar receipt: $0 was charged and Codex emits no cost field. The dollar figure is an API-equivalent estimate at the GPT-6 Astra list rates already on record in this harness, not an invoice.
- provenance/orchestrator-results.md is the task project's own result section copied verbatim with absolute local paths replaced.
- 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 raw Codex receipts (events.jsonl, meta.json, prompt and final-message files) carry the session id, the full reasoning transcript and local paths; they are not committed, only their sha256 commitments in provenance/source-receipt-hashes.json.
- The judge archive and the harness archive hash the control log on different bases, so a judge attempt and the harness self-check of the SAME trajectory carry different ctrl_sha256 values; both archives are committed verbatim and the underlying .npy files were checked byte for byte.
- The harness self-check records carry passed/reason fields the harness never fills in for an unjudged simulation; those entries are surfaced with judged: false.
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.