BuilderBuilder
Measured harness ledgerPublic result
GPT-6 Astra

Eiffel Tower Drawing — GPT-6 Astra Max

Draw the Eiffel Tower with a friction-held pencil on a Marvin arm and Wuji hand in MuJoCo.

Max reasoningHeadline result
Workflow cost
$1.37
Wall-clock
4m 10s wall-clock
Processed tokens
475K processed
Record state
judge_pass_independently_replayed
Public summary

GPT-6 Astra Max judge_pass_independently_replayed ledger: 4m 10s wall-clock, 475K processed, and $1.37 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-draw-mujoco-gpt-6-astra-max-codex-2026-09-19
  • Technical model: GPT-6 Astra
  • Provider: OpenAI Codex
  • Client: codex-sub wrapper (detached, headless, -l dexdraw-astra -m gpt-6-astra -e max -s danger-full-access -t 7200), Codex CLI 0.154.0; ran to its own end_turn
  • Stack: OpenAI Codex
  • Stack: codex-sub wrapper (detached, headless, -l dexdraw-astra -m gpt-6-astra -e max -s danger-full-access -t 7200), Codex CLI 0.154.0; ran to its own end_turn
  • Stack: Technical model/configuration: GPT-6 Astra
  • Stack: MuJoCo pencil-drawing fixture
  • Stack: Harness drawing 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-draw-mujoco-gpt-6-astra-max-codex-2026-09-19/evidence/model-supplied/ctrl.npy
  • SHA-256: cb2eb839d6242eeccd0cb72c8f60c2d42917801008806531d098f44a0d8f6708
Validation evidence
  • Result: PASS
  • Path: artifacts/dex-draw-mujoco-gpt-6-astra-max-codex-2026-09-19/validation/judge-replay.public.json
  • SHA-256: 20fce7279ebff75f1b780339a53c0ab09e0928f3bb2d890d185134a4bf363d47
  • 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.
  • 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 given harness/checker exposes the judge's own scoring in-process, so the solver could self-score without the operator; wall clock and cost are NOT comparable with the dex-cube-turn-mujoco cohorts.
  • usedThreeFingers / threeFingerFraction are reported, never gating.
  • 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.

Browse BuilderReturn to GPT-6 Astra
RemakeBenchResearch console