GPT-6 Astra in Codex CLI 0.156.1
skills off
Zoom, inline player and more ways to view
Showing a WebP render of the 427 KB SVG so the page loads fast; zooming loads the SVG itself.
Wall time 15m 48sCost $2.23 estimated8.5/10 · Draft score — AI judge
Review
A clean light-studio product shot with a strong wallpaper and crisp aluminium, keyboard, trackpad and speaker grilles.
The full review
A clean light-studio product shot with a strong wallpaper and crisp aluminium, keyboard, trackpad and speaker grilles. The lid is drawn close to front-on while the base is angled, so the two halves don't quite share one vanishing point, and with a white backdrop the 'screen glow' barely reads. No menu bar or dock.
Verdict by the AI judge (provisional).
OK. Finished on its own after 15.8 min and produced macbook.svg.
Bugs
- Lid perspective is flatter than the base (inconsistent vanishing)
- No UI on screen (no menu bar/dock/clock)
- Screen glow weak against the light background
Scores
AI judge
8.5/10
Draft score — AI judge
Visitor votes and reviewer grades are not available yet.
| Criterion | Marks |
|---|---|
| recognisable | 2 |
| perspective | 1.5 |
| screen glow | 1.5 |
| aluminium | 2 |
| craft | 1.5 |
| Total (sum of the marks) | 8.5 / 10 |
- AI judge
- AI judge: the test runner (model claude-opus-5-5), scoring by visual review of the 1600 px render against the pre-registered rubric. A draft score until the reviewer checks it. Rubric: Wave-1 SVG scoring rubric (AI Model Reviewer).
- Visitors
- Public voting with a blind reveal is coming: you score the output first, then see the other scores.
- Reviewer
- The reviewer's own grade appears here once it is added.
Scores compare results for the same prompt only. AI-judge boards rank runs within one prompt, equal totals sharing a rank; scores from different prompts are never averaged.
Downloads
Files actually published for this run. Original output, site-made previews and post-run conversions are labelled separately.
The exact prompt
agentic harness (save the file; self-render allowed), 373 characters. Every result for this prompt
Generate an SVG that looks like a realistic 3D render of a MacBook Pro 16" (opened, slight three-quarter view, screen glow, aluminum body). Use gradients and perspective to fake the 3D. Save it as macbook.svg in the current directory. You may render and inspect your own output (headless chromium is available at /usr/bin/chromium) and iterate on your own before finishing.
How it was made
Versions saved during the run
2 intermediate outputs, in the order the model wrote them.
Step by step
The prompt, every agent turn and tool call (tool name and a one-line summary; inputs and outputs are not shown), then the final message. The full transcript is 3.0 MB; it is published as a scrubbed, compressed download rather than shown on the page.
Show all 39 steps
Loading the timeline…
Download the full transcript Codex CLI rollout JSONL, 54 KB, gzip. Scrubbed: anything that looks like a key, token, e-mail address or phone number is replaced, and account details and the test machine's file paths are removed.
Cost breakdown
Headline cost $2.23, estimated from the token counts at list price.
| Tokens by type | Tokens | $ per 1M | Cost |
|---|---|---|---|
| Input (uncached) | 44,149 | $10.00 | $0.4415 |
| Cache read | 602,354 | $1.00 | $0.6024 |
| Output | 23,808 | $50.00 | $1.1904 |
| of which reasoning | 9,053 | billed as output |
- Total computed from tokens
- $2.2342
- Total reported by the harness
- none
Tokens from the Codex rollout token_count events (Codex prints no dollar figure); reasoning is part of output.
Prices: Project price table; OpenAI Standard tier, requests whose prompt is >272K tokens bill at 2x input/cache and 1.5x output (applied per request where per-request usage is logged), 2026-09-22.
Run notes
- Playcode MacBook SVG Benchmark prompt verbatim, except its last sentence ("Respond with ONLY the SVG markup, no explanation.") is swapped for the save-to-file harness suffix, as the prompt research recommends for harness runs.
- per-request tiering: requests with a prompt above 272K tokens billed at 2x input/cache, 1.5x output
- Mode: interactive TUI in tmux (160x48), inside bubblewrap sandbox
- Isolation: bwrap: private /tmp, HOME and TMPDIR inside run dir, own CLAUDE_CONFIG_DIR/CODEX_HOME copy; the project files, other runs, /tmp/hx_* not mounted