Grok 4.7 in Grok Build 1.0.41
skills off
Zoom, inline player and more ways to view
Showing a WebP render of the 156 KB SVG so the page loads fast; zooming loads the SVG itself.
Wall time 41m 45sCost $7.66 reported8.5/10 · Draft score — stored total; criterion breakdown unavailable
Review
Convincing MacBook Pro 16 in three-quarter view: notch with camera, speaker grilles either side of the keyboard, a large trackpad and side ports, with a lit macOS-style desktop (window, dock, gradient wallpaper) and a soft blue light spill.
The full review
Convincing MacBook Pro 16 in three-quarter view: notch with camera, speaker grilles either side of the keyboard, a large trackpad and side ports, with a lit macOS-style desktop (window, dock, gradient wallpaper) and a soft blue light spill. The keyboard rows warp slightly toward the left, the base has almost no contact shadow, and the aluminium shading is flat.
Verdict by the AI judge (provisional).
OK. Finished on its own after 41.8 min and produced macbook.svg.
Bugs
- keyboard rows warp slightly on the left
- little contact shadow
- flat aluminium shading
Scores
AI judge
8.5/10
Draft score — stored total; criterion breakdown unavailable
Visitor votes and reviewer grades are not available yet.
Draft score — stored total; criterion breakdown unavailable. the per-criterion marks could not be read, so the stored score is shown; the displayed total has not been verified through a criterion breakdown.
- 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
3 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 6.8 MB; it is published as a scrubbed, compressed download rather than shown on the page.
Show all 2 steps
Loading the timeline…
Download the full transcript transcript, 201 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 $7.66, as reported by Grok Build (its own bill for the run). The list-price estimate from the token counts is $5.81.
| Tokens by type | Tokens | $ per 1M | Cost |
|---|---|---|---|
| Input (uncached) | 343,895 | $2.00 | $0.6878 |
| Cache write | 0 | $0.00 | $0 |
| Cache read | 8,209,024 | $0.50 | $4.1045 |
| Output | 169,958 | $6.00 | $1.0197 |
| of which reasoning | 127,741 | billed as output |
- Total computed from tokens
- $5.8121
- Total reported by the harness
- $7.6555
- Difference
- computed 5.8121 vs harness 7.6555
Tokens from Grok Build's own per-session usage.json (inputTokens include cached reads; uncached = input - cachedRead; outputTokens include reasoning). Harness total = Grok Build costUsdTicks / 1e10 (its own xAI price table, incl. >200K tiers). Tool calls/turns from the ACP updates.jsonl.
Prices: models.dev catalog as loaded by OpenCode 1.18.32 (read 2026-09-23); matches the xAI list price ($2 in / $0.50 cached / $6 out). Requests whose context exceeds 200K bill at 2x ($4/$1/$12); per-request context is not logged by OpenCode, so the base rate is applied (Grok Build's own cost figure does apply its tiers), 2026-09-23.
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.
- Mode: interactive TUI in tmux (160x48), inside bubblewrap sandbox
- Isolation: bwrap: private /tmp, /run, PID/IPC/UTS ns; HOME, TMPDIR and the harness home (sessions, config copy) inside this run dir; only /usr, /etc, the harness binary dir(s) (ro) and this run dir bound; the project files, results/, other runs, /tmp/hx_* not mounted