Claude Opus 5.5 in OpenCode 1.18.32
skills off
Showing a WebP render of the 247 KB SVG so the page loads fast; zooming loads the SVG itself.
This is the unfinished output at the moment the run ended (Stopped by us). See the review below.
Wall time 25m 25sCost $3.87 reported
Review
Stopped by us (memory) about 25 minutes in, so not scored. The work-in-progress file was already strong: consistent three-quarter view, menu bar, dock, a flowing ribbon wallpaper and a glowing screen. A clean rerun is queued as attempt2.
Verdict by the AI judge (provisional).
The full review
Stopped by us. Stopped by us at 22:25:44Z (about 25 min in) to protect the shared box: available memory fell to 402 MB, under the 700 MB operator threshold set at 22:24Z. Not a model failure. The macbook.svg shown is the agent's work-in-progress file at the moment it was stopped (it had written it at 22:15 and was still refining).
Attempt 1 of 3
Every try of this model in this harness on this prompt, oldest first. A later attempt is the cell's result: attempt 3.
Scores
Not scored: only runs that finished on their own are scored.
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 7.0 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 OpenCode session export, 58 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 $3.87, as reported by OpenCode (its own bill for the run). The list-price estimate from the token counts is $3.87.
| Tokens by type | Tokens | $ per 1M | Cost |
|---|---|---|---|
| Input (uncached) | 36 | $4.00 | $0.0001 |
| Cache write | 260,512 | $5.00 | $1.3026 |
| Cache read | 1,560,461 | $0.20 | $0.3121 |
| Output | 31,579 | $20.00 | $0.6316 |
| reasoning | 80,940 | $20.00 | $1.6188 |
- Total computed from tokens
- $3.8652
- Total reported by the harness
- $3.8652
- Difference
- computed 2.2464 vs harness 3.8652
Tokens from OpenCode per-message usage; harness total = sum of OpenCode per-message cost. OpenCode reports reasoning separately; both bill at the output rate (output line here = output only, see reasoning).
Prices: Project price table (vendor list prices); cache write 1.25x input, 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.
- Mode: interactive TUI in tmux (160x48), inside bubblewrap sandbox
- Isolation: bwrap: private /tmp and /run, private PID ns; only this run dir, harness binaries (ro), opencode config, /usr, /etc bound; HOME/TMPDIR/XDG data private; the project files and other runs not mounted