Kimi K3 in OpenCode 1.18.32
skills off
Zoom, inline player and more ways to view
Wall time 11m 47sCost $0.49 reported9.0/10 · Draft score — AI judge
Review
Charming flat illustration: a helmeted pelican with a clear pouch leans over the bars (wing on the grip), both legs running down to the crank, on a red bike with a wicker basket.
The full review
Charming flat illustration: a helmeted pelican with a clear pouch leans over the bars (wing on the grip), both legs running down to the crank, on a red bike with a wicker basket. The saddle is hidden under the body, and the legs cut across the frame tubes a bit awkwardly.
Verdict by the AI judge (provisional).
OK. Finished on its own after 11.8 min and produced pelican.svg.
Bugs
- saddle hidden under body
- legs overlap frame awkwardly
Scores
AI judge
9.0/10
Draft score — AI judge
Visitor votes and reviewer grades are not available yet.
| Criterion | Marks |
|---|---|
| pelican | 2 |
| bicycle | 1.5 |
| riding | 2 |
| composition | 2 |
| craft | 1.5 |
| Total (sum of the marks) | 9 / 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), 234 characters. Every result for this prompt
Generate an SVG of a pelican riding a bicycle. Save it as pelican.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 machine-format transcript is published as a scrubbed download.
Show all 16 steps
Loading the timeline…
Download the full transcript OpenCode session export, 99 KB. 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 $0.49, as reported by OpenCode (its own bill for the run). The list-price estimate from the token counts is $0.49.
| Tokens by type | Tokens | $ per 1M | Cost |
|---|---|---|---|
| Input (uncached) | 31,265 | $3.00 | $0.0938 |
| Cache write | 0 | $0.00 | $0 |
| Cache read | 192,854 | $0.30 | $0.0579 |
| Output | 5,695 | $15.00 | $0.0854 |
| reasoning | 17,068 | $15.00 | $0.2560 |
- Total computed from tokens
- $0.4931
- Total reported by the harness
- $0.4931
- Difference
- computed 0.2371 vs harness 0.4931
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: models.dev catalog as loaded by OpenCode 1.18.32 (read 2026-09-23) (Moonshot kimi-k3 list price), 2026-09-23.
Run notes
- a well-known benchmark wording "Generate an SVG of a pelican riding a bicycle" (a full stop added before the harness suffix).
- 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