Kimi K3 in Kimi Code CLI 2.1.0
skills off
Wall time 13m 32sCost $0.74 estimated9.5/10 · Draft score — AI judge
Review
Clean flat illustration: a white pelican with a long orange bill and a pale pouch sits on the saddle of a teal bike, its wing reaching the bars. Wheels spin clockwise and the crank turns on one 1.2 s cycle; the pedals counter-rotate to stay level.
The full review
Clean flat illustration: a white pelican with a long orange bill and a pale pouch sits on the saddle of a teal bike, its wing reaching the bars. Wheels spin clockwise and the crank turns on one 1.2 s cycle; the pedals counter-rotate to stay level. Jointed orange legs are keyframed so the feet stay on the pedals and the knees bend. The background scrolls on 9.6 s (8 cycles), the ground dashes on 0.3 s and the chain dash is timed to the cycle, so the loop is seamless; pure SMIL, no JavaScript. The body is a flat, simple shape and the legs are heavy strokes.
Verdict by the AI judge (provisional).
OK. Finished on its own after 13.5 min and produced pelican_animated.svg.
Bugs
- flat, simple body shape
- heavy leg strokes
Scores
AI judge
9.5/10
Draft score — AI judge
Visitor votes and reviewer grades are not available yet.
| Criterion | Marks |
|---|---|
| pelican + bicycle | 2 |
| wheels + crank | 2 |
| legs in sync | 2 |
| seamless loop, no JS | 2 |
| craft | 1.5 |
| Total (sum of the marks) | 9.5 / 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), 385 characters. Every result for this prompt
Generate an animated SVG of a pelican riding a bicycle: the wheels and pedals turn, the legs pedal in sync, and it loops seamlessly. Use only SVG/SMIL or CSS inside the SVG, no JavaScript. Save it as pelican_animated.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 machine-format transcript is published as a scrubbed download.
Show all 2 steps
Loading the timeline…
Download the full transcript transcript, 354 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 $0.74, estimated from the token counts at list price.
| Tokens by type | Tokens | $ per 1M | Cost |
|---|---|---|---|
| Input (uncached) | 54,830 | $3.00 | $0.1645 |
| Cache write | 0 | $0.00 | $0 |
| Cache read | 630,272 | $0.30 | $0.1891 |
| Output | 25,756 | $15.00 | $0.3863 |
| of which reasoning | not recorded | billed as output |
- Total computed from tokens
- $0.7399
- Total reported by the harness
- none
Tokens summed from every step.end usage in Kimi Code's wire.jsonl (main agent + any subagent wires): inputOther = uncached input, inputCacheRead, inputCacheCreation, output (reasoning is included in output, not split). Kimi Code prints no dollar figure: cost = tokens x Moonshot list price.
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
- 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
