AI Model Reviewer

Claude Opus 5.5 in Claude Code 2.1.280

skills off

← Open in the gallerySame prompt, all models

Claude Opus 5.5's SVG for Animated pelican riding a bicycle (SMIL/CSS)

OKAnimated pelican riding a bicycle (SMIL/CSS)max effortHome harness

Wall time 35m 10sCost $4.96 reported10.0/10 · Draft score — AI judge

Open the SVG filePoster render (WebP)

Review

Excellent pure-SMIL animation (no script): both wheels spin clockwise (0 to 720 deg per 1.5 s, correct for rightward travel), the crank turns once per loop, and inverse-kinematics leg angles keep both feet on the pedals with bending knees.

The full review

Excellent pure-SMIL animation (no script): both wheels spin clockwise (0 to 720 deg per 1.5 s, correct for rightward travel), the crank turns once per loop, and inverse-kinematics leg angles keep both feet on the pedals with bending knees. Scarf, head and body bob on sub-loops of the same 1.5 s cycle, so the loop is seamless. The pelican itself is well drawn (pouch, crest, basket with a fish). No visible glitches in the 6 frames.

Verdict by the AI judge (provisional).

OK. Finished on its own after 35.2 min and produced pelican_animated.svg.

Scores

AI judge

10.0/10

Draft score — AI judge

Visitor votes and reviewer grades are not available yet.

CriterionMarks
pelican + bicycle drawn2
wheels + crank rotate2
legs in sync2
seamless loop, no JS2
craft2
Total (sum of the marks)10 / 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

Wall time 35m 10sFirst artifact at 12m 38s8 saved versions

Versions saved during the run

8 intermediate outputs, in the order the model wrote them.

Version 8 of 8
  1. v1 12:32
  2. v2 17:34
  3. v3 18:15
  4. v4 19:47
  5. v5 20:28
  6. v6 20:50
  7. v7 21:21
  8. v8 23:23

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 9.8 MB; it is published as a scrubbed, compressed download rather than shown on the page.

Show all 59 steps

Loading the timeline…

Download the full transcript Claude Code session JSONL, 125 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 $4.96, as reported by Claude Code (its own bill for the run). The list-price estimate from the token counts is $4.95.

Tokens by typeTokens$ per 1MCost
Input (uncached)90$4.00$0.0004
Cache write210,688$5.00$1.0534
Cache read6,119,067$0.20$1.2238
Output133,601$20.00$2.6720
of which reasoningnot recordedbilled as output
Total computed from tokens
$4.9496
Total reported by the harness
$4.9600
Difference
computed $4.95 vs reported $4.96 (diff -0.01)

Tokens summed from the Claude Code session JSONL (per message id, incl. subagent files); harness total from /cost.

Prices: Project price table (vendor list prices); cache write 1.25x input, 2026-09-22.

Run notes

one prompt, agentic harness (self-review allowed)wave 1

  • 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
6 frames at t=0, 0.25, 0.5, 0.75, 1.25, 2.0 s (SMIL/CSS clock set per frame)
6 frames at t=0, 0.25, 0.5, 0.75, 1.25, 2.0 s (SMIL/CSS clock set per frame)