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 output for Momijigari

▶ Open live demo

Zoom, inline player and more ways to view
Poster frame of Claude Opus 5.5's page
Open the original page

The model's own page, run in a sandboxed frame only when you ask (a page that needs its own origin opens in a new tab on a separate demo site). Phones get a full-screen player capped at 1.5x pixel density (2x on larger screens) so it stays smooth; the original page runs uncapped. It starts in its auto-tour (T switches to play mode on a keyboard).

Recorded from the live demo (stepped clock). Preview video recorded by this site from the live demo. The moving picture above is that preview; the button runs the real page.

OKMomijigarimax effortNeutral harness

Wall time 2h 47mCost $28.88 estimated

Snapshot 1 of 1 saved during Claude Opus 5.5's run
Still snapshots saved during the run (the moving picture above was recorded from the live demo): 1 distinct frame.

Generation timelapse

Poster for generation timelapse

Generation timelapse (the agent's screen during the run, sped up). This is not the finished video. Download video (3.2 MB).

Review

No verdict yet.

The full review

OK. Finished on its own after 167.7 min.

Attempt 3 of 3

Every try of this model in this harness on this prompt, oldest first. This run is the cell's result.

  1. Attempt 1 ended in an infrastructure failure, not a model result20m 04s$0.272026-09-26
  2. Attempt 2 Stopped by us43m 04s$6.432026-09-26
  3. Attempt 3 OK this run2h 47m$28.882026-09-26

Scores

AI judge

Not scored

No rubric for this prompt

Visitor votes and reviewer grades are not available yet.

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. No AI-judge score exists for this result: there is no rubric for this prompt, so no score is shown and none is made up.
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

as run, 1,341 characters. Every result for this prompt

Build an interactive Three.js scene of a single red Japanese maple (momiji) standing on a small rocky island in a still, misty lake. Its leaves are deep autumn red and orange; some drift down onto the water, where they float and leave gentle ripples. Low mist hangs over the lake and soft mountain silhouettes fade into the haze behind. A stone lantern stands beside the tree with a warm flame inside. Let the viewer interact: dragging across the water stirs the floating leaves and sends ripples through them, clicking the lantern makes it swing so its light sways across the water, and a dial turns the time of day from dawn through day and dusk to moonlight, changing the sky, the colour of the mist, the lighting and the reflections, with the moon and its reflection at night. Keep the mood calm and painterly, with a light wind moving the branches. Everything is built in code from Three.js geometry, shaders and materials; no external models or textures. Build it as index.html (plus any local asset files you create) in the current directory. Three.js may load from a pinned CDN. You may serve it locally and open it in headless chromium (/usr/bin/chromium, software WebGL, no GPU) to screenshot and inspect your own output, and iterate on your own before finishing. Close any browser you open as soon as you've taken your screenshot.

How it was made

Wall time 2h 47mFirst artifact at 49m 04s28 saved versions

Versions saved during the run

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

Version 28 of 28
  1. Version 1 at 49m 06s thumbnailv1 49:06
  2. Version 2 at 1h 02m thumbnailv2 1:02:40
  3. Version 3 at 1h 07m thumbnailv3 1:07:30
  4. Version 4 at 1h 07m thumbnailv4 1:07:46
  5. Version 5 at 1h 18m thumbnailv5 1:18:15
  6. Version 6 at 1h 23m thumbnailv6 1:23:10
  7. Version 7 at 1h 25m thumbnailv7 1:25:54
  8. Version 8 at 1h 39m thumbnailv8 1:39:09
  9. Version 9 at 1h 41m thumbnailv9 1:41:54
  10. Version 10 at 1h 45m thumbnailv10 1:45:25
  11. Version 11 at 1h 53m thumbnailv11 1:53:54
  12. Version 12 at 1h 54m thumbnailv12 1:54:09
  13. Version 13 at 2h 00m thumbnailv13 2:00:29
  14. Version 14 at 2h 01m thumbnailv14 2:01:42
  15. Version 15 at 2h 03m thumbnailv15 2:03:39
  16. Version 16 at 2h 11m thumbnailv16 2:11:14
  17. Version 17 at 2h 21m thumbnailv17 2:21:18
  18. Version 18 at 2h 23m thumbnailv18 2:23:58
  19. Version 19 at 2h 24m thumbnailv19 2:24:29
  20. Version 20 at 2h 25m thumbnailv20 2:25:10
  21. Version 21 at 2h 28m thumbnailv21 2:28:46
  22. Version 22 at 2h 30m thumbnailv22 2:30:08
  23. Version 23 at 2h 31m thumbnailv23 2:31:46
  24. Version 24 at 2h 32m thumbnailv24 2:32:48
  25. Version 25 at 2h 33m thumbnailv25 2:33:09
  26. Version 26 at 2h 34m thumbnailv26 2:34:59
  27. Version 27 at 2h 44m thumbnailv27 2:44:01
  28. Version 28 at 2h 45m thumbnailv28 2:45:56

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

Show all 153 steps

Loading the timeline…

Download the full transcript Claude Code session JSONL, 322 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 $28.88, estimated from the token counts at list price.

Tokens by typeTokens$ per 1MCost
Input (uncached)204$4.00$0.0008
Cache write2,797,845$5.00$13.99
Cache read27,422,730$0.20$5.4845
Output470,154$20.00$9.4031
of which reasoning328,006billed as output
Total computed from tokens
$28.88
Total reported by the harness
none

Computed from harness-reported token counts x list prices.

Prices: Project price table (vendor list prices), 2026-09-22.

Run notes

one prompt, agentic harness (self-review allowed)prompt rewritten after the 2026-09-24 box losslabelled re-run (of threejs_momijigari__claude-code__opus-5-5__attempt1)

  • frozen prompt (rewritten): engine/prompts_rewritten/threejs_momijigari.txt: written by us from the recorded description (zero results)
  • plain wave-1-equivalent cc_config copy (settings.json + .claude.json; no ECC files)
  • Mode: interactive TUI in tmux (160x48), inside bubblewrap sandbox
  • Context setting: 1M ([1m] model name)
  • Isolation audit: outside paths seen