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 GPU boids 50k

▶ 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. Tap inside for sound.

OKGPU boids 50khigh effortNeutral harness

Wall time 34m 57sCost $4.09 estimated

Review

No verdict yet.

The full review

OK. Finished on its own after 35.0 min.

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, 1,483 characters. Every result for this prompt

Build a single-page WebGPU compute-shader boids visualizer that runs 50,000 boids at 60fps, with a CPU (JS) mode capped at 2,000 for side-by-side comparison. Show separation/alignment/cohesion sliders, a predator that follows the mouse, spatial hashing grid overlay toggle, and an FPS + ms-per-step readout for each mode so the speedup is visible. Include a short in-page explanation panel of the algorithm and the spatial hash. One HTML file, no external assets. The GPU mode must use a WebGPU compute shader when navigator.gpu is available and otherwise fall back to a WebGL2 GPU path (for example float-texture ping-pong) so it still runs 50,000 boids where WebGPU is missing; label which GPU path is active. Make the page start a demo on load with no input (the predator follows a scripted path until the mouse moves) so a headless capture shows constant motion.

Save it as index.html in the current directory: one self-contained file with inline CSS and JavaScript only, no libraries or frameworks, and no external requests of any kind (no CDNs, web fonts, images or audio files). It must work when opened directly from disk, fit any window from a 390 px wide phone to a desktop, and run without console errors. You may serve it locally and open it in headless chromium (/usr/bin/chromium, software WebGL, no GPU, no WebGPU) 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 34m 57sFirst artifact at 11m 20s12 saved versions

Versions saved during the run

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

Version 12 of 12
  1. Version 1 at 11m 23s thumbnailv1 11:23
  2. Version 2 at 11m 28s thumbnailv2 11:28
  3. Version 3 at 13m 49s thumbnailv3 13:49
  4. Version 4 at 14m 54s thumbnailv4 14:54
  5. Version 5 at 16m 15s thumbnailv5 16:15
  6. Version 6 at 16m 50s thumbnailv6 16:50
  7. Version 7 at 21m 58s thumbnailv7 21:58
  8. Version 8 at 31m 53s thumbnailv8 31:53
  9. Version 9 at 32m 33s thumbnailv9 32:33
  10. Version 10 at 33m 19s thumbnailv10 33:19
  11. Version 11 at 33m 49s thumbnailv11 33:49
  12. Version 12 at 34m 19s thumbnailv12 34:19

No transcript was delivered with this result.

Cost breakdown

Headline cost $4.09, estimated from the token counts at list price.

Tokens by typeTokens$ per 1MCost
Input (uncached)80$4.00$0.0003
Cache write146,669$5.00$0.7333
Cache read5,121,348$0.20$1.0243
Output116,649$20.00$2.3330
of which reasoning58,710billed as output
Total computed from tokens
$4.0909
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)

  • frozen prompt (written): written 2026-10-05 from an idea-scan prompt, with a WebGL2 GPU fallback, auto-demo and the standard suffix, because the capture boxes have no WebGPU; category algorithm_visualizers; 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: none
  • Renderer: WebGPU compute + render (getContext('webgpu') at index.html line 618) with a WebGL2 fallback (getContext('webgl2') at line 886) and a Canvas 2D CPU view (getContext('2d') at line 1077); in the headless Chromium console check (no WebGPU available) the WebGL2 fallback ran (page badge "GPU path: WebGL2 fallback (float-texture ping-pong)"), 0 console errors, 0 page errors; single self-contained index.html, no CDN and no external assets. Card: the run's own render.png poster (session capture too short for a card video).
  • Same frozen prompt as the other rows on this test; configurations differ and all rows are unscored, so this is not a head-to-head result.