AI Model Reviewer

Claude Opus 5.5 in Pi 0.87.1 + skills kit (ponytail, ECC, vetted skills)

skills off

← Open in the gallerySame prompt, all models

Claude Opus 5.5's output for GPU fluid sim

▶ 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).

OKGPU fluid simmax effortNeutral harness

Wall time 49m 01sCost $4.78 reported

Snapshot 18 of 18 saved during Claude Opus 5.5's run
  1. Snapshot 1 of 18 saved during Claude Opus 5.5's run
  2. Snapshot 3 of 18 saved during Claude Opus 5.5's run
  3. Snapshot 6 of 18 saved during Claude Opus 5.5's run
  4. Snapshot 8 of 18 saved during Claude Opus 5.5's run
  5. Snapshot 11 of 18 saved during Claude Opus 5.5's run
  6. Snapshot 13 of 18 saved during Claude Opus 5.5's run
  7. Snapshot 16 of 18 saved during Claude Opus 5.5's run
  8. Snapshot 18 of 18 saved during Claude Opus 5.5's run
Still frames from a low-frame-rate recording made during the run (under 12 fps, so not shown as video): 18 distinct frames.

Review

No verdict yet.

The full review

OK. Finished on its own after 49.0 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, 664 characters. Every result for this prompt

Build a GPU-accelerated fluid simulation in a single HTML file using WebGL, no external libraries. Dragging the mouse or a finger should push colorful dye through the fluid, with a soft glow. Make it look stunning and run smoothly.

Build it as a self-contained index.html in the current directory, with WebGL/WebGL2 shaders you write yourself; no libraries and no CDNs; interactive with mouse or touch input. 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 49m 01sFirst artifact at 7m 54s11 saved versions

Versions saved during the run

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

Version 11 of 11
  1. Version 1 at 7m 57s thumbnailv1 7:57
  2. Version 2 at 12m 30s thumbnailv2 12:30
  3. Version 3 at 17m 57s thumbnailv3 17:57
  4. Version 4 at 20m 34s thumbnailv4 20:34
  5. Version 5 at 28m 14s thumbnailv5 28:14
  6. Version 6 at 36m 52s thumbnailv6 36:52
  7. Version 7 at 38m 23s thumbnailv7 38:23
  8. Version 8 at 39m 18s thumbnailv8 39:18
  9. Version 9 at 40m 09s thumbnailv9 40:09
  10. Version 10 at 42m 35s thumbnailv10 42:35
  11. Version 11 at 44m 41s thumbnailv11 44:41

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, 619 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 $4.78, as reported by Pi 0.87.1 + skills kit (ponytail, ECC, vetted skills) (its own bill for the run). The list-price estimate from the token counts is $4.78.

Tokens by typeTokens$ per 1MCost
Input (uncached)116$4.00$0.0005
Cache write179,753$5.00$0.8988
Cache read6,806,762$0.20$1.3614
Output126,151$20.00$2.5230
of which reasoningnot recordedbilled as output
Total computed from tokens
$4.7836
Total reported by the harness
$4.7836
Difference
matches

Pi 0.87.1 + skills kit (ponytail, ECC, vetted skills) reported its own total; token counts x list prices shown beside it. usage from the harness's own JSON events (message_end usage; cost.total as reported)

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

Run notes

one prompt, agentic harness (self-review allowed)labelled re-run (of gpu_fluid_sim__pi-kitted__opus-5-5)headless mode (TUI not automatable)

  • frozen prompt (written): engine/prompts_written/gpu_fluid_sim.txt: Voxyz's own prompt verbatim (x.com/Voxyz_ai/status/2103088468762960378) + our fixed inputs (self-contained index.html, own WebGL/WebGL2 shaders, no libraries/CDNs, mouse/touch input) (supervisor 725c3fc2 05:53Z; zero results)
  • Pi 0.87.1 + skills kit (ponytail, ECC, vetted skills): headless one-shot mode (TUI not automatable), run in tmux for screenshots
  • Mode: headless mode (TUI not automatable) — pi --mode json in tmux, inside bubblewrap
  • Isolation audit: outside paths seen