AI Model Reviewer

GPT-6 Sol in Codex CLI 0.156.1

skills off

← Open in the gallerySame prompt, all models

GPT-6 Sol's output for Webgpu ink marbling

▶ Open live demo

Zoom, inline player and more ways to view
Poster frame of GPT-6 Sol'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).

OKWebgpu ink marblingmax effortNeutral harness

Wall time 17m 10sCost $3.16 estimated

Review

No verdict yet.

The full review

OK. Finished on its own after 17.2 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, 1,055 characters. Every result for this prompt

Build a single-file WebGPU (with WebGL2 fallback) paper-marbling simulator (ebru / suminagashi). Users drop ink colors onto a water surface, then drag combs and styluses to rake the ink into feathered and peacock patterns, using a real-time 2D fluid solver (advection + pressure projection) on the GPU. Include 6 ink colors, comb/stylus/drop tools, a 'press paper' button that freezes the pattern into a printed sheet with paper texture, and an IDLE AUTO-PLAY mode that drops ink and rakes classic patterns on its own when untouched for 5 seconds. Target 60 fps at 1080p. Output one index.html, no external assets. Save the main page as index.html in the current directory (plus any local asset files you create), with no build step. 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. Finish with a short README.md describing the controls.

How it was made

Wall time 17m 10sFirst artifact at 3m 07s22 saved versions

Versions saved during the run

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

Version 22 of 22
  1. Version 1 at 3m 09s thumbnailv1 3:09
  2. Version 2 at 3m 50s thumbnailv2 3:50
  3. Version 3 at 4m 30s thumbnailv3 4:30
  4. Version 4 at 5m 00s thumbnailv4 5:00
  5. Version 5 at 5m 45s thumbnailv5 5:45
  6. Version 6 at 7m 22s thumbnailv6 7:22
  7. Version 7 at 7m 27s thumbnailv7 7:27
  8. Version 8 at 7m 37s thumbnailv8 7:37
  9. Version 9 at 7m 52s thumbnailv9 7:52
  10. Version 10 at 8m 07s thumbnailv10 8:07
  11. Version 11 at 8m 52s thumbnailv11 8:52
  12. Version 12 at 9m 38s thumbnailv12 9:38
  13. Version 13 at 10m 44s thumbnailv13 10:44
  14. Version 14 at 10m 49s thumbnailv14 10:49
  15. Version 15 at 11m 30s thumbnailv15 11:30
  16. Version 16 at 11m 50s thumbnailv16 11:50
  17. Version 17 at 12m 52s thumbnailv17 12:52
  18. Version 18 at 13m 27s thumbnailv18 13:27
  19. Version 19 at 14m 13s thumbnailv19 14:13
  20. Version 20 at 14m 18s thumbnailv20 14:18
  21. Version 21 at 15m 14s thumbnailv21 15:14
  22. Version 22 at 17m 01s thumbnailv22 17:01

No transcript was delivered with this result.

Cost breakdown

Headline cost $3.16, estimated from the token counts at list price.

Tokens by typeTokens$ per 1MCost
Input (uncached)258$2.00$0.0005
Cache write153,974$2.00$0.3079
Cache read8,846,570$0.20$1.7693
Output108,626$10.00$1.0863
of which reasoning58,300billed as output
Total computed from tokens
$3.1640
Total reported by the harness
none

Computed from harness-reported token counts x list prices. Cache writes priced at the input rate (the price table has no separate cache-write price). No request above 272,000 input tokens (86 checked): standard rates.

Prices: Project price table, 2026-09-25.

Run notes

one prompt, agentic harness (self-review allowed)

  • frozen prompt (written): X-idea prompt queue (frozen in prompts_queue), MR wave 5 Three.js/WebGPU expansion; category threejs; IDLE AUTO-PLAY mode in prompt; engine threejs harness suffix appended; zero results
  • plain CODEX_HOME copy (config.toml only, run work/ trusted; no AGENTS.md/skills/state)
  • Mode: interactive TUI in tmux (160x48), inside bubblewrap sandbox
  • Isolation audit: outside paths seen
  • Renderer: WebGPU when an adapter is available (navigator.gpu.requestAdapter, site/index.html line 1948; WebGPUBackend at line 1371), otherwise its WebGL2 engine (WebGLBackend, getContext('webgl2') at line 1180; fallback at line 1974). The live demo runs in any WebGL2 browser.
  • Card video: the run's own 8 s session capture of the idle auto-play mode (78 frames, 1280x720, headless Chromium, no GPU), re-encoded as H.264. Poster: the run's own render.png. Neither capture shows on screen which backend ran.