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 snow physics

▶ 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 snow physicsmax effortNeutral harness

Wall time 16m 06sCost $2.82 estimated

Review

No verdict yet.

The full review

OK. Finished on its own after 16.1 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, 1,022 characters. Every result for this prompt

Build a single self-contained HTML file that renders a real-time snow simulation in the browser with WebGPU compute (fall back to WebGL2 if WebGPU is missing). Requirements: at least 200k particles simulated on the GPU; wind field the user can change with the mouse; snow accumulates on a simple terrain heightmap and on two primitive objects (a box and a sphere) so drifts visibly build up over time; a footprint/trail when the user drags across the ground; on-screen FPS and particle count; a reset button. No external assets; CDN imports allowed. Aim for 60 FPS on a laptop GPU. 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 16m 06sFirst artifact at 3m 27s19 saved versions

Versions saved during the run

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

Version 19 of 19
  1. Version 1 at 3m 30s thumbnailv1 3:30
  2. Version 2 at 4m 10s thumbnailv2 4:10
  3. Version 3 at 4m 56s thumbnailv3 4:56
  4. Version 4 at 5m 16s thumbnailv4 5:16
  5. Version 5 at 5m 56s thumbnailv5 5:56
  6. Version 6 at 7m 07s thumbnailv6 7:07
  7. Version 7 at 7m 12s thumbnailv7 7:12
  8. Version 8 at 8m 07s thumbnailv8 8:07
  9. Version 9 at 8m 48s thumbnailv9 8:48
  10. Version 10 at 8m 58s thumbnailv10 8:58
  11. Version 11 at 9m 18s thumbnailv11 9:18
  12. Version 12 at 9m 33s thumbnailv12 9:33
  13. Version 13 at 10m 19s thumbnailv13 10:19
  14. Version 14 at 10m 59s thumbnailv14 10:59
  15. Version 15 at 11m 20s thumbnailv15 11:20
  16. Version 16 at 11m 45s thumbnailv16 11:45
  17. Version 17 at 12m 20s thumbnailv17 12:20
  18. Version 18 at 12m 36s thumbnailv18 12:36
  19. Version 19 at 15m 28s thumbnailv19 15:28

No transcript was delivered with this result.

Cost breakdown

Headline cost $2.82, estimated from the token counts at list price.

Tokens by typeTokens$ per 1MCost
Input (uncached)249$2.00$0.0005
Cache write136,057$2.00$0.2721
Cache read7,747,290$0.20$1.5495
Output99,618$10.00$0.9962
of which reasoning60,182billed as output
Total computed from tokens
$2.8182
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 (83 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 4 Three.js/WebGPU expansion; category threejs; 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: tries WebGPU first (navigator.gpu.requestAdapter, site/index.html line 1117; fallback adapters skipped, line 1118) and otherwise uses its WebGL2 engine (getContext('webgl2'), site/index.html line 444; engine label WEBGL2, line 447; fallback at line 1134). The live demo runs in any WebGL2 browser; WebGPU is used when available.
  • Poster: shows the WEBGL2 fallback path (engine label top right). No card video: the card uses the poster.