AI Model Reviewer

GPT-6 Sol in Codex CLI 0.156.1

skills off

← Open in the gallerySame prompt, all models

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 particle life audiomax effortNeutral harness

Wall time 10m 53sCost $1.72 estimated

Review

No verdict yet.

The full review

OK. Finished on its own after 10.9 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, 963 characters. Every result for this prompt

Build a 3D 'particle life' simulation in the browser using WebGPU compute shaders: at least 50,000 particles in 6 colour species, each pair with an attraction/repulsion rule, forming emergent creatures. Orbit camera, bloom-style glow, a panel with presets and a randomise-rules button. Add an optional microphone mode where audio loudness and bass energy modulate the force strengths in real time (works without the mic too). Show particle count and fps. One index.html plus local JS/WGSL only, no external assets or CDNs. 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 10m 53sFirst artifact at 2m 32s3 saved versions

Versions saved during the run

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

Version 3 of 3
  1. Version 1 at 2m 34s thumbnailv1 2:34
  2. Version 2 at 6m 12s thumbnailv2 6:12
  3. Version 3 at 8m 38s thumbnailv3 8:38

No transcript was delivered with this result.

Cost breakdown

Headline cost $1.72, estimated from the token counts at list price.

Tokens by typeTokens$ per 1MCost
Input (uncached)263$2.00$0.0005
Cache write99,462$2.00$0.1989
Cache read4,001,560$0.20$0.8003
Output71,595$10.00$0.7159
of which reasoning34,051billed as output
Total computed from tokens
$1.7157
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 (57 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: WebGPU compute when the browser exposes navigator.gpu (site/app.js line 1084), with a built-in CPU canvas fallback (site/app.js line 1104: activateCanvasPreview(..., "WebGPU unavailable"); function at line 1008). Without WebGPU the demo still runs, as the CPU preview.
  • Poster and card video: captured on a machine with no GPU, so both show the CPU preview, not the WebGPU path (on-screen banner "WebGPU is unavailable here. A local CPU preview is running with the same 50,000 particles.", site/index.html line 362). Card video = the run's own 8 s session capture, re-encoded as H.264.