AI Model Reviewer

GPT-6 Astra in OpenCode 1.18.32

skills off

← Open in the gallerySame prompt, all models

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

OKPaint studiomax effortNeutral harness

Wall time 20m 13sCost $6.31 reported

Review

No verdict yet.

The full review

OK. Finished on its own after 20.2 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, 1,879 characters. Every result for this prompt

Build a working digital painting app in one page, a compact cross between MS Paint and Procreate. It needs: a large canvas with pressure-friendly smooth strokes using pointer events (mouse, touch and pen) with stroke smoothing; brushes (round, soft airbrush, marker, calligraphy nib whose width depends on direction, pixel pencil, eraser, smudge); a colour wheel with hue ring and saturation-value square, hex input and a palette of recent colours; flood fill with tolerance; shapes (line, rectangle, ellipse) with shift to constrain; layers panel with add, delete, reorder by drag, opacity, visibility, blend modes (normal, multiply, screen, overlay) and live thumbnails; unlimited undo and redo; pinch and wheel zoom plus pan with the space bar; and export of the flattened image as a PNG download. So the page is alive without input, on load it plays a scripted painting demo with a visible cursor: it paints a small landscape at dusk on several layers (sky gradient, mountains, a moon, trees with the calligraphy brush, smudged fog), changes blend modes, zooms in and out, undoes a stroke and redoes it, then clears and paints a different scene, looping until the user touches the canvas or any control. Make the interface sleek and dark, with the painting as the hero.

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) 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 20m 13sFirst artifact at 7m 36s3 saved versions

Versions saved during the run

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

Version 3 of 3
  1. v1 7:43
  2. v2 12:16
  3. v3 19:18

No transcript was delivered with this result.

Cost breakdown

Headline cost $6.31, as reported by OpenCode (its own bill for the run). The list-price estimate from the token counts is $6.11.

Tokens by typeTokens$ per 1MCost
Input (uncached)141$10.00$0.0014
Cache write78,952$10.00$0.7895
Cache read2,461,927$1.00$2.4619
Output57,142$50.00$2.8571
of which reasoning12,955billed as output
Total computed from tokens
$6.1100
Total reported by the harness
$6.3073
Difference
Harness-reported $6.3073 vs list-price estimate $6.1100 (-3.1%); the harness figure is the headline.

OpenCode 1.18.32 reported its own total; token counts x list prices shown beside it. Cache writes priced at the input rate (the price table has no separate cache-write price). The harness reports reasoning tokens separately from output; here output includes them (44,187 visible + 12,955 reasoning), and both bill at the output rate.

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 for the MR category expansion (owner request: 500 finished runs in every category); category app_clones; zero results
  • plain OpenCode config copy (providers only; no ECC instructions/agents)
  • opencode export written to a file (not piped)
  • Mode: interactive TUI in tmux (160x48), inside bubblewrap sandbox
  • Isolation audit: outside paths seen
  • Renderer: Canvas 2D (getContext('2d') at index.html line 125) plus DOM/CSS UI and inline SVG; single self-contained index.html, no CDN and no external assets.
  • Card video: the run's own session capture (headless Chromium, no GPU), re-encoded as H.264. Poster: the run's own render.png.
  • 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.