GPT-6 Astra in OpenCode 1.18.32
skills off
Zoom, inline player and more ways to view
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.
Wall time 14m 45sCost $3.61 reported
Review
No verdict yet.
The full review
OK. Finished on its own after 14.8 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, 1,483 characters. Every result for this prompt
Build a single-page WebGPU compute-shader boids visualizer that runs 50,000 boids at 60fps, with a CPU (JS) mode capped at 2,000 for side-by-side comparison. Show separation/alignment/cohesion sliders, a predator that follows the mouse, spatial hashing grid overlay toggle, and an FPS + ms-per-step readout for each mode so the speedup is visible. Include a short in-page explanation panel of the algorithm and the spatial hash. One HTML file, no external assets. The GPU mode must use a WebGPU compute shader when navigator.gpu is available and otherwise fall back to a WebGL2 GPU path (for example float-texture ping-pong) so it still runs 50,000 boids where WebGPU is missing; label which GPU path is active. Make the page start a demo on load with no input (the predator follows a scripted path until the mouse moves) so a headless capture shows constant motion. 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, 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.
How it was made
Versions saved during the run
4 intermediate outputs, in the order the model wrote them.
No transcript was delivered with this result.
Cost breakdown
Headline cost $3.61, as reported by OpenCode (its own bill for the run). The list-price estimate from the token counts is $3.48.
| Tokens by type | Tokens | $ per 1M | Cost |
|---|---|---|---|
| Input (uncached) | 105 | $10.00 | $0.0010 |
| Cache write | 51,185 | $10.00 | $0.5119 |
| Cache read | 1,150,107 | $1.00 | $1.1501 |
| Output | 36,305 | $50.00 | $1.8153 |
| of which reasoning | 8,508 | billed as output |
- Total computed from tokens
- $3.4783
- Total reported by the harness
- $3.6062
- Difference
- Harness-reported $3.6062 vs list-price estimate $3.4783 (-3.5%); 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 (27,797 visible + 8,508 reasoning), and both bill at the output rate.
Prices: Project price table (vendor list prices), 2026-09-22.
Run notes
- frozen prompt (written): written 2026-10-05 from an idea-scan prompt, with a WebGL2 GPU fallback, auto-demo and the standard suffix, because the capture boxes have no WebGPU; category algorithm_visualizers; 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: none
- Renderer: WebGPU compute + render (getContext('webgpu') at index.html line 291) with a WebGL2 fallback (getContext('webgl2') at line 185) and a Canvas 2D CPU view (getContext('2d') at line 84); in the headless Chromium console check (no WebGPU available) the WebGL2 fallback ran (page badge "WEBGL2 · GPU"), 0 console errors, 0 page errors; 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.