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. It starts in its auto-tour (T switches to play mode on a keyboard).

Recorded from the live demo (stepped clock). Preview video recorded by this site from the live demo. The moving picture above is that preview; the button runs the real page.

OKX16 enginemax effortNeutral harness

Wall time 13m 57sCost $2.84 reported

Snapshot 5 of 5 saved during GPT-6 Astra's run
  1. Snapshot 1 of 5 saved during GPT-6 Astra's run
  2. Snapshot 2 of 5 saved during GPT-6 Astra's run
  3. Snapshot 3 of 5 saved during GPT-6 Astra's run
  4. Snapshot 4 of 5 saved during GPT-6 Astra's run
  5. Snapshot 5 of 5 saved during GPT-6 Astra's run
Still snapshots saved during the run (the moving picture above was recorded from the live demo): 5 distinct frames.

Generation timelapse

Poster for generation timelapse

Generation timelapse (the agent's screen during the run, sped up). This is not the finished video. Download video (548 KB).

Review

No verdict yet.

The full review

OK. Finished on its own after 13.9 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, 725 characters. Every result for this prompt

Build a conceptual X-16 engine in 3D with Three.js: four cylinder banks, one crankshaft and exposed mechanics inspired by experimental multi-bank engine architectures. Make it animate (pistons, rods and crank moving in sync) with orbit controls. Everything is built in code from Three.js geometry, shaders and materials; no external models or textures. Build it as a single self-contained index.html in the current directory. Three.js may load from a CDN or be vendored. 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 13m 57sFirst artifact at 6m 10s5 saved versions

Versions saved during the run

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

Version 5 of 5
  1. Version 1 at 6m 18s thumbnailv1 6:18
  2. Version 2 at 7m 54s thumbnailv2 7:54
  3. Version 3 at 8m 34s thumbnailv3 8:34
  4. Version 4 at 10m 31s thumbnailv4 10:31
  5. Version 5 at 12m 17s thumbnailv5 12:17

Step by step

The prompt, every agent turn and tool call (tool name and a one-line summary; inputs and outputs are not shown), then the final message. The full transcript is 3.0 MB; it is published as a scrubbed, compressed download rather than shown on the page.

Show all 50 steps

Loading the timeline…

Download the full transcript OpenCode session export, 74 KB, gzip. Scrubbed: anything that looks like a key, token, e-mail address or phone number is replaced, and account details and the test machine's file paths are removed.

Cost breakdown

Headline cost $2.84, as reported by OpenCode (its own bill for the run). The list-price estimate from the token counts is $2.73.

Tokens by typeTokens$ per 1MCost
Input (uncached)87$10.00$0.0009
Cache write45,384$10.00$0.4538
Cache read749,336$1.00$0.7493
Output30,502$50.00$1.5251
of which reasoning8,020billed as output
Total computed from tokens
$2.7291
Total reported by the harness
$2.8426
Difference
Harness-reported $2.8426 vs list-price estimate $2.7291 (-4.0%); 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 (22,482 visible + 8,020 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)labelled re-run (of x16_engine__opencode__gpt-6-astra)

  • frozen prompt (written): engine/prompts_written/x16_engine.txt: a new test's prompt written by us from the project lead's brief (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