GPT-6 Sol in Codex CLI 0.156.1
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. It starts in its auto-tour (T switches to play mode on a keyboard).
Wall time 35m 07sCost $2.62 estimated
Review
No verdict yet.
The full review
OK. Finished on its own after 35.1 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, 1,202 characters. Every result for this prompt
Build a short cinematic camera study in Three.js that demonstrates a side-on tracking shot. A runner (a stylised low-poly figure with an animated running cycle) jogs along a riverside path at dawn past lamp posts, benches, trees and a railing, with a city skyline far behind. The camera travels parallel to the runner at the same speed, keeping them at the same size and in the same third of the frame, while foreground objects whip past quickly, midground objects slower, and the skyline barely moves. The animation plays automatically, fills the window at 16:9, loops seamlessly every 8 seconds with no visible jump at the loop point, and shows a small unobtrusive caption in one corner naming the technique. 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 (inline CSS and JS) in the current directory. Three.js may load from a pinned CDN. 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
Versions saved during the run
11 intermediate outputs, in the order the model wrote them.
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 5.0 MB; it is published as a scrubbed, compressed download rather than shown on the page.
Show all 217 steps
Loading the timeline…
Download the full transcript Codex CLI rollout JSONL, 144 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 $2.62, estimated from the token counts at list price.
| Tokens by type | Tokens | $ per 1M | Cost |
|---|---|---|---|
| Input (uncached) | 333 | $2.00 | $0.0007 |
| Cache write | 114,514 | $2.00 | $0.2290 |
| Cache read | 7,943,119 | $0.20 | $1.5886 |
| Output | 80,322 | $10.00 | $0.8032 |
| of which reasoning | 51,454 | billed as output |
- Total computed from tokens
- $2.6215
- 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 (111 checked): standard rates.
Prices: Project price table, 2026-09-25.
Run notes
- frozen prompt (written): video_house_skill/mr_cinematography_tests.json (sha256 b69c15a6...38b) 'prompt' field verbatim; Cinematography set (Tracking shot) copy at prompts/cine_tracking_shot.md (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
