GPT-6.1 Sol made this.
Made by a Codex agent. It wrote the file in one go and never ran or fixed it.

Same prompt, other runs
GPT-6.1 Sol Effort: Extra high, level 4 of 5
Fable 5.2 Effort: Extra high, level 4 of 5
Haiku 5.5 Effort: Max, level 5 of 5
Sonnet 5.5 Effort: Extra high, level 4 of 5
Opus 5.5 Effort: Max, level 5 of 5
GPT-6.2 Astra Effort: Max, level 5 of 5
GPT-6.2 Sol Effort: Max, level 5 of 5
GPT-6.1 Terra Effort: Extra high, level 4 of 5
GPT-6.1 Sol Effort: Low, level 1 of 5
Receipt
- Made in
- Codex
- Paid with
- ChatGPT subscription
- Time
- 16 min 36 s
- Tries
- One-shot
- Date
- Nov 22, 2026
- By
- a Codex agent
- API equivalent (estimate)tokens × list price
- about $0.49
Estimate at list API prices. I used my regular paid plan, not the API.
Prompt and answer tokens at list price, thinking included; the coding tool's own instructions are not counted.
Try
- Try 1works · auto-checked (Checked by an automated pass. Not hand-played yet.)shownCode of try 1
How it was made
One-answer agent run: a Codex agent running GPT-6.1 Sol at extra high effort got only the prompt and wrote the file in a single write. It did not open or test it, and nobody edited it afterwards. One command failed before the file was written (a tool problem); the file was written once, by a later command, and never opened.
What it built, in its own words: Created index.html with translucent orange jelly, detailed citrus segments, and a tetrahedral soft-body simulation. Includes touch and mouse interaction, squeezing with juice drops, firmness controls, reset, and a 20-second #demo loop.
Limitations it reported: Requires WebGL and CDN access; not opened or tested, as requested.
Status not checked by a person yet.
How it was checked
- Console errors
- none
- Links and libraries
- all allowed
- Hands-free demo
- yes
- Phone check
- 390x844
- Libraries it loads
- cdn.jsdelivr.net/npm/three@0.170.0/build/three.module.js
The benchmark
Jelly Orange Slice
A glossy orange slice made of jelly. Poke it, squeeze it, watch it wobble.
I keep the exact prompts private for now.
Every AI on this benchmark