Results
| 1 | Gemini 4 Carbon | |
|---|---|---|
| 2 | GPT-6 Astra | |
| 3 | Gemini 4 Hydrogen | |
| 4 | GPT-6 Sol | |
| 5 | Gemini 4 Argon | |
| 6 | GPT-6.1 Sol | |
| 7 | Muse Wonder Full | |
| 8 | Claude Opus 5 | |
| 9 | Claude Sonnet 5.5 | |
| 10 | Claude Opus 4.7 |
Public leaderboard · Agents, tool use & computer use
An AI runs a simulated vending-machine business for a long time; tests staying sensible over many days.
An agent runs a simulated vending-machine business for a simulated year (suppliers, prices, refunds, stock), scored by its money balance at the end.
Average final money balance ($) — higher is better.
| 1 | Gemini 4 Carbon | |
|---|---|---|
| 2 | GPT-6 Astra | |
| 3 | Gemini 4 Hydrogen | |
| 4 | GPT-6 Sol | |
| 5 | Gemini 4 Argon | |
| 6 | GPT-6.1 Sol | |
| 7 | Muse Wonder Full | |
| 8 | Claude Opus 5 | |
| 9 | Claude Sonnet 5.5 | |
| 10 | Claude Opus 4.7 |
Note: Top 10 of 76 shown on page; no update date shown, but includes very recent models.
Source: Andon Labs · andonlabs.com · retrieved 2026-11-17