Support

Settings

Theme

Explore themes

Mode

Library

Looks borrowed from benchmark sites and products. Themes with a light and a dark version follow your mode.

Bring your own theme

Upload a Priors theme file, or have your agent make one: copy the prompt, tell it the look you want, and upload what it returns. With the Priors skill installed it already knows the format.

Custom themes stay in this browser. They travel inside shared chart links and a page's theme, so others see them as you do.

For the builder, Explore and model pages on this device. Published pages keep the theme their owner picked.

Mode

Benchmarks · agentic

Vending-Bench 2

Year-long simulated vending-machine business; agents handle suppliers, inventory, pricing, and refunds. Score is the final bank balance.

66 models · 71 results · data as of 2026-10-29 · andonlabs.com ↗

Leaderboard

Chart settings
66 of 66 selected
Gemini 4 Carbon max

Score vs subscription cost per task

Vending-Bench 2 · measured cost per task · subscription-priced where plan data exists (Real API Pricing, full allowance used)

Highlight models

Click a point on the chart to highlight that exact effort; click it again to remove it.

50 more in settings
Chart settings
66 of 66 selected

Money balance ($) by day

As published by andonlabs.com, one line per run · follows the leaderboard’s model and effort settings

Top 10 of 66 runs by score ·

More from this benchmark

1 published measures

All results

71 rows
#ModelEffortVending-Bench 2Subscription $ / taskAPI $ / taskOutput tokens
1Gemini 4 Carbonmax$16,484$370$370521k
2GPT-6 Astramax$15,515$69$810321k
3GPT-6 Solmax$14,428$6.85$111420k
4Gemini 4 Argonmax$13,718$249$249193k
5Muse Wonder Fullmax$12,292
6Opus 5max$11,182$9.62$555440k
7Sonnet 5.5max$11,165$3.31$2192.1M
8Opus 4.7max$10,937$559$559440k
9Grok 4.7max$10,537$23$248252k
10GPT-5.6 Solmax$9,619$19$340284k
11Muse Wonder (Max)max$9,432$219$329269k
12Opus 5.5max$9,235$7.20$476829k
13GPT-6.1 Terramax$9,107$63$63254k
14Grok 4.6max$9,047$23$2231.2M
15GLM 5.2max$8,314$16$184234k
16GLM 5.3max$8,164$13$128305k
17Opus 4.6max$8,018$682$682272k
18GPT-5.5xhigh$7,524$14$256586k
19GPT-5.6 Terramax$7,343$8.09$147400k
20Sonnet 4.6max$7,204$265$2651.7M
21Muse Spark 1.1max$6,520$54$54185k
22Sonnet 5max$6,378$4.29$248327k
23Kimi K2.6max$6,205$128$128685k
24GPT-5.4xhigh$6,144$114$114587k
25GPT-5.3 Codexxhigh$5,940$68$68370k
26Opus 4.8high$5,787$7.89$455414k
27Fable 5high$5,680$154$1369312k
28GLM 5.1max$5,634$170$170268k
29Gemini 3 Prohigh$5,478$147$147475k
30Fable 5.1max$5,422$234$1504318k