Vending-Bench 2: leaderboard
Simulates running a vending machine business for a year - order supplies, negotiate with suppliers, handle refunds, set prices. A 'good' strategy yields ~$63K but best models only hit ~$8K. No performance ceiling.
Metric: Money Balance ($). Source: andonlabs.com. Status: saturation imminent. 61 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5 | 11181.87 |
| 2 | Claude Opus 4.7 | 10936.76 |
| 3 | GPT-5.6 Sol | 9619.37 |
| 4 | Grok 4.6 | 9047.03 |
| 5 | GLM-5.2 | 8313.78 |
| 6 | GLM-5.3 | 8163.61 |
| 7 | Claude Opus 4.6 | 8017.59 |
| 8 | GPT-5.5 | 7523.84 |
| 9 | GPT-5.6 Terra | 7343.21 |
| 10 | Claude Sonnet 4.6 | 7204.14 |
| 11 | Muse Spark 1.1 | 6520.47 |
| 12 | Claude Sonnet 5 | 6377.7 |
| 13 | Kimi K2.6 | 6204.57 |
| 14 | GPT-5.4 | 6144.18 |
| 15 | GPT-5.3 Codex | 5940.12 |
Interactive version: theaggregate.ai/benchmark?slug=vending-bench-2 · How It Works · Data refreshed daily, snapshot 2026-09-05.