TestsBenchmarks · Agentic
Vending-Bench 2
Money balance after an agent runs a simulated vending-machine business for a year; tests long-horizon coherence.
Measured by independent testersIndependent Reported by the makerVendor-reported
| Thinking levelSetting | |||||||
|---|---|---|---|---|---|---|---|
| 1 | GPT-6 Astra | OpenAI | $15,515 | Default | Independent testIndependentAndon Labs ↗ | — | 1 Oct 2026 |
| 2 | GPT-6 Sol | OpenAI | $14,428 | Default | Independent testIndependentAndon Labs ↗ | — | 1 Oct 2026 |
| 3 | Gemini 4 Argon | Google (Gemini / DeepMind) | $13,718 | Default | Independent testIndependentAndon Labs ↗ | — | 1 Oct 2026 |
| 4 | Claude Opus 5 | Anthropic | $11,182 | Default | Independent testIndependentAndon Labs ↗ | — | 1 Oct 2026 |
| 5 | Claude Opus 4.7 | Anthropic | $10,937 | Default | Independent testIndependentAndon Labs ↗ | — | 1 Oct 2026 |
| 6 | Grok 4.7 | SpaceXAI (formerly xAI) | $10,537 | Default | Independent testIndependentAndon Labs ↗ | — | 1 Oct 2026 |
| 7 | GPT-5.6 Sol | OpenAI | $9,619 | Default | Independent testIndependentAndon Labs ↗ | — | 1 Oct 2026 |
| 8 | Claude Opus 5.5 | Anthropic | $9,235 | Default | Independent testIndependentAndon Labs ↗ | — | 1 Oct 2026 |
| 9 | Grok 4.6 | SpaceXAI (formerly xAI) | $9,047 | Default | Independent testIndependentAndon Labs ↗ | — | 1 Oct 2026 |
| 10 | GLM-5.2 | Z.ai (Zhipu) | $8,314 | Default | Independent testIndependentAndon Labs ↗ | — | 1 Oct 2026 |