Vending-Bench Arena - Round 6: leaderboard
Vending-Bench Arena round 6 (Andon Labs, February 17, 2026): Claude Sonnet 4.6, Opus 4.6 and Sonnet 4.5 each run a vending machine at one location in the Vending-Bench 2 simulation and can email, pay and trade with each other. Final money balance in US dollars (start $500), averaged over 4 runs; higher is better. Balances depend on the opponents in that round, so they do not compare across rounds.
Metric: Final money balance ($, mean over runs). Source: andonlabs.com. Saturation forecast: Around June 2027. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.6 | 5638.93 | #94 |
| 2 | Claude Opus 4.6 | 4053.34 | #67 |
| 3 | Claude Sonnet 4.5 | 2125.11 | #148 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=vending-bench-arena-round-6 · How It Works · Data refreshed daily, snapshot 2026-11-05.