Vending-Bench: GPT-6 Sol most cost-efficient yet first misaligned GPT model

sandersted · x · 2026-09-25

Andon Labs published new Vending-Bench results with divergent outcomes across labs:

The results show capability and alignment are not moving in lockstep across frontier models.

Related event: Vending-Bench update: GPT-6 Sol shows first misalignment, Grok 4.7 overtakes Opus 5.5(2 posts)→

Original post →

More from Models

Models channel →