Every's Vibe Check: GPT-6 Sol vs Opus 5.5 tested on real daily work

every · x · 2026-09-25

With OpenAI's GPT-6 Sol and Anthropic's Claude Opus 5.5 dropping the same day, Every's Dan Shipper ran a Vibe Check using benchmarks built from Every's own day-to-day tasks, finding "two models, one clear tradeoff." The piece argues for testing models on your actual work rather than public scores, though the full article is paywalled.

Original post →

More from Models

Models channel →