Grok 4.7 scores 94% on Next.js evals, 2x-7x cheaper than Opus 5.5 and GPT-6 Sol

elonmusk · x · 2026-09-23

rauchg's team ran fresh Next.js coding evals: Claude Opus 5.5, GPT-6 Sol and Fable 5.1 all scored 97%, while Grok 4.7 came in at 94% — but at 2x-7x lower cost. Elon Musk reposted, calling Grok 4.7's performance strong for a smallish model. The takeaway: frontier coding capability has converged, and price is becoming the differentiator.

Original post →

More from Models

Models channel →