Gemini 4 Neon benchmark leak claims sweep over Claude Opus 5.5 and GPT-6.2 Sol

kristoph · x · 2026-11-19

Developer kristoph notes Google went from "written off 6 months ago" to "winning hard," sharing a benchmark table comparing Gemini 4 Neon against Claude Opus 5.5 and GPT-6.2 Sol (attributed to a DeepMind evals page; model names unverified).

Key claimed results, with Gemini 4 Neon leading most categories:

Original post →

More from Models

Models channel →