Gemini 4 Neon benchmark table shows wins over Opus 5.5 and GPT-6.2 Sol on most metrics

imjustnewatai · x · 2026-11-19

A shared benchmark table for Google's Gemini 4 Neon shows it leading Claude Opus 5.5 and GPT-6.2 Sol on most metrics: AA Index 61, GraphWalks long context 95.2%, LVBench 89.0%, AutomationBench 56.3%, SEC-bench Pro 90.5%, and WebExploitBench 51.3%. It trails Opus 5.5 slightly on Terminal-bench 4.1 (65.2% vs 65.8%) and FrontierCode 2.0 (46.2% vs 47.3%), and GPT-6.2 Sol on Chartography (73.5% vs 75.1%). Commentators call it 'cheaper and better.'

Related event: Gemini 4 Neon Benchmarks Leak, Leading Claude Opus 5.5 and GPT-6.2 Sol(4 posts)→

Original post →

More from Models

Models channel →