Full benchmark results for Gemini 4 Argon with high reasoning released

ArtificialAnlys · x · 2026-10-01

Artificial Analysis has posted the full benchmark results for Gemini 4 Argon with high reasoning enabled, following its earlier #1 AutomationBench-AA score of 77.5% and Terminal Bench 4 result of 57%, giving the community complete data for comparison.

Related event: Gemini 4 Argon High-Reasoning Benchmarks Released(4 posts)→

Original post →

More from Models

Models channel →