Full Gemini 3.8 Flash benchmark results across high, medium and low reasoning

ArtificialAnlys · x · 2026-09-02

Artificial Analysis publishes full benchmark results for Gemini 3.8 Flash across its high, medium and low reasoning levels, covering the Intelligence Index, AA-Briefcase (Elo 1213), agentic and coding evals, speed and cost.

Related event: Gemini 3.8 Flash Benchmarks: Smarter, Pricier, Still on the Cost Frontier(8 posts)→

Original post →

More from Models

Models channel →