PulseAugur
EN
LIVE 03:52:24

Google's Gemini 3.5 Flash outperforms 3.1 Pro on coding and agents

By PulseAugur Editorial · [1 sources] ·

Google's Gemini 3.5 Flash model has surpassed its predecessor, Gemini 3.1 Pro, on several key benchmarks, particularly in coding and agentic tasks. This new tier offers a significant cost reduction of 40% and approximately four times faster output generation compared to 3.1 Pro. While Gemini 3.5 Flash excels in tool-use and agentic performance, Gemini 3.1 Pro still maintains an edge in pure reasoning and novel problem-solving benchmarks. AI

IMPACT Accelerates adoption of cheaper, faster models for agentic tasks, potentially lowering costs for AI-powered applications.

RANK_REASON New model release from a frontier lab (Google) with performance benchmarks against prior models. [lever_c_demoted from frontier_release: ic=1 ai=1.0]

Read on dev.to — LLM tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

COVERAGE [1]

  1. dev.to — LLM tag TIER_1 English(EN) · Thousand Miles AI ·

    Gemini 3.5 Flash beat 3.1 Pro on coding and agents

    <p>Gemini 3.5 Flash scored 76.2% on Terminal-Bench 2.1. Gemini 3.1 Pro — the tier above it in Google's own lineup — scored 70.3%.</p> <p>Google shipped Flash at I/O 2026 on May 19. It costs $2.50 per million input tokens and $15 per million output, which is 40% cheaper than 3.1 P…

RELATED ENTITIES

RELATED TOPICS