GoogleReleased 2026-03

Gemini 3 Flash

Fast, affordable Gemini 3 tier with surprisingly strong science and multimodal chops for the price.

Context

Speed

180 t/s

Price /M

$0.30 / $2.5

Access

api

When to use it

High-throughput apps, classification, and cost-sensitive Google stack workloads.

Not a frontier coding leader; use Pro for hard reasoning.

SpeedBest valueMultimodalLong context

Arena Elo1473

Human preference ranking from blind pairwise chats. Higher is better; top frontier models cluster within ~50–80 Elo.

AA Intelligence Index42

Artificial Analysis composite across agents, coding, science, and general evaluations (v4.1 weighting).

SWE-bench Verified78%

Percent of real GitHub issues resolved end-to-end. Strong signal for agentic coding usefulness.

GPQA Diamond90.4%

PhD-level science questions. Separates frontier reasoning models better than saturated knowledge tests.

MMLU-Pro—

Harder multi-choice knowledge/reasoning suite than classic MMLU.

Humanity's Last Exam33.7%

Frontier closed-ended academic difficulty across many domains.