Model

Gemini 3.1 Pro

CLOSED

Google · Gemini 3.1 family · released Feb 19, 2026

Coding-arena leader with extended long-context frontier reasoning; ARC-AGI-2 77.1%, 1M-token context.

ReasoningCodingVisionFunction callingTool useAgentic

2598.4

Elo · rank #11

Parameters

Undisclosed

Active params

Undisclosed

Context

1M tokens

Architecture

Sparse Mixture-of-Experts Transformer (configuration undisclosed)

License

Proprietary

Languages

—

API price (in/out)

$2 / $12

Modalities

text · vision · audio · video

Benchmark results

Bar shows position within the tracked field; marker = field best

Agents' Last ExamAgents32.0%#11

best: GPT-5.6 · 52.7%

ARC-AGI-2Reasoning77.1%#4

best: GPT-5.6 · 92.5%

BrowseCompAgents85.9%#5

best: Kimi K3 · 91.2%

GDPval-AAAgents1317#22

best: Claude Fable 5 · 1932

GPQA DiamondReasoning94.3%#3

best: GPT-5.6 · 94.6%

Humanity's Last ExamReasoning44.4%#13

best: Claude Sonnet 5 · 57.4%

LiveCodeBench ProCoding2887#1

best: this model · 2887

LiveCodeBenchCoding88.5%#11

best: DeepSeek-V4-Pro (Think Max) · 93.5%

MMMLUKnowledge92.6%#1

best: this model · 92.6%

MMMU-ProVision80.5%#8

best: Claude Opus 4.7 · 85.5%

SWE-bench ProCoding54.2%#29

best: Claude Fable 5 · 80.0%

SWE-bench VerifiedCoding80.6%#13

best: Claude Fable 5 · 95.0%

τ²-Bench RetailAgents90.8%#2

best: Claude Sonnet 4.6 · 91.7%

τ²-Bench TelecomAgents99.3%#2

best: Claude Opus 4.6 · 99.3%

Terminal-Bench 2.0Coding68.5%#18

best: GPT-5.6 · 88.8%

Run it locally

Closed weights — available via API only. No local deployment.

Input / M tok

Output / M tok

$12

Gemini 3.1 family

Elo progression across releases

Gemini 3.1 ProFeb 20262598.4 Gemini 3.1 Flash-LiteMar 20261920.1

Resources

DOCShttps://deepmind.google/models/gemini/pro/APIAvailable via Google API

API price $2/$12 · each benchmark row carries its own source badge (see methodology)