Google: Gemini 3.1 Pro Preview

Google: Gemini 3.1 Pro Preview

google · Released Feb 19, 2026 Frontier Best for Agents
Intelligence #2 / 565
92.1 Our Score
Speed #84 / 262
135.9 tokens / sec
Input #473 / 566
$2.00 per 1M tokens
Output #505 / 566
$12.00 per 1M tokens
Context #17 / 566
1M tokens

Analysis Summary

Google: Gemini 3.1 Pro Preview sits in the Frontier tier on our leaderboard, ranked #2 of 565 published models on overall intelligence. At $2.00 input and $12.00 output per 1M tokens, it is among the most expensive on the market. It offers an exceptionally large context window suited to long-document workflows and supports tool use, function calling, vision, and reasoning.

Editorial notes

Gemini 3.1 Pro Preview from Google leads across reasoning, coding, and agentic benchmarks with a 1M token context, full multimodal input, and tool use, making it a top-tier business model.

Assessed May 31, 2026

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence8.4Technical9Value6.8Content9.5
Intelligence 8.4/10
Technical 9/10
Content 9.5/10
Value 6.8/10

How Google: Gemini 3.1 Pro Preview compares

Google: Gemini 3.1 Pro Preview ranks #5 of 371 AI models we track for overall intelligence, #6 of 308 for coding, #4 of 283 for agentic tasks. Its 1M-token context window is larger than 97% of the models we list. At $2.00 per million input tokens it is cheaper than 16% of comparable models.

About Google: Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation..

Capabilities

Tool Use Function Calling Vision

Performance Indices

Source: Artificial Analysis

57.2 Intelligence Index
55.5 Coding Index
74.7 Agentic Index

Benchmark Scores

Intelligence

GPQA Diamond 94.1% Graduate-level scientific reasoning
HLE 44.7% Humanity's Last Exam
SciCode 58.9% Scientific computing

Technical

TerminalBench Hard 53.8% Agentic terminal tasks
τ²-Bench 95.6% Conversational agent benchmark

Content

IFBench 77.1% Instruction following
LCR 72.7% Long-context reasoning

Benchmark data from Artificial Analysis and Hugging Face

How does Google: Gemini 3.1 Pro Preview stack up?

Compare side-by-side with other frontier models.

Compare Models

Model Information

OpenRouter ID google/gemini-3.1-pro-preview
Providergoogle
Model FamilyGemini 3
Release Date February 19, 2026
Context Length1,048,576 tokens
Max Completion65,536 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $2.00 $0.002000
Output $12.00 $0.012000

Live Performance

Live endpoint metrics, refreshed every 30 minutes.

96%
Avg Uptime
5,887ms
Best Latency (TTFT)
79 tok/s
Best Throughput
2/2
Active Endpoints
Available via: Google AI Studio, Google

Frequently asked questions about Google: Gemini 3.1 Pro Preview

How much does Google: Gemini 3.1 Pro Preview cost?

Google: Gemini 3.1 Pro Preview costs $2.00 per million input tokens and $12.00 per million output tokens.

What is the context window of Google: Gemini 3.1 Pro Preview?

Google: Gemini 3.1 Pro Preview has a context window of 1,048,576 tokens (1M).

Is Google: Gemini 3.1 Pro Preview good for coding?

On our coding benchmark index, Google: Gemini 3.1 Pro Preview ranks #6 of 308 models, placing it in the top quartile of the field for code generation and debugging.

What can Google: Gemini 3.1 Pro Preview do?

Google: Gemini 3.1 Pro Preview supports image/vision input, tool use, and function calling.

Who created Google: Gemini 3.1 Pro Preview?

Google: Gemini 3.1 Pro Preview is developed by Google and was released on February 19, 2026.