Status: Preview

Gemini 3.1 Pro Preview

Provider: Google Family: Gemini 3.1 Preview

Official docs

analytics

Capabilities

Context window 1.0M Tokens

Status Preview Google

Release Feb 2026

Aktuelle Pro-Preview der Gemini-3.1-Reihe mit Fokus auf Thinking, Zuverlässigkeit und Agentic Workflows.

Recommended for

arrow_right Evaluierung, Prototyping, frühe Tests
arrow_right Komplexes Reasoning und Analyse
arrow_right Kostensensitive Produktions-Workloads

Use Cases

arrow_right Mehrstufige Analyse, Planung, Vergleich, Entscheidungsunterstützung
arrow_right Klassifikation, Extraktion, Routing, Zusammenfassungen in großem Volumen
arrow_right Workflow-Orchestrierung, Tool-Aufrufe, strukturierte Prozessschritte

Technical specs

Model ID
gemini-3-1-pro-preview
Family Gemini 3.1
Context window 1.0M
Release 2/19/2026

terminal Official docs

Benchmarks

Arena Performance · lmarena.ai

Chat #6 / 87

1 Claude Opus 4.6 1,476

4 Claude Sonnet 4.6 1,389

6 Kimi K2.5 1,355

2 Grok 4 Fast 1,338

7 GLM-5 1,318

3 DeepSeek-V3.2-Exp 1,300

8 Qwen3.5-397B-A17B 1,295

6 Gemini 3.1 Pro Preview 1,222

Websites #4 / 98

1 Claude Sonnet 4.6 1,076

2 Gemini 3 Flash Preview 780

3 GPT-5.4 705

4 Gemini 3.1 Pro Preview 674

5 Claude Opus 4.6 666

6 GPT-5.4 mini 640

Coding #2 / 135

1 Claude Opus 4.6 2,002

2 Gemini 3.1 Pro Preview 1,861

7 Kimi K2.5 1,780

3 GPT-5.4 1,679

8 GLM-5 1,650

9 Qwen3.5-397B-A17B 1,590

10 MiniMax M2.5 1,440

3D #3 / 90

1 Gemini 3 Pro Preview 2,075

2 Claude Opus 4.6 2,049

3 Gemini 3.1 Pro Preview 1,920

4 Claude Sonnet 4.6 1,831

5 GPT-5.4 1,780

Games #4 / 94

1 Claude Opus 4.6 1,550

2 Claude Sonnet 4.6 1,401

3 GPT-5.4 1,270

4 Gemini 3.1 Pro Preview 1,235

5 Grok 4 Fast 1,190

6 DeepSeek-V3.2-Exp 1,155

Animations #2 / 88

1 Claude Opus 4.6 2,196

2 Gemini 3.1 Pro Preview 2,174

3 GPT-5.4 1,962

4 Claude Sonnet 4.6 1,831

5 GPT-5.4 mini 1,720

SVG #1 / 93

1 Gemini 3.1 Pro Preview 2,570

2 Gemini 3 Pro Preview 2,333

3 Claude Opus 4.6 2,079

4 Gemini 3 Flash Preview 2,003

5 GPT-5.4 1,950

Data Viz #3 / 86

1 Claude Opus 4.6 2,806

2 GPT-5.4 2,661

3 Gemini 3.1 Pro Preview 2,174

4 Claude Sonnet 4.6 1,980

5 GPT-5.4 mini 1,840

Math #3 / 75

1 Claude Opus 4.6 1,795

2 GPT-5.4 1,740

3 Gemini 3.1 Pro Preview 1,695

4 Qwen3.5-397B-A17B 1,660

5 DeepSeek-V3.2-Exp 1,620

6 Kimi K2.5 1,585

7 Claude Sonnet 4.6 1,550

Reasoning #3 / 80

1 Claude Opus 4.6 1,820

2 GPT-5.4 1,755

3 Gemini 3.1 Pro Preview 1,710

4 Kimi K2-Thinking-0905 1,680

5 Claude Sonnet 4.6 1,640

6 Qwen3.5-397B-A17B 1,590

7 DeepSeek-V3.2-Exp 1,555

HumanEval

Overall 71.4% #4/66 open_in_new

SWE-Bench Verified

Overall 80.6% #2/77 open_in_new

Terminal-Bench

Overall 68.5% #1/25 open_in_new

Timeline

History

4/1/2026 · today

New model

New advanced intelligence model with complex problem-solving and agentic capabilities

open_in_new Source

4/1/2026 · 1d ago

First captured in AI Radar

Google

2/19/2026 · 42d ago

Model release

Gemini 3.1 Pro Preview

open_in_new Source