Gemini 3.1 Pro
GeminiBalanced
ThinkingTool UseVisionStructured Output
About this model
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...
Performance Tier
Balanced
Gemini 3.1 Pro is a balanced model from Gemini : strong performance at a reasonable price.
Strong cost-performance ratio. Reliable for most professional use cases without premium pricing.
Pricing
This model is included in Elosia plansHigh
High pricing. Reserve this level for tasks that demand maximum quality.
| Type | per 1M tokens |
|---|---|
| Input (prompt) | $2.00 |
| Output (completion) | $12.00 |
| Image | $2.00 |
| Internal reasoning | $12.00 |
| Cache read | $0.200 |
| Cache write | $0.375 |
Capabilities
Context Length1.0M
Max Output Tokens66K
TokenizerGemini
Inputaudio, file, image, text, video
Outputtext
Release DateFebruary 19, 2026
Benchmarks
General Intelligence
MMLU
Not reported
GPQA Diamond
94.3%
Mathematics
MATH-500
Not reported
AIME 2025
100%
Programming
HumanEval
Not reported
SWE-bench Verified
80.6%
Reasoning
ARC-AGI-2
77.1%
Humanity's Last Exam
51.4%
Multimodal
MMMU-Pro
80.5%
Where does Gemini 3.1 Pro stand?
Compare its performance index against every other model.
Recommended Use Cases
ResearchAnalysisCodingMathematicsSummarizationData Extraction
Strengths
- ARC-AGI-2 77.1%, more than double Gemini 3 Pro reasoning score
- Strong software engineering (SWE-bench 80.6%)
- Excellent science reasoning (GPQA Diamond 94.3%)
- Enhanced agentic reliability for complex autonomous workflows
Limitations
- Preview model: may have stability changes
- Superseded by Gemini 4 Argon as Google's flagship
Frequently asked questions
Resources
This model may use your data for training
