Gemini 3.1 Pro Preview
This model improves upon Gemini 2.5 Pro and is catered towards challenging tasks, especially those involving complex reasoning or agentic workflows. Improvements highlighted include use cases for coding, multi-step function calling, planning, reasoning, deep knowledge tasks, and instruction following.
Introducing Gemini 3Model Snapshot
TypeLanguage
ReleaseFeb 19, 2026
Context1,048,576
Tagsfile-input, tool-use, reasoning, vision
Overall
Rank #41 across 600
46.5
Coding
Rank #40 across 266
68.8
Blended Price
Rank #308 across 379
$4.50/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Output Speed122 tok/s
First Token17.34s
Max Output65,536
Pricing
Blended$4.50/M
Input$2.00/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 46.5 | #41 |
| Artificial Analysis Coding Index | coding | 68.8 | #40 |
| MMLU-Pro | reasoning | 91.2% | #1 |
| LiveBench Mathematics | math | 91.0% | #9 |