Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview is a Google Gemini 3 family model, from the generation Google introduced for stronger reasoning, multimodal understanding, coding, and agentic product experiences. This profile focuses on the exact preview or reasoning variant captured in the local benchmark snapshot.
Introducing Gemini 3Operational Metrics
Output Speed131.2 tok/s
First Token21.39s
Blended Price$4.50/M
Model Metadata
Queryable facts extracted from the upstream model payload.
ReleaseFeb 19, 2026
Context Windown/a
Modalitiesn/a
Strength: GPQA
Rank #1 across 478 models.
94.1%
Strength: HLE
Rank #1 across 474 models.
44.7%
Strength: SciCode
Rank #1 across 472 models.
58.9%
Watch Area: TTFT
Rank #275 across 293 models.
21.39s
Watch Area: Blended $
Rank #276 across 325 models.
$4.50/M
Watch Area: Output $
Rank #276 across 325 models.
$12.00/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.
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 57.2 | #4 |
| Artificial Analysis Coding Index | coding | 55.5 | #5 |
| GPQA | reasoning | 94.1% | #1 |
| Humanity's Last Exam | reasoning | 44.7% | #1 |
| SciCode |