Gemini 2.5 Pro Preview (May' 25)
Gemini 2.5 Pro Preview (May' 25) is a Google Gemini 2.5 model, part of the Gemini generation that emphasized thinking, long-context work, multimodal reasoning, and developer access through AI Studio and Vertex AI. The profile lets you compare the specific Pro, Flash, or Flash-Lite variant on measured quality, speed, and cost.
Gemini 2.5 thinking modelsOperational Metrics
Output Speedn/a
First Tokenn/a
Blended Price$3.44/M
Model Metadata
Queryable facts extracted from the upstream model payload.
ReleaseMay 6, 2025
Context Windown/a
Modalitiesn/a
Strength: MATH-500
Rank #9 across 201 models.
98.6%
Strength: AIME
Rank #18 across 194 models.
84.3%
Strength: LCB
Rank #40 across 343 models.
77.0%
Watch Area: Output $
Rank #259 across 325 models.
$10.00/M
Watch Area: Value
Rank #257 across 323 models.
8.6
Watch Area: Blended $
Rank #251 across 325 models.
$3.44/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 | 29.5 | #148 |
| MMLU-Pro | reasoning | 83.7% | #49 |
| GPQA | reasoning | 82.2% | #83 |
| Humanity's Last Exam | reasoning | 15.4% | #92 |
| LiveCodeBench |