Gemini 2.5 Flash (Reasoning)
Gemini 2.5 Flash (Reasoning) 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 Speed199.6 tok/s
First Token7.96s
Blended Price$0.850/M
Model Metadata
Queryable facts extracted from the upstream model payload.
ReleaseMay 20, 2025
Context Windown/a
Modalitiesn/a
Strength: MATH-500
Rank #15 across 201 models.
98.1%
Strength: Speed
Rank #24 across 293 models.
199.6 tok/s
Strength: AIME
Rank #21 across 194 models.
82.3%
Watch Area: TTFT
Rank #251 across 293 models.
7.96s
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 | 27.0 | #171 |
| Artificial Analysis Coding Index | coding | 22.2 | #174 |
| Artificial Analysis Math Index | math | 73.3 | #86 |
| MMLU-Pro | reasoning | 83.2% | #57 |