Gemini 2.5 Pro Preview (May’ 25)
Intelligence
29.5
#167/523
Coding
—
Math
—
Speed
—
Pricing
$1.25 / $10.00
per 1M tokens (in/out)
Gemini 2.5 Pro Preview (May’ 25) is Google’s latest AI model designed for professional users. It operates at a speed of 0 tokens per second and is priced at $1.25 per million input tokens and $10 per million output tokens.
When to Use Gemini 2.5 Pro Preview (May’ 25)
✓ Best For
- Data analysis and insights generation.
- Complex coding tasks.
- Mathematical problem solving.
✗ Not Ideal For
- Real-time applications due to zero speed.
- High-volume output tasks given the pricing structure.
How Gemini 2.5 Pro Preview (May’ 25) Compares
Intelligence Index · Higher is better
AmazonxAIGoogleAlibabaDeepSeek
Benchmark Profile
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (8)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 29.5 | |
| MMLU-Pro | 837% | |
| GPQA | 822% | |
| LiveCodeBench | 77% | |
| HLE | 154% | |
| SciCode | 41.6% | |
| AIME | 84.3% | |
| MATH 500 | 98.6% |
Data: Artificial Analysis · Updated: April 10, 2026
Frequently Asked Questions (15)
When was Gemini 2.5 Pro Preview (May' 25) released?
Gemini 2.5 Pro Preview (May' 25) was released on May 6, 2025.
Who created Gemini 2.5 Pro Preview (May' 25)?
Gemini 2.5 Pro Preview (May' 25) was created by Google.
How intelligent is Gemini 2.5 Pro Preview (May' 25)?
Gemini 2.5 Pro Preview (May' 25) scores 30 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other reasoning models in a similar price tier (median: 31).
How much does Gemini 2.5 Pro Preview (May' 25) cost?
Gemini 2.5 Pro Preview (May' 25) costs $1.25 per 1M input tokens (better than average, median: $1.35) and $10.00 per 1M output tokens (somewhat higher than average, median: $8.40), based on Google's API.
What is Gemini 2.5 Pro Preview (May' 25) API pricing?
Gemini 2.5 Pro Preview (May' 25) costs $1.25 per 1M input tokens and $10.00 per 1M output tokens (based on Google's API). For a blended rate (3:1 input to output ratio), this is $3.44 per 1M tokens. Pricing may vary by provider.
Is Gemini 2.5 Pro Preview (May' 25) a reasoning model?
Yes, Gemini 2.5 Pro Preview (May' 25) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
What input modalities does Gemini 2.5 Pro Preview (May' 25) support?
Gemini 2.5 Pro Preview (May' 25) supports text, speech, and video input.
What output modalities does Gemini 2.5 Pro Preview (May' 25) support?
Gemini 2.5 Pro Preview (May' 25) supports text output.
Can Gemini 2.5 Pro Preview (May' 25) process images?
No, Gemini 2.5 Pro Preview (May' 25) does not support image input. It can only process text and speech and video.
Is Gemini 2.5 Pro Preview (May' 25) multimodal?
Yes, Gemini 2.5 Pro Preview (May' 25) is multimodal. It can process text, speech, and video input and generate text output.
What is the context window of Gemini 2.5 Pro Preview (May' 25)?
Gemini 2.5 Pro Preview (May' 25) has a context window of 1.0M tokens. This determines how much text and conversation history the model can process in a single request.
Is Gemini 2.5 Pro Preview (May' 25) open source?
No, Gemini 2.5 Pro Preview (May' 25) is proprietary. The model weights are not publicly available.
How many parameters does Gemini 2.5 Pro Preview (May' 25) have?
Gemini 2.5 Pro Preview (May' 25) is a proprietary model and Google has not disclosed the model size or parameter count.
How does Gemini 2.5 Pro Preview (May' 25) perform on benchmarks?
Gemini 2.5 Pro Preview (May' 25) achieves a score of 30 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
What is the knowledge cutoff date for Gemini 2.5 Pro Preview (May' 25)?
Gemini 2.5 Pro Preview (May' 25) has a knowledge cutoff of January 2025. The model's training data includes information up to this date.
