Gemini 2.5 Pro Preview (Mar’ 25)
Intelligence
30.3
#161/523
Coding
46.7
#23/429
Math
—
Speed
—
Pricing
—
Gemini 2.5 Pro Preview (Mar’ 25) is Google’s latest AI model designed for advanced applications. It features an Intelligence Index of 30.3 and a Coding Index of 46.7, making it suitable for tasks requiring substantial cognitive and coding capabilities. The model is targeted at professional users seeking efficient processing of complex queries.
When to Use Gemini 2.5 Pro Preview (Mar’ 25)
✓ Best For
- Advanced coding tasks.
- Data analysis and interpretation.
- Complex problem-solving scenarios.
✗ Not Ideal For
- Real-time applications due to a speed of 0 tok/sec.
- Basic tasks that do not require high intelligence or coding capabilities.
How Gemini 2.5 Pro Preview (Mar’ 25) Compares
Intelligence Index · Higher is better
OpenAIXiaomiGoogleLG AI ResearchZ AI
Benchmark Profile
Coding Index
KimiGoogleAlibaba
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (9)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 30.3 | |
| Coding Index | 46.7 | |
| MMLU-Pro | 858% | |
| GPQA | 836% | |
| LiveCodeBench | 778% | |
| HLE | 171% | |
| SciCode | 39.5% | |
| AIME | 87% | |
| MATH 500 | 98% |
Data: Artificial Analysis · Updated: April 10, 2026
Frequently Asked Questions (15)
When was Gemini 2.5 Pro Preview (Mar' 25) released?
Gemini 2.5 Pro Preview (Mar' 25) was released on March 25, 2025.
Who created Gemini 2.5 Pro Preview (Mar' 25)?
Gemini 2.5 Pro Preview (Mar' 25) was created by Google.
How intelligent is Gemini 2.5 Pro Preview (Mar' 25)?
Gemini 2.5 Pro Preview (Mar' 25) scores 30 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other reasoning models in a similar price tier (median: 13).
Is Gemini 2.5 Pro Preview (Mar' 25) a reasoning model?
Yes, Gemini 2.5 Pro Preview (Mar' 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 (Mar' 25) support?
Gemini 2.5 Pro Preview (Mar' 25) supports text, image, speech, and video input.
What output modalities does Gemini 2.5 Pro Preview (Mar' 25) support?
Gemini 2.5 Pro Preview (Mar' 25) supports text output.
Can Gemini 2.5 Pro Preview (Mar' 25) process images?
Yes, Gemini 2.5 Pro Preview (Mar' 25) supports image input and can analyze, describe, and answer questions about images.
Is Gemini 2.5 Pro Preview (Mar' 25) multimodal?
Yes, Gemini 2.5 Pro Preview (Mar' 25) is multimodal. It can process text, image, speech, and video input and generate text output.
What is the context window of Gemini 2.5 Pro Preview (Mar' 25)?
Gemini 2.5 Pro Preview (Mar' 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 (Mar' 25) open source?
No, Gemini 2.5 Pro Preview (Mar' 25) is proprietary. The model weights are not publicly available.
How many parameters does Gemini 2.5 Pro Preview (Mar' 25) have?
Gemini 2.5 Pro Preview (Mar' 25) is a proprietary model and Google has not disclosed the model size or parameter count.
How does Gemini 2.5 Pro Preview (Mar' 25) perform on benchmarks?
Gemini 2.5 Pro Preview (Mar' 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 (Mar' 25)?
Gemini 2.5 Pro Preview (Mar' 25) has a knowledge cutoff of January 2025. The model's training data includes information up to this date.
Is Gemini 2.5 Pro Preview (Mar' 25) available via API?
Check the providers page for current API availability.
Where can I use Gemini 2.5 Pro Preview (Mar' 25)?
Visit the providers page to see availability.
