Gemini 2.5 Pro Preview (May' 25)

Gemini 2.5 Pro Preview (May' 25)

Googletext

API Available

Specifications

Context Window

Input Price/1M

$1.25

Output Price/1M

$10.00

Parameters

00

Benchmarks

Gemini 2.5 Pro Preview (May' 25) results on the main AI model evaluation benchmarks. Higher scores indicate better performance.

Agentic

BenchmarkScoreMaximumMethodology
Terminal-Bench Hard27.0100.0

Coding

BenchmarkScoreMaximumMethodology
LiveCodeBench77.0100.0Artificial Analysis official API
AA Coding Index46.7100.0Artificial Analysis official API
SciCode42.0100.0

Knowledge

BenchmarkScoreMaximumMethodology
MMLU-Pro84.0100.0

Long Context

BenchmarkScoreMaximumMethodology
AA-LCR66.0100.0

Math

BenchmarkScoreMaximumMethodology
MATH-50098.0100.0Artificial Analysis official API
AIME 202588.0100.0
AA Math Index87.7100.0

overall

BenchmarkScoreMaximumMethodology
AA Intelligence Index29.5100.0Artificial Analysis official API

Reasoning

BenchmarkScoreMaximumMethodology
MMLU Pro85.8100.0Artificial Analysis official API
GPQA Diamond82.0100.0Artificial Analysis official API
IFBench49.0100.0
HLE15.0100.0

Tool Use

BenchmarkScoreMaximumMethodology
Tau²-Bench54.0100.0

Information

Release date
May 06, 2025
Tool Calling
❌ Not supported
Vision
❌ Not supported
Audio
❌ Not supported

Full Analysis: Gemini 2.5 Pro Preview (May' 25)

What is Gemini 2.5 Pro Preview (May' 25)?

Gemini 2.5 Pro Preview (May' 25) is an AI model developed by Google, classified as a text model. It focuses on text processing and natural language generation. As a proprietary model, it is available via Google's cloud API.

Pricing & Costs in 2026

Gemini 2.5 Pro Preview (May' 25) is usage-based, priced at $1.25/1M input tokens and $10/1M output tokens. For context: 1 million tokens is approximately 750,000 words, or about 10 average-length books. The mid-range pricing balances quality and cost for most professional applications.

Benchmarks & Performance

Gemini 2.5 Pro Preview (May' 25) was evaluated on 15 different benchmarks, covering categories like Agentic, Coding, Knowledge, Long Context, Math, overall, Reasoning, Tool Use. Results show exceptional performance across available evaluations.

It's important to note that benchmarks measure specific aspects and don't capture the full user experience. Factors like instruction adherence, behavior in long conversations, and real-world task quality vary significantly between models and aren't always reflected in standard scores.

Recommended Use Cases

Gemini 2.5 Pro Preview (May' 25) specializes in text, offering advanced capabilities for creating and processing text content.

Comparison with Alternatives

In the 2026 AI model ecosystem, Gemini 2.5 Pro Preview (May' 25) competes directly with similarly capable models. Key competitors include GPT (OpenAI), Claude (Anthropic), and open source models like Llama (Meta) and Qwen (Alibaba). The choice between models depends on the specific use case, budget, latency requirements, and need for features like multimodality and tool calling.

For a detailed side-by-side comparison, use our comparison tool or check the overall model ranking.

Frequently Asked Questions

What is Gemini 2.5 Pro Preview (May' 25)?

Gemini 2.5 Pro Preview (May' 25) is an AI model developed by Google. It is a text model.

How much does Gemini 2.5 Pro Preview (May' 25) cost?

Gemini 2.5 Pro Preview (May' 25) costs $1.25/1M input tokens and $10/1M output tokens. For heavy usage (e.g., a chatbot handling 100k messages/month), costs can range from $10 to $1,000 depending on volume.

How does Gemini 2.5 Pro Preview (May' 25) compare with other models?

In available benchmarks, Gemini 2.5 Pro Preview (May' 25) scored: Terminal-Bench Hard: 27/100, LiveCodeBench: 77/100, AA Coding Index: 46.7/100. See the full table above for a detailed comparison.

Is Gemini 2.5 Pro Preview (May' 25) open source?

No, Gemini 2.5 Pro Preview (May' 25) is a proprietary model from Google. It is available via cloud API. For open source alternatives, check our open source model ranking.

What is Gemini 2.5 Pro Preview (May' 25) best for?

Gemini 2.5 Pro Preview (May' 25) excels at general-purpose language tasks.

Last updated: June 01, 2026 View methodology →