Google DeepMind
Try Google AI Studio Try Gemini

Gemini

Our most intelligent AI models

Chat with Gemini Try in Google AI Studio

Models

We’re expanding our Gemini 2.5 family of models

Gemini 2.5 models are capable of reasoning through their thoughts before responding, resulting in enhanced performance and improved accuracy.

Model family

Gemini 2.5 builds on the best of Gemini — with native multimodality and a long context window.

Hands-on with Gemini 2.5

See how Gemini 2.5 uses its reasoning capabilities to create interactive simulations and do advanced coding.

Make an interactive animation

See how Gemini 2.5 Pro uses its reasoning capabilities to create an interactive animation of “cosmic fish” with a simple prompt.

Create your own dinosaur game

Watch Gemini 2.5 Pro create an endless runner game, using executable code from a single line prompt.

Code a fractal visualization

See how Gemini 2.5 Pro creates a simulation of intricate fractal patterns to explore a Mandelbrot set.

Plot interactive economic data

Watch Gemini 2.5 Pro use its reasoning capabilities to create an interactive bubble chart to visualize economic and health indicators over time.

Animate complex behavior

See how Gemini 2.5 Pro creates an interactive Javascript animation of colorful boids inside a spinning hexagon.

Code particle simulations

Watch Gemini 2.5 Pro use its reasoning capabilities to create an interactive simulation of a reflection nebula.

Adaptive and budgeted thinking

Adaptive controls and adjustable thinking budgets allow you to balance performance and cost.

  • Calibrated

    The model explores diverse thinking strategies, leading to more accurate and relevant outputs.

  • Controllable

    Developers have fine-grained control over the model's thinking process, allowing them to manage resource usage.

  • Adaptive

    When no thinking budget is set, the model assesses the complexity of a task and calibrates the amount of thinking accordingly.

Performance

Gemini 2.5 is state-of-the-art across a wide range of benchmarks.

View 2.5 tech report

Benchmarks

In addition to its strong performance on academic benchmarks, Gemini 2.5 tops the popular coding leaderboard WebDev Arena.

Benchmark
Gemini 2.5
Flash-Lite Preview 06-17
Non-thinking
Gemini 2.5
Flash-Lite Preview 06-17
Thinking
Gemini 2.5
Flash Non-thinking
Gemini 2.5
Flash Thinking
View 2.5 Flash
Gemini 2.5
Pro Thinking
View 2.5 Pro
Input price
$/1M tokens
(no caching) 		$0.10 $0.10 $0.30 $0.30 $1.25
 $2.50 > 200k tokens
Output price
$/1M tokens $0.40 $0.40 $2.50 $2.50 $10.00
 $15.00 > 200k tokens
Reasoning & knowledge Humanity's Last Exam (no tools)
5.1% 6.9% 8.4% 11.0% 21.6%
Science GPQA diamond
64.6% 66.7% 78.3% 82.8% 86.4%
Mathematics AIME 2025
49.8% 63.1% 61.6% 72.0% 88.0%
Code generation LiveCodeBench (UI: 1/1/2025-5/1/2025)
33.7% 34.3% 41.1% 55.4% 69.0%
Code editing Aider Polyglot
26.7%
27.1%
44.0%
56.7%
82.2%
Agentic coding SWE-bench Verified
single attempt 31.6% 27.6% 50.0% 48.9% 59.6%
   
multiple attempts 42.6% 44.9% 60.0% 60.3% 67.2%
Factuality SimpleQA
10.7% 13.0% 25.8% 26.9% 54.0%
Factuality FACTS grounding
84.1% 86.8% 83.4% 85.3% 87.8%
Visual reasoning MMMU
72.9% 72.9% 76.9% 79.7% 82.0%
Image understanding Vibe-Eval (Reka)
51.3% 57.5% 66.2% 65.4% 67.2%
Long context MRCR v2 (8-needle)
128k (average) 16.6% 30.6% 34.1% 54.3% 58.0%
   
1M (pointwise) 4.1% 5.4% 16.8% 21.0% 16.4%
Multilingual performance Global MMLU (Lite)
81.1% 84.5% 85.8% 88.4% 89.2%

Methodology

Gemini results: All Gemini scores are pass @1."Single attempt" settings allow no majority voting or parallel test-time compute; "multiple attempts" settings allow test-time selection of the candidate answer. They are all run with the AI Studio API with default sampling settings. To reduce variance, we average over multiple trials for smaller benchmarks. Aider Polyglot score is the pass rate average of 3 trials. Vibe-Eval results are reported using Gemini as a judge. Google's scaffolding for "multiple attempts" for SWE-Bench includes drawing multiple trajectories and re-scoring them using model's own judgement. For Aider results differ from the official leaderboard due to a difference in the settings used for evaluation (non-default).

Result sources: Where provider numbers are not available we report numbers from leaderboards reporting results on these benchmarks: Humanity's Last Exam results are sourced from https://agi.safe.ai/ and https://scale.com/leaderboard/humanitys_last_exam, LiveCodeBench results are from https://livecodebench.github.io/leaderboard.html (1/1/2025 - 5/1/2025 in the UI), Aider Polyglot numbers come from https://aider.chat/docs/leaderboards/. FACTS come from https://www.kaggle.com/benchmarks/google/facts-grounding. For MRCR v2 which is not publically available yet we include 128k results as a cumulative score to ensure they can be comparable with other models and a pointwise value for 1M context window to show the capability of the model at full length. The methodology has changed in this table vs previously published results for MRCR v2 as we have decided to focus on a harder, 8-needle version of the benchmark going forward.

Input and output price reflects text, image and video modalities.

Building responsibly in the agentic era

As we develop these new technologies, we recognize the responsibility it entails, and aim to prioritize safety and security in all our efforts.

Learn more

For developers

Gemini’s advanced thinking, native multimodality and massive context window empowers developers to build next-generation experiences.

Start building

Developer ecosystem

Build with cutting-edge generative AI models and tools to make AI helpful for everyone.

Google AI Studio

Build with the latest models from Google DeepMind

Gemini API

Easily integrate Google’s most capable AI model to your apps

Accessing our latest AI models

We want developers to gain access to our models as quickly as possible. We’re making these available through Google AI Studio.

Sign in to Google AI Studio

Get the latest updates

Sign up for news on the latest innovations from Google DeepMind.

Gemini Flash

General availability

Gemini 2.5 Flash

Best for fast performance on everyday tasks

Try in Google AI Studio

Our powerful and most efficient workhorse model designed for speed and low-cost.

Speed and value at scale

Ideal for tasks like summarization, chat applications, data extraction, and captioning.

  • Thinking budget

    Control how much 2.5 Flash reasons to balance latency and cost.

  • Natively multimodal

    Understands input across text, audio, images and video.

  • Long context

    Explore vast datasets with a 1-million token context window.

Preview

Native audio

Converse in more expressive ways with native audio outputs that capture the subtle nuances of how we speak. Seamlessly switch between 24 languages, all with the same voice.

  • Natural conversation

    Remarkable quality, more appropriate expressivity, and prosody, delivered with low latency so you can converse fluidly.

  • Style control

    Use natural language prompts to adapt the delivery within the conversation, steer it to adopt accents and produce a range of tones and expressions.

  • Tool integration

    Gemini 2.5 can use tools and function calling during dialog allowing it to incorporate real-time information or use custom developer-built tools.

  • Conversation context awareness

    Our system is trained to discern and disregard background speech, ambient conversations and other irrelevant audio.

Benchmarks

Benchmark
Gemini 2.5
Flash Thinking
Gemini 2.0
Flash
OpenAI
o4-mini
Claude
Sonnet 3.7 64k Extended thinking
Grok 3
Beta Extended thinking
DeepSeek
R1
Input price
$/1M tokens $0.30 $0.10 $1.10 $3.00 $3.00 $0.55
Output price
$/1M tokens $2.50 $0.40 $4.40 $15.00 $15.00 $2.19
Reasoning & knowledge Humanity's Last Exam (no tools)
11.0% 5.1% 14.3% 8.9% — 8.6%*
Science GPQA diamond
single attempt (pass@1) 82.8% 60.1% 81.4% 78.2% 80.2% 71.5%
   
multiple attempts — — — 84.8% 84.6% —
Mathematics AIME 2025
single attempt (pass@1) 72.0% 27.5% 92.7% 49.5% 77.3% 70.0%
   
multiple attempts — — — — 93.3% —
Code generation LiveCodeBench v5
single attempt (pass@1) 63.9% 34.5% — — 70.6% 64.3%
   
multiple attempts — — — — 79.4% —
Code editing Aider Polyglot
61.9% / 56.7% whole / diff-fenced
22.2% whole
68.9% / 58.2% whole / diff
64.9% diff
53.3% diff
56.9% diff
Agentic coding SWE-bench Verified
60.4% — 68.1% 70.3% — 49.2%
Factuality SimpleQA
26.9% 29.9% — — 43.6% 30.1%
Factuality FACTS Grounding
85.3% 84.6% 62.1% 78.8% 74.8% 56.8%
Visual reasoning MMMU
single attempt (pass@1) 79.7% 71.7% 81.6% 75.0% 76.0% no MM support
   
multiple attempts — — — — 78.0% no MM support
Image understanding Vibe-Eval (Reka)
65.4% 56.4% — — — no MM support
Long context MRCR v2
128k (average) 74.0% 36.0% 49.0% — 54.0% 45.0%
   
1M (pointwise) 32.0% 6.0% — — — —
Multilingual performance Global MMLU (Lite)
88.4% 83.4% — — — —

Methodology

Gemini results: All Gemini scores are pass @1 (no majority voting or parallel test time compute unless indicated otherwise). They are all run with the AI Studio API for the model-id gemini-2.5-flash-preview-05-20 and gemini-2.0-flash with default sampling settings. To reduce variance, we average over multiple trials for smaller benchmarks. Vibe-Eval results are reported using Gemini as a judge.

Non-Gemini results: All the results for non-Gemini models are sourced from providers' self reported numbers unless mentioned otherwise below. All SWE-bench Verified numbers follow official provider reports, using different scaffoldings and infrastructure. Google's scaffolding includes drawing multiple trajectories and re-scoring them using model's own judgement.

Thinking vs not-thinking: For Claude 3.7 Sonnet: GPQA, AIME 2024, MMMU come with 64k extended thinking, Aider with 32k, and HLE with 16k. Remaining results come from the non thinking model due to result availability. For Grok-3 all results come with extended reasoning except for SimpleQA (based on xAI reports) and Aider.

Single attempt vs multiple attempts: When two numbers are reported for the same eval higher number uses majority voting with n=64 for Grok models and internal scoring with parallel test time compute for Anthropic models.

Result sources: Where provider numbers are not available we report numbers from leaderboards reporting results on these benchmarks: Humanity's Last Exam results are sourced from https://agi.safe.ai/ and https://scale.com/leaderboard/humanitys_last_exam, AIME 2025 numbers are sourced from https://matharena.ai/. LiveCodeBench results are from https://livecodebench.github.io/leaderboard.html (10/1/2024 - 2/1/2025 in the UI), Aider Polyglot numbers come from https://aider.chat/docs/leaderboards/. FACTS come from https://www.kaggle.com/benchmarks/google/facts-grounding. For MRCR v2 which is not publically available yet we include 128k results as a cumulative score to ensure they can be comparable with previous results and a pointwise value for 1M context window to show the capability of the model at full length.

API costs are sourced from providers' website and are current as of May 20th.

* indicates evaluated on text problems only (without images)

Input and output price reflects text, image and video modalities.

Model information

2.5 Flash
Model deployment status General availability
Supported data types for input Text, Image, Video, Audio, PDF
Supported data types for output Text
Supported # tokens for input 1M
Supported # tokens for output 64k
Knowledge cutoff January 2025
Tool use Function calling
Structured output
Search as a tool
Code execution
Best for Cost-efficient thinking
Well-rounded capabilities
Availability Gemini app
Google AI Studio
Gemini API
Live API
Vertex AI