Gemini 3.5

Frontier intelligence with action

Try in Gemini

Try in Google AI Studio

Gemini 3.6 Flash

Best for token efficiency in coding, knowledge work, and multimodal tasks

Try in Gemini

Learn more

Gemini 3.5 Flash-Lite

Best for high-volume tasks that need efficiency and intelligence

Try in Gemini

Learn more

3.5 Pro coming soon

Gemini 3.1 Pro

Best for complex tasks and bringing creative concepts to life

Try in Gemini

Learn more

Gemini 3.1 Deep Think

Best for modern challenges across science, research and engineering

Try in Gemini

Learn more

Explore the latest

Introducing our latest series of models combining frontier intelligence with action. Build more capable, intelligent agents efficiently.

Models
Capabilities
Performance
Hands-on
Showcase
Safety
Ecosystem
Try Gemini

Models

Completing everyday tasks, or solving your most challenging problems. Discover the right model for what you need

Capabilities

Agentic coding

Tackle complex, development tasks with advanced reasoning at speed.

Advanced multimodal understanding

Transform text, images, video and audio into rich interactive user interfaces.

Long horizon tasks

Execute sophisticated workflows over extended timeframes.

Multi-step problem-solving

Leverage advanced tools to solve demanding, real-world problems.

Performance

Benchmark	Notes	Gemini 3.6 Flash	Gemini 3.5 Flash	Gemini 3.1 Pro	GPT-5.6 Luna	Grok 4.5	Claude Sonnet 5
Input price $/1M tokens, no caching		$1.50	$1.50	$2.00	$1.00	$2.00	$3.00 $2.00 (temp discount)
Output price $/1M tokens		$7.50	$9.00	$12.00	$6.00	$6.00	$15.00 $10.00 (temp discount)
SWE-Bench Pro (Public) Diverse agentic coding tasks		58.7%	55.1%	54.2%	62.7%	64.7%	63.2%
DeepSWE v1.1 Long-horizon software engineering		49%	37%	12%	67%	54%	54%
Terminal-bench 2.1 Agentic terminal coding	Terminus-2 harness	78.0%	76.2%	73.8%	84.7%	83.3%	80.4%
MLE-Bench Machine Learning Engineering		63.9%	49.7%	42.6%	47.6%	43.2%	66.9%
OSWorld-Verified Agentic computer use		83.0%	78.4%	76.2%	72.6%	—	81.2%
GDPVal-AA v2 Knowledge work	Elo	1421	1349	965	1584	1535	1607
CharXiv Reasoning Information synthesis from complex charts	No tools	85.2%	84.2%	83.3%	82.7%	81.6%	77.0%
CharXiv Reasoning Information synthesis from complex charts	With tools	89.4%	84.9%	83.2%	—	—	88.3%
GDM-MRCR v2 (8-needle) Long context performance	128k (average)	91.8%	77.3%	84.9%	74.8%	81.4%	71.6%
GDM-MRCR v2 (8-needle) Long context performance	1M (pointwise)	54.0%	26.6%	26.3%	—	—	—

For details on our evaluation methodology please see deepmind.google/models/evals-methodology/gemini-3-6-flash

Hands-on

Explore what you can do with Gemini 3.6 Flash and 3.5 Flash-Lite

3.6 Flash vs. 3.5 Flash token efficiency SxS (API)

3.6 Flash shows better token efficiency and reduced verbosity than 3.5 Flash in an OSWorld verified task.

Financial data analysis (AIS)

3.6 Flash, using Managed Agents on AIS, can help parse through and analyze financial data and transcripts more efficiently and accurately than 3.5 Flash.

Code Migration Side by Side (AGY)

3.6 Flash executes code migrations, using multi-agent orchestration on AGY, with lower latency and higher quality than 3.5 Flash.

Custom Creative Tool (Gemini App)

3.6 Flash helps develop a photographic texture extractor for 3D workflows, using canvas.

3.5 Flash-Lite vs. 3.5 Flash latency SxS (API)

3.5 Flash-Lite executes high volume tasks at a lower latency than 3.5 Flash.

One prompt, 25 web design options (API)

Working alongside 3.6 Flash as the master agent, 3.5 Flash-Lite instantly generates 25 unique, ready-to-explore web design concepts.

Receipt analysis and translation at scale (API)

3.5 Flash-Lite can scale receipt translation and summarization with its multimodal understanding.

Rapid game development (API)

3.5 Flash-Lite builds a game by instantly generating and iterating through multiple options.

“Gemini 3.5 Flash-Lite delivers the intelligence, speed, and cost efficiency needed for Ashler’s agentic retrieval and tool-use tasks. It excels at analyzing fragmented infrastructure records while maintaining context across hundreds of deliverables, supporting our users as they build the next generation of power grids, transportation networks, and data centers.”
**Connor Goggins, Co-founder & CTO, Ashler**

“When evaluating models for Figma Make, we look for a balance of quality, speed, and cost. Gemini 3.6 Flash hits the sweet spot, offering a much faster way to explore and iterate on prototypes while upholding the quality of designs.”
**Matt Colyer, Director of Product, Figma**

“Gemini 3.6 Flash excels at document drafting and review in practice areas like capital markets and corporate M&A. Compared to its predecessor, Gemini 3.6 Flash showed strong gains in performance on our benchmarks and was notably more efficient, completing tasks 12% faster on average.”
**Niko Grupen, Head of Applied Research, Harvey**

“Gemini 3.6 Flash was the best model we tested for evidence finding in citation-heavy financial research, outperforming the frontier baselines in our internal evaluations. It surfaced the exact proof points analysts need from dense materials like transaction documents, covenant language, guidance, and operating metrics. For Hebbia users, that means faster answers backed by evidence they can trust.”
**Joe Renner, Evaluations Lead, Applied Research, Hebbia**

“Gemini 3.6 Flash delivers coding and reasoning quality close to Gemini Pro, while preserving the speed and cost profile that make Flash ideal for real-time developer workflows. The new model also improves low reasoning coding performance by 10–20% compared to the previous Flash generation.”
**Nick Frolov, Head of Product, Junie, JetBrains**

“Google Gemini 3.5 Flash-Lite is a huge jump from Gemini 3.1 Flash-Lite, punching way above its weight class. Gemini 3.5 Flash-Lite has proven incredibly fast and reliable. Ultimately, the model unlocks direct accessibility, giving users a highly responsive option they can choose on demand for smooth, uninterrupted execution.”
**Ashwin Kannan, Principal AI Engineer, Palo Alto Networks**

“Gemini 3.5 Flash-Lite landed on the Pareto frontier in our receipt extraction benchmark, offering one of the best tradeoffs we’ve tested between accuracy, latency, and cost. That combination is critical at Ramp, where we need to process receipts quickly and reliably at scale.”
**Veeral Patel, Head of Applied AI, Ramp**

Showcase

See how Shopify is using Gemini 3.5 Flash

Shopify is running subagents in parallel to analyze complex data over a long horizon for more accurate merchant growth forecasts at a global scale.

See how Macquarie Bank is using Gemini 3.5 Flash

Macquarie Bank is piloting how 3.5 Flash can accelerate customer onboarding by reasoning over complex 100+ page documents, retrieving relevant information and making reliable recommendations with low latency.

See how Salesforce is using Gemini 3.5 Flash

Salesforce is integrating 3.5 Flash into Agentforce to reliably automate complicated enterprise tasks by deploying multiple subagents that retain context and execute complex, multi-turn tool calling.

See how Ramp is using Gemini 3.5 Flash

3.5 Flash is helping Ramp enable smarter, more reliable OCR through multimodal understanding of complex invoices combined with reasoning over historical patterns.

See how Xero is using Gemini 3.5 Flash

Xero is deploying agents to autonomously manage complex, multi-week workflows, such as identifying suppliers and gathering information for 1099 tax forms, enabling small businesses to automate tedious admin tasks.

See how Databricks is using Gemini 3.5 Flash

Databricks is using agentic workflows to monitor and retrieve real-time information, reason across massive datasets to diagnose issues, identify fixes and propose solutions for data scientists.