Back to model catalog

Gemini · Model guide

Gemini 3.6 Flash

gemini/gemini-3.6-flash
Modalities
TextImageAudioVideoText
Context
1M
Max output
66K
Gemini 3.6 Flash

A more token-efficient workhorse model

Context window
1M
1,048,576 tokens
Max output
64K
65,536 tokens
Knowledge cutoff
2026-03
Newer than 3.5 Flash
Scaled agents
Multi-step tool calls, computer use, terminal automation
Coding and ML engineering
Long-horizon fixes, code migrations, ML experiments
Multimodal knowledge work
Document parsing, chart analysis, report drafting

Built on 3.5 Flash: same 1M context and adjustable thinking, with the knowledge cutoff moved to March 2026.

Overview

Gemini 3.6 Flash is Google DeepMind's workhorse model, released on July 21, 2026. It is built directly on Gemini 3.5 Flash and belongs to the Gemini 3 family of natively multimodal reasoning models. It keeps the 1M context window and adjustable thinking levels of 3.5 Flash, moves the knowledge cutoff forward to March 2026, and improves across coding, knowledge work, and multimodal understanding.

The pitch for this generation is not "bigger" but "cheaper to run". On the Artificial Analysis Index, 3.6 Flash consumes 17% fewer output tokens than 3.5 Flash for comparable tasks, and up to 65% fewer on long-horizon software engineering evals such as Datacurve's DeepSWE. It also takes fewer reasoning steps and tool calls to finish a multi-step workflow. CrossModel exposes it as gemini/gemini-3.6-flash.

Key capabilities

DimensionDetail
Context window1,048,576 tokens (about 1M)
Max output65,536 tokens (about 64K)
Knowledge cutoffMarch 2026
Input modalitiesText, image (Google's native model also supports audio, video, and PDF)
Output modalitiesText
Toolsfunction calling, structured outputs, streaming, adjustable thinking levels, context caching, code execution, computer use (preview)

Google publishes a single input/output rate for 3.6 Flash with no long-context tier, which suits frequent, cost-sensitive workloads at scale. See live rates in the model catalog.

Token efficiency

Token Efficiency

Same job, fewer tokens spent

Output token usage
−17%
Artificial Analysis Index, vs 3.5 Flash
Peak DeepSWE reduction
−65%
Datacurve long-horizon software engineering
01
Fewer reasoning steps
Less wandering inside one multi-step workflow
02
Fewer tool calls
Fewer repeated read-and-verify round trips
03
Fewer wasted edits
Less unwanted code editing and fewer execution loops
04
Lower cost per task
Efficiency stacks with a lower unit price per agentic task

Google's framing: fewer reasoning steps and tool calls, which lowers the total cost of a single agentic task.

For teams building agents, the real bill is not "price per million tokens" — it is "how many tokens does one task burn". That is exactly what 3.6 Flash optimizes: fewer output tokens, fewer reasoning steps, fewer repeated tool calls, and fewer wasted code edits and execution loops. −17% is the cross-task average; −65% is the extreme observed on DeepSWE — and the workloads with the biggest gap tend to be the long-horizon tasks where 3.5 Flash was most prone to wandering.

Benchmarks

Three axes dominate the evaluation story: long-horizon coding and terminal work, computer use, and long-context retrieval. The official model card reports all of these alongside 3.5 Flash, 3.1 Pro, GPT-5.6 Luna, Grok 4.5, and Claude Sonnet 5.

Coding, terminal, and computer use

Coding & Agents

Coding and agent scores move up across the board

DeepSWE v1.1
49%
3.5 Flash 37%
MLE-Bench
63.9%
3.5 Flash 49.7%
OSWorld-Verified
83.0%
3.5 Flash 78.4%
Terminal-bench 2.1
78.0%
3.5 Flash 76.2%
SWE-Bench Pro
58.7%
3.5 Flash 55.1%

Values in parentheses are Gemini 3.5 Flash on the same benchmark, from the official model card (July 2026).

The clearest gains are in long-horizon engineering work: DeepSWE v1.1 rises from 37% to 49% and MLE-Bench (machine learning engineering) from 49.7% to 63.9% — the latter lands near Claude Sonnet 5's 66.9%, an unusual position for a Flash-tier model. OSWorld-Verified 83.0% is the one row where 3.6 Flash leads every model in the comparison, and Google has made computer use a built-in client-side tool in the Gemini API and Gemini Enterprise. Terminal-bench 2.1 78.0% and SWE-Bench Pro 58.7% are steady progress but still trail pricier flagships like Luna, Grok 4.5, and Sonnet 5.

Knowledge work and long context

Knowledge Work & Long Context

Long context is the single biggest jump this generation

GDPval-AA v2
1421
Elo, 3.5 Flash 1349
MRCR v2 @128K
91.8%
3.5 Flash 77.3%
MRCR v2 @1M
54.0%
Full-window, 3.5 Flash 26.6%
CharXiv no tools
85.2%
3.5 Flash 84.2%
CharXiv with tools
89.4%
3.5 Flash 84.9%

MRCR v2 at the full 1M window goes from 26.6% to 54.0%, moving full-window retrieval into usable territory.

GDPval-AA v2 climbs from 1349 to 1421 Elo, a measure of real knowledge-work output. Customers such as Hebbia and Harvey report it is particularly capable at multimodal tasks — document parsing, chart and data analysis, report drafting — which the chart-reasoning result of CharXiv 85.2% (89.4% with tools) backs up.

The real leap is long context: MRCR v2 @128K goes from 77.3% to 91.8%, and the full 1M window doubles from 26.6% to 54.0%. The previous generation's conclusion — that precise retrieval across a filled million-token window remains hard industry-wide — is meaningfully rewritten here. 54% is still not high-fidelity, but it moves full-window retrieval from "basically unusable" into "usable with verification".

Safety

3.6 Flash ships with enhanced Frontier Safety safeguards in the CBRN (chemical, biological, radiological, nuclear) and cyber-offense domains, making it substantially more resistant to jailbreaks while being trained to minimize refusals for beneficial uses. The model card reports a 5.45 percentage-point improvement in multilingual safety and 1.35 points in text safety over 3.5 Flash, with unjustified refusals up only 0.25 points. Under the Frontier Safety Framework it reaches no Critical Capability Levels.

When to use it

  • Scaled agent workflows: frequent multi-step tool calls, computer use, and terminal automation, where token efficiency directly sets the cost per task.
  • Long-horizon coding and migrations: DeepSWE- and MLE-Bench-shaped work that needs sustained edit, verify, and correct loops.
  • Very long document understanding: cross-document retrieval over contracts, codebases, filings, and meeting transcripts — near-lossless within 128K and usable at the full window.
  • Multimodal knowledge work: document parsing, chart and data analysis, and report drafting with structured outputs.

If you are on Gemini 3.5 Flash today, 3.6 Flash is close to a no-tradeoff swap: same context and interface shape, better scores, fewer tokens burned. Reach for a Pro tier or another vendor's flagship only when you need top-end single-shot coding results.

CrossModel exposes Gemini 3.6 Flash through an OpenAI-compatible /v1/chat/completions API. Current pricing is available in the model catalog.