DataLearner logo
GE

Gemini 3.6 Flash

Multimodal modelCoding modelGemini 3.6

Gemini 3.6 Flash

Release date: 2026-07-21Updated: 2026-08-22Views: 1,089
Live demoGitHubHugging FaceCompare
Parameters
No data
Context length
1M
Multilingual
No data
Reasoning ability
4/5

Gemini 3.6 Flash is a multimodal model from Google Deep Mind, released on 2026-07-21. It accepts text, image, audio, and video input and returns text output. The recorded context window is 1M, and the recorded maximum output is 64K. Cataloged capabilities include Reasoning model, Coding model, Function calling, and Tool use. The model weights are proprietary and are not published for download. Use the linked references to confirm current access, licensing, and provider-specific limits.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Gemini 3.6 Flash

Model basics

Reasoning traces
Supported
Thinking modes
Thinking Level · Medium (Default)Thinking Level · High
Context length
1M tokens
Max output length
64K tokens
Model type
Multimodal model
Modality (in / out)
Text, Image, Audio, Video → Text
Release date
2026-07-21
Model file size
No data
MoE architecture
No
Total params / Active params
No data / Not applicable
Knowledge cutoff
No data
Gemini 3.6 Flash

Open source & experience

Code license
Proprietary
Weights license
Proprietary
GitHub repo
N/A
Hugging Face
N/A
Live demo
aistudio.google.com
Gemini 3.6 Flash

Official resources

Paper
Paper
DataLearnerAI blog
N/A
Gemini 3.6 Flash

API details

API speed
4/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Learn about pricing modes
Standard
TypeConditionInputOutput
Text-$1.50/ 1M$7.50/ 1M
Batch
TypeConditionInputOutput
Text-$0.750/ 1M$3.75/ 1M
flex
TypeConditionInputOutput
Text-$0.750/ 1M$3.75/ 1M
priority
TypeConditionInputOutput
Text-$2.70/ 1M$13.50/ 1M
Cache PricingPrompt Cache
TypeTTLWriteRead
Text-—$0.075/ 1M

“—” means the modality is not billed in that direction, or the vendor has not published a price for it.

Gemini 3.6 Flash

Benchmark Results

Gemini 3.6 Flash currently shows benchmark results led by GPQA Diamond (8 / 271, score 94.13), Context Arena (17 / 126, score 88.78), OSWorld-Verified (5 / 26, score 83). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking
Tool usage

General Evaluation

2 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Low
86.36
86 / 271
GPQA Diamond
High
94.13
8 / 271

Writing and Creative Capabilities

1 evaluations
Benchmark / mode
Score
Rank/total
Creative Writing
Standard Mode
1599.70
34 / 99

Coding and Software Engineer

3 evaluations
Benchmark / mode
Score
Rank/total
SWE-Bench Pro - Public
Thinking ModeTools
58.70
16 / 60
WeirdML v2
HighTools
56.10
33 / 52
DeepSWE
Thinking ModeTools
49
28 / 35

Text Embedding

3 evaluations
Benchmark / mode
Score
Rank/total
Context Arena
Low
71.70
60 / 126
Context Arena
Medium
86.56
21 / 126
Context Arena
High
88.78
17 / 126

AI Agent - Tool Usage

3 evaluations
Benchmark / mode
Score
Rank/total
OSWorld-Verified
Thinking ModeTools
83
5 / 26
Terminal-Bench 2.1
Thinking ModeTools
78
27 / 49
MLE-Bench
Thinking ModeTools
63.90
1 / 3

Productivity Knowledge

1 evaluations
Benchmark / mode
Score
Rank/total
GDPval-AA v2
Thinking Mode
1421
18 / 25

Multimodal Understanding

2 evaluations
Benchmark / mode
Score
Rank/total
CharXiv RQ
Thinking Mode
85.20
10 / 19
CharXiv RQ
Thinking ModeTools
89.40
4 / 19

Long Context

2 evaluations
Benchmark / mode
Score
Rank/total
GDM-MRCR v2 (8-needle, 128K)
Thinking Mode
91.80
2 / 8
GDM-MRCR v2 (8-needle, 1M)
Thinking Mode
54
1 / 3

Math and Reasoning

2 evaluations
Benchmark / mode
Score
Rank/total
FrontierMath v2
High
58.95
23 / 58
FrontierMath Tier 4 v2
High
21.95
25 / 41
View benchmark analysisCompare with other models

Compare with other models

Gemini 3.6 Flash

Publisher

Google Deep Mind
Google Deep Mind
View publisher details
Gemini 3.6 Flash

Model Overview

Gemini 3.6 Flash is a multimodal model from Google Deep Mind, released on 2026-07-21.

It accepts text, image, audio, and video input and produces text output. Its cataloged capabilities include Reasoning model, Coding model, Function calling, Tool use, and Structured output. The recorded context window is 1M, and the recorded maximum output is 64K.

The model weights are proprietary and are not published for download. The page records 12 API pricing rules from DeepMind; current provider pricing and conditions should be checked before deployment. The evaluation section contains 15 cataloged benchmark results with their recorded modes and scores. The page links 2 release, model-card, repository, or provider references for checking the underlying claims. Specifications, availability, and prices can change; undisclosed values are intentionally left unstated.

Gemini 3.6 Flash

FAQ

What is Gemini 3.6 Flash?

Gemini 3.6 Flash is a multimodal model from Google Deep Mind, released on 2026-07-21. It accepts text, image, audio, and video input and returns text output. The recorded context window is 1M, and the recorded maximum output is 64K. Cataloged capabilities include Reasoning model, Coding model, Function calling, and Tool use. The model weights are proprietary and are not published for download. Use the linked references to confirm current access, licensing, and provider-specific limits.

What input and output modalities does Gemini 3.6 Flash support?

The current model record lists text, image, audio, and video as input and text as output.

What are the main recorded specifications for Gemini 3.6 Flash?

The recorded context window is 1M, and the recorded maximum output is 64K. Fields without a source-backed value remain undisclosed.

Does Gemini 3.6 Flash have API pricing?

The page records 12 API pricing rules from DeepMind; current provider pricing and conditions should be checked before deployment.

Are benchmark results available for Gemini 3.6 Flash?

The evaluation section contains 15 cataloged benchmark results with their recorded modes and scores. Compare only results that use the same benchmark version and evaluation mode.

Is Gemini 3.6 Flash open source?

The model weights are proprietary and are not published for download. Review the linked license text before commercial or derivative use.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code