Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. All models overview
  2. Text
  3. Google

Gemini 3.6 Flash

Google's GA Flash model delivers near-Pro coding and agentic capability at Flash-tier speed and cost, with improved token efficiency over Gemini 3.5 Flash. It is optimized for multi-step orchestration, full-stack code refactoring, general reasoning, and multimodal workflows.

  • Reasoning
  • Vision
  • Audio Input
  • Video Input
  • Native PDF input
  • Tool Calling
  • Structured Output

Added Jul 21, 2026

Pricing

Auto routing · per 1M tokens
Input
$0.75
Output
$3.75
Cache read
$0.075
Compare provider prices

Specifications

Context window
1M
Max output
65.5K

Benchmarks

Sourced from LMArena.

Arena Score

1482.7

Overall Rank

#28 / 422

Votes

35,294

Confidence Interval

1478.3 - 1487.2

Category Scores

Coding

#43 / 417

10,124 votes

1518.1

Math

#18 / 405

1,702 votes

1500.9

Longer Query

#40 / 400

16,632 votes

1484.9

Creative Writing

#19 / 420

7,355 votes

1471.4

Instruction Following

#39 / 422

12,785 votes

1472.9

Hard Prompts

#33 / 422

23,566 votes

1501.1

Additional Categories
22

French

#11 / 302

1,130 votes

1511.5

Russian

#22 / 386

4,075 votes

1493.4

Chinese

#23 / 396

2,573 votes

1533.0

Industry Entertainment And Sports And Media

#24 / 420

9,042 votes

1461.4

Industry Writing And Literature And Language

#25 / 421

9,610 votes

1474.3

Multi Turn

#26 / 420

5,736 votes

1489.8

Spanish

#26 / 304

930 votes

1474.8

German

#27 / 321

583 votes

1484.6

Exclude Ties

#28 / 422

26,405 votes

1494.9

Japanese

#28 / 288

611 votes

1475.2

Non English

#28 / 422

20,410 votes

1472.4

Korean

#32 / 289

629 votes

1440.0

English

#33 / 422

14,882 votes

1485.4

Industry Life And Physical And Social Science

#35 / 420

5,665 votes

1495.3

Industry Software And It Services

#35 / 422

14,170 votes

1511.2

Polish

#38 / 243

527 votes

1476.4

Industry Business And Management And Financial Operations

#40 / 415

6,689 votes

1473.8

Industry Legal And Government

#42 / 394

2,931 votes

1480.6

Industry Mathematical

#42 / 403

2,034 votes

1486.5

Hard Prompts English

#45 / 420

9,951 votes

1498.4

Expert

#47 / 372

4,029 votes

1498.8

Industry Medicine And Healthcare

#57 / 392

2,488 votes

1480.9

Published 2026-11-18 · Matched as Gemini 3.6 Flash (High) · CC BY 4.0

LMArena Dataset

Leaderboard results

BenchmarkScoreRank on NanoGPT
Epoch AI Benchmarking Hub

Epoch AI data, CC BY 4.0 · Updated Nov 19, 2026

Epoch Capabilities Index

155.2

#41 of 113

FrontierMath v2 (Tiers 1–3)

58.9%

#44 of 83

GPQA Diamond

94.1%

#14 of 118

SimpleQA Verified

66.2%

#17 of 83

FrontierMath v2 (Tier 4)

22.0%

#47 of 67

OTIS Mock AIME 2024–2025

94.2%

#48 of 120

MirrorCode

23.3%

#35 of 41

Chess Puzzles

42.0%

#34 of 82

Mystery Game Puzzles

30.0%

#36 of 79

EQ-Bench

EQ-Bench data, MIT · Updated Nov 19, 2026

Creative Writing v3

1602

#43 of 91

UGI Leaderboard

UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026

UGI Score

55.8

#19 of 125

UGI Willingness

2.2

#87 of 125

UGI Writing

69.8

#11 of 125

Filtered and ranked to models on NanoGPT.

Providers

Provider information for this model’s automatic routing. These routes cannot be selected individually.

Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)

Cache write /M
Auto
Auto
Recommended
$0.75$3.75$0.075$0.0417N/AN/A
Google AI Studio
Google AI Studio
US
$0.75$3.75$0.075$0.0417N/AN/A
Google Vertex
Google Vertex
US
$0.75$3.75$0.075$0.0417N/AN/A
Privacy:No training on prompts

Related text models

Compare Gemini 3.6 Flash with similar models from the same provider or model family.

Gemini 3.8 Flash

google/gemini-3.8-flash

Google's fast multimodal model for agentic workloads, including coding, tool use, image understanding, PDF and document extraction, audio, and video. Its capabilities, limits, reasoning behavior, and pricing currently mirror Gemini 3.7 Flash.

Gemini 3.7 Flash

google/gemini-3.7-flash

Google's frontier-performance Flash model for multimodal and agentic workloads, including coding, tool use, image understanding, PDF and document extraction, audio, and video. Google reports 65.3% on DeepSWE v1.1, up from 49.0% for Gemini 3.6 Flash, and 34% on GDP.pdf, up from 14%.

Gemini 3.5 Flash Lite

google/gemini-3.5-flash-lite

Google's cost-efficient Gemini 3.5 Flash Lite model for high-volume multimodal reasoning, tool use, and structured-output workloads.

Gemini 3.5 Flash

google/gemini-3.5-flash

Google's speed-focused Gemini Flash model for frontier multimodal intelligence across text, images, audio, video, PDFs, and code. Built for agentic coding, reliable tool use, structured outputs, and long-context workflows. Audio input costs $3.00 per million audio tokens.

Gemini 3.5 Flash Thinking

google/gemini-3.5-flash-thinking

Gemini 3.5 Flash with higher thinking enabled for harder reasoning, agentic coding, tool use, multimodal analysis, and long-context workflows. Audio input costs $3.00 per million audio tokens.

Gemini Flash Latest

google/gemini-flash-latest

Compatibility alias that routes to the newest version of Gemini Flash. Currently routes to Gemini 3.8 Flash.