Skip to main content

Gemini 3.6 Flash (high)

GoogleGemini

Description

Gemini 3.6 Flash is Google's workhorse multimodal reasoning model for agentic coding, knowledge work, and spatial reasoning. It supports text, image, video, audio, and PDF inputs, a 1 million-token context window, and a 65,536-token text output. It improves quality and token efficiency over Gemini 3.5 Flash.

Release Date
2026-07-21
Parameters
Context Length
1.0M
Modalities
audio, image, pdf, text, video

Capability Radar

48
general
67
coding
93
reasoning
68
scienceest.
80
agents
90
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Code Ranking23
89.0
AA
General Ranking24
83.0
AA
Science21
86.0
AA

Benchmark Scores (LLM Stats)

Agents

GDPval-AA1421.00 / 3000SR
OSWorld-Verified83.0%SR
Terminal-Bench 2.178.0%SR
MLE-Bench63.9%SR
SWE-Bench Pro58.7%SR
DeepSWE 1.149.0%SR

General

MRCR v2 (8-needle)54.0%SR

Multimodal

CharXiv-R89.4%SR

AA Evaluation Indices

Coding Index
69.2
Intelligence Index
50.1
Gpqa
0.9
Terminalbench V2 1
0.8
Lcr
0.7
Scicode
0.5
Hle
0.4
Tau Banking
0.2

LLM Stats Category Scores

Legal
100
Finance
100
Reasoning
100
Agents
100
General
100
Multimodal
90
Vision
90
Tool Calling
80
Code
60
Long Context
50

Pricing

Input Price$1.5 / 1M tokens
Output Price$7.5 / 1M tokens
Blended Price (3:1)$3 / 1M tokens
Cache Read Price$0.15 / 1M tokens

Speed

Tokens/sec311.0
Time to First Token12.80s
Time to Answer12.80s

Provider Price Ranking

Provider Price Ranking

9 providers

Cheapest: NanoGPTMost Expensive: Venice AI
ProviderInputOutput
1NanoGPTCheapest
$0.0748
$0.306
2GooglePRIMARY
$1.5
$7.5
3OpenRouter
$1.5
$7.5
4Kilo Gateway
$1.5
$9
5Vercel AI Gateway
$1.5
$7.5
6Vertex
$1.5
$9
7OrcaRouter
$1.5
$9
8Merge Gateway
$1.5
$9
9Venice AI
$1.875
$9.375

Compare pricing across different API providers for this model.

External Sources