modelgrep
G

Google: Gemini 3.5 Flash

google/gemini-3.5-flash

30th smartest of 179ReasoningToolsJSONVisionAudio
Use via OpenRouter ↗
Intelligence
43.3
30th of 179
Design Elo
1328
Game Dev
Speed
172
21st fastest
Latency
1.6s
first token
Input price
$1.50
232nd cheapest
Context
1.0M
66K max out

How it compares

Smarter than83%
of all ranked models
Faster than93%
of all ranked models
Cheaper than22%
of all ranked models

Overview

Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...

Benchmarks

independent · via OpenRouter
Artificial Analysis81th percentile
Intelligence Index
43.3
Coding Index
47.1
Agentic Index
51.0
GPQA Diamond
83%
Humanity's Last Exam
23%
SciCode
49%
Tau²-Bench (agentic)
59%
Design Arena · Elo22,698 tournaments
Game Dev
1328
3D
1314
asciiart
1312
UI Component
1304
svg
1303
codecategories
1300
Website
1293
fullstack
1283
webapps
1275
Data Viz
1268
mobileapps
1267
androidnative
1255
agenticslides(python-pptx)
1247
agenticslides
1244
agenticgamedev
1217
agentichtmlslides
1162
agenticslides(html)
1162

Providers & pricing (2)

ProviderIn $/MOut $/MUptime
Google AI Studiocache$1.50$9.0099.9%
Googlecache$1.50$9.0099.3%

Specifications

Context window1.0M
Max output66K
Knowledge cutoffJan 2025
Input modalitiestext, image, video, file, audio
Output modalitiestext
Prompt cachingSupported
Cache read price$0.150/M
ModeratedNo

Gemini 3.5 Flash FAQ

How much does Gemini 3.5 Flash cost?

Gemini 3.5 Flash costs $1.50 per million input tokens and $9.00 per million output tokens via OpenRouter, making it 232nd cheapest of 298 paid models.

How smart is Gemini 3.5 Flash?

Gemini 3.5 Flash scores 43.3 on the Artificial Analysis Intelligence Index, ranking 30th of 179 benchmarked models, with a GPQA Diamond score of 83%.

How fast is Gemini 3.5 Flash?

Gemini 3.5 Flash generates around 172 tokens per second with 1.6s time-to-first-token (p50), the 21st fastest tracked model.

What is Gemini 3.5 Flash's context window?

Gemini 3.5 Flash supports a 1.0M-token context window and can output up to 66K tokens. It accepts text, image, video, file, audio input.

Compare head-to-head