Intelligence index
Outperforms 80% of compared models
Gemini 3.5 Flash
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 loops, supporting text, image, video, audio, and PDF inputs.
Defaults to medium thinking effort for faster and more cost-efficient responses, with full support for thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs.
- Input / output price
- $1.5/$9per 1M tokens
- Context
- 1.0M
- Released
- 2026-05-19
Pricing
Artificial Analysis
Explore rankingsDesign Arena
Elo scores and win rates across design and agent tasks.
Category performance
1,000-1,500 EloModel Arena
SVG
1252Elo
Win rate 58.2%
Asciiart
1251Elo
Win rate 58.9%
Website
1267Elo
Win rate 53.7%
Game Development
1262Elo
Win rate 52.5%
UI Component
1267Elo
Win rate 54.2%
Code Categories
1265Elo
Win rate 54%
3D
1240Elo
Win rate 55.8%
Data Visualization
1239Elo
Win rate 53.1%
Agent Arena
Agenticslides(python-pptx)
1242Elo
Win rate 57.8%
Pptxslides
1244Elo
Win rate 57.7%
Agenticslides
1244Elo
Win rate 57.5%
Python-pptxslides
1247Elo
Win rate 57.4%
Agentichtmlslides
1162Elo
Win rate 45.8%
Agenticslides(html)
1162Elo
Win rate 45.7%
Agenticgamedev
1144Elo
Win rate 55.4%
Androidnative
1183Elo
Win rate 57.5%
Fullstack
1197Elo
Win rate 56.2%
Spreadsheet
1080Elo
Win rate 43.5%
Htmlslides
1039Elo
Win rate 46.5%
Blender3d
990Elo
Win rate 30.3%
Mobile Apps
1175Elo
Win rate 50.6%
Webapps
1202Elo
Win rate 52.2%
Godotgamedev
1098Elo
Win rate 43%
Related Models
Gemini 4 Argon
googleGemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across long, multi-step tasks and to turn long documents mixing text, tables, charts and images into a single grounded output. It leads the Vals Index across finance, legal, coding and tax work, and supports long decode of up to 1M output tokens in a single response.
- Context
- 1.0M
- Max output
- 943.7K
- Released
- 2026-10-13
- Input
- $2/M
- Output
- $10/M
- Cache read
- $0.1/M
Gemini 3.8 Flash
googleGemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
- Context
- 1.0M
- Max output
- 65.5K
- Released
- 2026-09-02
- Input
- $0.825/M
- Output
- $4.13/M
- Cache read
- $0.083/M
Gemini 3.7 Flash
googleGemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.
- Context
- 1.0M
- Max output
- 65.5K
- Released
- 2026-08-13
- Input
- $0.75/M
- Output
- $3.75/M
- Cache read
- $0.075/M