Home/Models/Gemini 3.1 Flash Lite Preview
Google DeepMind logo

Gemini 3.1 Flash Lite Preview

by Google DeepMind · Released Mar 2026

Multimodal1M ContextPreview
Compare
Context
1.0M tokens (~524 books)
Input $/1M
$0.25
Output $/1M
$1.50
Type
multimodal
License
Proprietary
Benchmarks
5 tested
Data updated today
About

Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...

Tested on 5 benchmarks with 0.0% average. Top scores: Chatbot Arena Elo — Overall (1435.5%), Chatbot Arena Elo — Coding (1238.1%), Artificial Analysis — Quality Index (33.5%).

Capabilities
speed
49.6
#36 globally
Benchmark Scores
Compare All
Tested on 5 benchmarks · Ranked across 2 categories
Score Distribution (all 233 models)
0255075100
Chatbot Arena Elo — Overall

Chatbot Arena overall Elo rating. Crowdsourced human preference ranking from blind head-to-head comparisons across all topics.

1436
Chatbot Arena Elo — Coding

Chatbot Arena coding Elo. Human preference ranking specifically for coding tasks and technical questions.

1238
Artificial Analysis — Quality Index

Artificial Analysis Quality Index. Composite quality score combining multiple benchmark results into a single metric.

33.5
Artificial Analysis — Coding Index

Artificial Analysis Coding Index. Composite coding quality score from multiple code benchmarks.

30.1
Artificial Analysis — Agentic Index

Artificial Analysis Agentic Index. Composite score measuring agent capability across tool use and planning tasks.

25.7
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Documentation
BenchGecko API
gemini-3-1-flash-lite-preview
Specifications
  • Typemultimodal
  • Context1.0M tokens (~524 books)
  • ReleasedMar 2026
  • LicenseProprietary
  • Statuspreview
  • Cost / Message~$0.002
Available On
Google DeepMind logoGoogle DeepMind$0.25
Categories
Share & Export
Tweet
Gemini 3.1 Flash Lite Preview is a proprietary multimodal AI model by Google DeepMind, released in March 2026. Context window: 1M tokens.