Skip to content
Yardstick
  1. Models
  2. Google
  3. Gemini 3.5 Flash-Lite

Gemini 3.5 Flash-Lite

Google · Fast & cheap · Jul 21, 2026

The quickest and cheapest current Gemini, for high-throughput pipelines and sub-agents.

Model documentation (opens in a new tab)
Artificial Analysis Intelligence Index
22.2#25 of 29
API price per 1M tokens
$0.30 / $2.50input / output · $0.85 blended
Context window
1Mup to 66K output tokens
Output speed
346 t/s8.6s to first answer

Benchmark results

Each row shows this model (blue) against every other model in the catalogue (grey), worst on the left, best on the right.

Overall capability

  • Artificial Analysis Intelligence Index22.2#25 of 29
    11.357.6
  • LiveBench63.9%#23 of 23

    High effort

    63.9%83.4%

Coding

  • Arena WebDev1,440#24 of 27
    1,2631,814

Multimodal

  • Arena Vision1,264#10 of 15
    1,1991,301

Human preference

  • Arena Text1,455#17 of 24
    1,4251,525

Specs & pricing

Developer
Google
Released
Jul 21, 2026
Availability
Generally available
API model ID
gemini-3.5-flash-lite
Weights
Proprietary (API only)
Reasoning
Adjustable effort
Knowledge cutoff
Mar 2026
Accepts
Text, Image, Video, Audio
Produces
Text
Context window
1,048,576 tokens
Max output
65,536 tokens
Input price
$0.30 / 1M tokens
Output price
$2.50 / 1M tokens
Cached input
$0.03 / 1M tokens

Closest alternatives

Models from other labs nearest to Gemini 3.5 Flash-Lite on Artificial Analysis Intelligence Index.

  • Kimi K2.7 Code

    Moonshot AI

    Intelligence 25.8 · $0.95 / $4

    Compare side by side

  • Muse Glimmer 30B

    Meta

    Intelligence 17.5 · Self-hosted

    Compare side by side

  • MiniMax M3

    MiniMax

    Intelligence 29.2 · $0.30 / $1.20

    Compare side by side

Sources

  • Model documentation (opens in a new tab)
  • Model card (opens in a new tab)
  • Pricing (opens in a new tab)
Yardstick

A plain reading of how today’s SI models compare. Scores are taken from each benchmark’s own leaderboard wherever one exists; anything a lab reported about its own model is marked.

Data as of Oct 8, 2026.

Explore

  • Models
  • Compare
  • Benchmarks
  • Value
  • Labs
  • Methodology & sources

Sources

  • Artificial Analysis (opens in a new tab)
  • Arena (opens in a new tab)
  • Epoch AI Benchmarking Hub (opens in a new tab)
  • ARC Prize (opens in a new tab)
  • Terminal-Bench (opens in a new tab)
  • Scale AI Labs (opens in a new tab)

Yardstick is an independent reference and is not affiliated with, sponsored by or endorsed by any lab listed. Product names and logos are trademarks of their respective owners and are used only to identify them. Benchmarks are imperfect proxies: check a model on your own task before you commit to it.

  • Models
  • Compare
  • Benchmarks
  • Value
  • Labs
  • Models
  • Compare
  • Benchmarks
  • Value
  • Labs
  • Models
  • Compare
  • Benchmarks
  • Value
  • Labs