Skip to content
llmwaves

Gemini 3.5 Flash Lite

Google · released Jul 21, 2026

ProprietaryReasoningTool useStructured outputVisionAudio inVideo in

Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.

Specification

Context window
1.05M
Max output
66K
Knowledge cutoff
Not stated
Parameters
Undisclosed
Licence
Proprietary
Serving providers
2
Moderated
No
Uptime
100.0%

Intelligence

37.4

84th percentile

Coding

49.3

Coding Index

Agentic

27.2

Agentic Index

Output speed

74 t/s

Median across providers

Latency

350ms

Time to first token

Cost per task

$0.22

Estimated

Benchmarks

Where the score comes from

The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.

Evaluation scores

Percentage correct · higher is better

  • GPQA Diamond
    83.8%
  • AA-LCR (long context)
    74.7%
  • SciCode
    40.9%
  • Humanity's Last Exam
    18.8%
  • τ²-bench (Telecom)
    17.5%

An evaluation missing from this list was not run for this model — it is not a zero.

View as table
EvaluationScore
GPQA Diamond83.8%
AA-LCR (long context)74.7%
SciCode40.9%
Humanity's Last Exam18.8%
τ²-bench (Telecom)17.5%

Against its peers

Intelligence Index · this model highlighted, nearest peers in grey

Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.

View as table
ModelIntelligence
MiMo-V2.538.0
Grok 4.2038.0
Grok 4.337.9
Ling-3.0-flash37.8
Qwen3.6 27B37.7
GPT-5.137.5
Gemini 3.5 Flash Lite37.4
Claude Sonnet 4.636.8

Percentile among all indexed models

Intelligence84th
Coding63th
Agentic50th

Pricing

What it costs to run

List prices per million tokens, plus what one representative task works out to.

List price

Input / 1M tokens
$0.3
Output / 1M tokens
$2.5
Cached input / 1M
$0.03
Blended 3:1
$0.85

One task, estimated

$0.22

Input tokens
50,000
Output tokens
80,000
Profile
Reasoning

Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).

Serving providers

Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.