Gemini 3.5 Flash-Lite
Google · 1 configuration
Intelligence22.2
Input / 1M$0.30
Output / 1M$2.50
Context1M
Tariff: Google · Source: artificial-analysis · USD per million tokens
Thinking configuration
What does more thinking buy you?
Compare this model’s measured thinking configurations.
Scroll the chart ↔ · tap a point for details
Efficient frontier: best measured score at each cost1 measured configurations · 0 without both values
Selected: thinking thinking · Click a point to switch configuration
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.
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
22.2 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
83.8 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
18.8 %SciCodeCode generation for scientific research problems.
41.3 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
53.6 %MMMU-ProMultimodal understanding of academic problems that include images.
79.0 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
29.5 %Specifications from the catalog
Inputtext, image, video, file, audio
Outputtext
Tool callingYes
Structured outputYes
Speed312.8 tok/s
First token8.76 s
Maximum output65.5K
Catalog listing date2026-07-21