Gemini 2.5 Flash-Lite
Google · 2 thinking configurations
Intelligence8.5
Input / 1M$0.10
Output / 1M$0.40
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 cost2 measured configurations · 0 without both values
Selected: thinking thinking · Click a point to switch configuration
Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
8.5 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
62.5 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
6.8 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
18.4 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
49.9 %MMMU-ProMultimodal understanding of academic problems that include images.
58.2 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
17.9 %Specifications from the catalog
Inputtext, image, file, audio, video
Outputtext
Tool callingYes
Structured outputYes
Speed352.8 tok/s
First token20.12 s
Maximum output65.5K
Catalog listing date2025-07-22