1 / 3
Swipe to compare

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 delivers faster token generation and improved benchmark performance compared to earlier Flash models, with thinking disabled by default to prioritize speed. Designed for high-throughput use cases where rapid response is more important than deep reasoning, it offers the most affordable entry point in the Gemini 2.5 lineup.

Author
GoogleGoogle
Release Date
2025-09-25
Knowledge Cutoff
2025-01-31
License
Proprietary
I/O Format
Context Length
1.0M / 66K
API I/O (1M)
$0.1 / $0.4
How to Use
API Access
Output Speed
105 tok/s
Arena Overall
1380
Intelligence Index
19.4
Coding Index
14.5
Math Index
46.7
LiveBench
41.5
ForecastBench
56.9
GPQA Diamond
65.1%
HLE
4.6%
MMLU-Pro
79.6%
AIME 2025
46.7%
MATH-500
LB Reasoning
43.3
LB Math
61.0
LB Data Analysis
47.0
LiveCodeBench
64.1%
LB Coding
66.4
LB Agentic
5.0
TAU2
30.4%
TerminalBench
7.6%
SciCode
28.5%
IFBench
41.8%
AA-LCR
0.5
Hallucination (HHEM)
3.3%
Factual Consistency (HHEM)
96.7%
LB Language
52.0
LB Instruction Following
23.1