Google

Gemini 2.5 Flash-Lite

Multimodal
Zero-eval
#1MRCR v2
#1Arc
#3FACTS Grounding

by Google

About

Gemini 2.5 Flash-Lite is a multimodal language model developed by Google. The model shows competitive results across 13 benchmarks. It excels particularly in FACTS Grounding (84.1%), Global-MMLU-Lite (81.1%), MMMU (72.9%). With a 1.1M token context window, it can handle extensive documents and complex multi-turn conversations. The model is available through 1 API provider. As a multimodal model, it can process and understand text, images, and other input formats seamlessly. Released in 2025, it represents Google's latest advancement in AI technology.

Pricing Range
Input (per 1M)$0.10 -$0.10
Output (per 1M)$0.40 -$0.40
Providers1
Timeline
AnnouncedJun 17, 2025
ReleasedJun 17, 2025
Knowledge CutoffJan 1, 2025
Specifications
Capabilities
Multimodal
License & Family
License
Creative Commons Attribution 4.0 License
Benchmark Performance Overview
Performance metrics and category breakdown

Overall Performance

13 benchmarks
Average Score
40.8%
Best Score
84.1%
High Performers (80%+)
2

Performance Metrics

Max Context Window
1.1M
Avg Throughput
5.7 tok/s
Avg Latency
0ms

Top Categories

factuality
84.1%
vision
72.9%
code
42.5%
general
35.8%
reasoning
2.5%
Benchmark Performance
Top benchmark scores with normalized values (0-100%)
Ranking Across Benchmarks
Position relative to other models on each benchmark

FACTS Grounding

Rank #3 of 9
#1Gemini 2.5 Flash
85.3%
#2Gemini 2.5 Pro Preview 06-05
87.8%
#3Gemini 2.5 Flash-Lite
84.1%
#4Gemini 2.0 Flash
83.6%
#5Gemini 2.0 Flash-Lite
83.6%
#6Gemma 3 12B
75.8%

Global-MMLU-Lite

Rank #4 of 14
#1Gemini 2.5 Flash
88.4%
#2Gemini 2.5 Pro
88.6%
#3Gemini 2.5 Pro Preview 06-05
89.2%
#4Gemini 2.5 Flash-Lite
81.1%
#5Gemini 2.0 Flash-Lite
78.2%
#6Gemma 3 27B
75.1%
#7Gemma 3 12B
69.5%

MMMU

Rank #15 of 52
#12Llama 4 Maverick
73.4%
#13Claude Sonnet 4
74.4%
#14GPT-4.1
74.8%
#15Gemini 2.5 Flash-Lite
72.9%
#16GPT-4.1 mini
72.7%
#17GPT-4o
72.2%
#18Gemini 2.0 Flash
70.7%

GPQA

Rank #44 of 115
#41GPT-4.1 mini
65.0%
#42QwQ-32B
65.2%
#43DeepSeek R1 Distill Llama 70B
65.2%
#44Gemini 2.5 Flash-Lite
64.6%
#45DeepSeek R1 Distill Qwen 32B
62.1%
#46Gemini 2.0 Flash
62.1%
#47o1-mini
60.0%

Vibe-Eval

Rank #6 of 8
#3Gemini 1.5 Pro
53.9%
#4Gemini 2.0 Flash
56.3%
#5Gemini 2.5 Flash
65.4%
#6Gemini 2.5 Flash-Lite
51.3%
#7Gemini 1.5 Flash
48.9%
#8Gemini 1.5 Flash 8B
40.9%
All Benchmark Results for Gemini 2.5 Flash-Lite
Complete list of benchmark scores with detailed information
FACTS Grounding
FACTS Grounding benchmark
factuality
text
0.84
84.1%
Self-reported
Global-MMLU-Lite
Global-MMLU-Lite benchmark
general
text
0.81
81.1%
Self-reported
MMMU
MMMU benchmark
vision
multimodal
0.73
72.9%
Self-reported
GPQA
GPQA benchmark
general
text
0.65
64.6%
Self-reported
Vibe-Eval
Vibe-Eval benchmark
code
text
0.51
51.3%
Self-reported
AIME 2025
AIME 2025 benchmark
general
text
0.50
49.8%
Self-reported
LiveCodeBench
LiveCodeBench benchmark
code
text
0.34
33.7%
Self-reported
SWE-Bench Verified
SWE-Bench Verified benchmark
general
text
0.32
31.6%
Self-reported
Aider-Polyglot
Aider-Polyglot benchmark
general
text
0.27
26.7%
Self-reported
MRCR v2
MRCR v2 benchmark
general
text
0.17
16.6%
Self-reported
Showing 1 to 10 of 13 benchmarks