Gemini 3.5 Flash-Lite Benchmark Details

Gemini 3.5 Flash-Lite currently shows benchmark results led by Creative Writing (41 / 99, score 1556), GPQA Diamond (114 / 270, score 83.33), Context Arena (57 / 126, score 72.57). This page also compares it with 2 competitor models and 2 predecessor or same-series models, including performance and pricing views when available.

Benchmark Results

Gemini 3.5 Flash-Lite

Benchmark Results

Other

2 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Low

75.76

166 / 270

GPQA Diamond

High

83.33

114 / 270

Writing and Creative Capabilities

1 evaluations

Benchmark / mode

Score

Rank/total

Creative Writing

Standard Mode

1556

41 / 99

Coding and Software Engineer

1 evaluations

Benchmark / mode

Score

Rank/total

SWE-Bench Pro - Public

Thinking EnabledTools

54.20

36 / 60

Text Embedding

3 evaluations

Benchmark / mode

Score

Rank/total

Context Arena

Low

61.90

75 / 126

Context Arena

Medium

65.50

72 / 126

Context Arena

High

72.57

57 / 126

AI Agent - Tool Usage

2 evaluations

Benchmark / mode

Score

Rank/total

OSWorld-Verified

Thinking EnabledTools

14 / 26

Terminal-Bench 2.1

Thinking EnabledTools

47 / 49

Productivity Knowledge

1 evaluations

Benchmark / mode

Score

Rank/total

AA-Briefcase

Thinking EnabledTools

636.95

17 / 19

Math and Reasoning

2 evaluations

Benchmark / mode

Score

Rank/total

FrontierMath v2

High

25.96

46 / 58

FrontierMath Tier 4 v2

High

39 / 40

Compare with other models

Competitor Comparison

Benchmark scores for Gemini 3.5 Flash-Lite compared against top models in its class

Gemini 3.5 Flash-LiteGPT-5.6 Luna DeepSeek-V4-Flash

Benchmark categories:

The chart shows each model’s highest score per benchmark within the current filter. Out-of-100 benchmarks use raw heights; out-of-range benchmarks are scaled within that benchmark while labels keep the original scores.

7 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.

Benchmark	Gemini 3.5 Flash-LiteCurrent	GPT-5.6 Luna	DeepSeek-V4-Flash
GPQA Diamond Accuracy 科学与综合推理	83.33Thinking Level · High	91.60Thinking Level · High	88.10Thinking Level · High
Creative Writing Elo、大模型评判两两对战写作和创作	1556.00Standard Mode	1826.60Standard Mode	1555.70Standard Mode
SWE-Bench Pro - Public Accuracy 编程与软件工程	54.20Thinking Enabled ｜ Tools	--	52.60Thinking Level · Extra High ｜ Tools
Context Arena Accuracy (8 needles, 4K-128K context) 文本向量检索	72.57Thinking Level · High	81.80Thinking Level · High	69.42Thinking Enabled
Terminal-Bench 2.1 Accuracy AI Agent - 工具使用	54.00Thinking Enabled ｜ Tools	84.70Thinking Level · High	82.70Thinking Level · High ｜ Tools
AA-Briefcase Elo score 生产力知识	636.95Thinking Enabled ｜ Tools	1359.76Thinking Level · High ｜ Tools	--
FrontierMath v2 Accuracy (verification_code) 数学推理	25.96Thinking Level · High	82.11Thinking Level · High	--

Standard API Pricing: Gemini 3.5 Flash-Lite vs. Peer Models

Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.

Source: DataLearnerAI. Standard text prices shown here use the default supplier. · USD / 1M tokens

Model	Supplier	Standard input	Standard output	Base price applies to
Gemini 3.5 Flash-Lite	DeepMind	$0.3 / 1M tokens	$2.5 / 1M tokens	—
GPT-5.6 Luna	OpenAI	$0.2 / 1M tokens	$1.2 / 1M tokens	—
DeepSeek-V4-Flash	DeepSeek-AI	$0.14 / 1M tokens	$0.28 / 1M tokens	—

Version History

How each version of the Gemini 3.5 Flash-Lite series stacks up on benchmark tests

Gemini 3.5 Flash-LiteGemini 3.1 Flash-Lite Gemini 2.5 Flash-Lite

Benchmark categories:

1 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.· Click a row to view its trend chart.

Benchmark	Gemini 3.5 Flash-LiteCurrent	Gemini 3.1 Flash-Lite	Gemini 2.5 Flash-Lite
GPQA Diamond Accuracy 科学与综合推理	83.33Thinking Level · High	81.82Thinking Level · High	66.70Standard Mode

Single-Benchmark Version Trend

Viewing: GPQA Diamond · 科学与综合推理

Benchmark

NormalNormal + ToolsThinkingThinking + ToolsDeepDeep + Tools

X-axis shows model and release date, Y-axis shows score; solid lines connect the same mode across versions, while dotted guides align modes within the same generation.

Standard API Pricing Across the Gemini 3.5 Flash-Lite Series

Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.

Source: DataLearnerAI. Standard text prices shown here use the default supplier. · USD / 1M tokens

Model	Supplier	Standard input	Standard output	Base price applies to
Gemini 3.5 Flash-Lite	DeepMind	$0.3 / 1M tokens	$2.5 / 1M tokens	—
Gemini 2.5 Flash-Lite	Google Deep Mind	$0.1 / 1M tokens	$0.4 / 1M tokens	—