Gemini 2.0 Flash-Lite (Feb '25)

GoogleGeminiProprietary

描述

A Gemini 2.0 Flash model optimized for cost efficiency and low latency

发布日期

2025-02-25

参数规模

—

上下文长度

—

支持模态

image, text

能力雷达图

general

coding

reasoning

science

agents

multimodal

排行榜排名

领域	#排名	分数	来源
代码能力榜	505	20.0	AA
通用能力榜	440	32.0	AA
多模态榜	93	48.0	LS
科学能力	489	28.0	AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Audio

CoVoST2

38.4%自报

Factuality

SimpleQA

21.7%自报

General

Global-MMLU-Lite

78.2%自报

Language

MMLU-Pro

71.6%自报

Long Context

MRCR 1M

58.0%自报

Math

MATH

86.8%自报

HiddenMath

55.3%自报

Multimodal

MMMU

68.0%自报

Reasoning

FACTS Grounding

83.6%自报

Bird-SQL (dev)

57.4%自报

GPQANYU + Cohere + Anthropic (2023)

51.5%自报

LiveCodeBench v5

28.9%自报

Vision

EgoSchema

67.2%自报

AA 评测指数

(Artificial Analysis)

Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))

87.3

Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))

72.4

Gpqa(NYU + Cohere + Anthropic (2023))

53.5

Aime(MAA (Mathematical Association of America))

27.7

Livecodebench(UC Berkeley + MIT + Cornell (2024))

18.5

Intelligence Index(Artificial Analysis)

7.4

Hle(Center for AI Safety + Scale AI (2025))

3.4

LLM Stats 分类评分

(LLM Stats (zeroeval))

Grounding

Legal

Math

Multimodal

Finance

Healthcare

Vision

Language

Long Context

Reasoning

General

Physics

Factuality

Biology

Chemistry

Speech To Text

Audio

定价

输入价格免费

输出价格免费

混合价格(3:1)免费

速度

Tokens/秒0.0

首Token延迟0.00s

首回答延迟0.00s

供应商价格排行

暂无提供商数据

外部链接

LLM Stats Artificial Analysis