跳转到主要内容

Gemini 2.5 Flash-Lite (Non-reasoning)

GoogleGemini开源权重Creative Commons Attribution 4.0 License

描述

Gemini 2.5 Flash-Lite is a model developed by Google DeepMind, designed to handle various tasks including reasoning, science, mathematics, code generation, and more. It features advanced capabilities in multilingual performance and long context understanding. It is optimized for low latency use cases, supporting multimodal input with a 1 million-token context length.

发布日期
2025-06-17
参数规模
—
上下文长度
1.0M
支持模态
audio, image, pdf, text, video

能力雷达图

40
general
30
coding
30
reasoning
51
science估算
30
agents
81
multimodal

缺少专门科学评测时,Science 由 LLM Stats 科学得分或推理能力估算。

排行榜排名

领域#排名分数来源
音频能力55
50.0
AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Factuality

SimpleQA10.7%自报

General

Global-MMLU-Lite81.1%自报
Aider-Polyglot26.7%自报

Long Context

MRCR v216.6%自报

Math

AIME 202549.8%自报

Multimodal

MMMU72.9%自报
Vibe-Eval51.3%自报

Reasoning

FACTS Grounding84.1%自报
GPQANYU + Cohere + Anthropic (2023)64.6%自报
LiveCodeBench33.7%自报
SWE-Bench Verified31.6%自报
Humanity's Last Exam5.1%自报
Arc2.5%自报

AA 评测指数

(Artificial Analysis)

暂无 AA 评测数据

LLM Stats 分类评分

(LLM Stats (zeroeval))
Language
80
Grounding
80
Healthcare
70
Multimodal
60
Physics
60
Biology
60
Chemistry
60
Reasoning
50
Factuality
50
General
40
Vision
40
Math
30
Frontend Development
30
Code
30
Long Context
20

定价

输入价格$0.1 / 1M tokens
输出价格$0.4 / 1M tokens
混合价格(3:1)$0.175 / 1M tokens
缓存读取价格$0.01 / 1M tokens

速度

Tokens/秒271.7
首Token延迟0.33s
首回答延迟0.33s

供应商价格排行

供应商价格排行

1 个供应商

供应商输入输出
1Google主要
$0.1
$0.4

比较该模型在不同 API 供应商之间的定价。

外部链接