跳转到主要内容

Gemma 3 4B Instruct

GoogleGemma开源权重Gemma · 商用许可

描述

Gemma 3 4B is a 4-billion-parameter vision-language model from Google, handling text and image input and generating text output. It features a 128K context window, multilingual support, and open weights. Suitable for question answering, summarization, reasoning, and image understanding tasks.

发布日期
2025-03-12
参数规模
4.0B
上下文长度
131K
支持模态
image, text

能力雷达图

50
general
40
coding
60
reasoning
26
science估算
54
agents
70
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
多模态榜129
31.0
LS

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Chat

IFEvalGoogle Research (2023)90.2%自报

Factuality

SimpleQA4.0%自报

General

Global-MMLU-Lite54.5%自报

Language

WMT24++46.8%自报
MMLU-Pro43.6%自报
ECLeKTic4.6%自报

Math

GSM8k89.2%自报
MATH75.6%自报
MathVista-Mini50.0%自报
HiddenMath43.0%自报

Reasoning

BIG-Bench Hard72.2%自报
HumanEvalOpenAI (2021)71.3%自报
Natural2Code70.3%自报
FACTS Grounding70.1%自报
ChartQAMasry et al. (2022)68.8%自报
MBPP0.63 / 100自报
Bird-SQL (dev)36.3%自报
GPQANYU + Cohere + Anthropic (2023)30.8%自报
LiveCodeBench12.6%自报
BIG-Bench Extra Hard11.0%自报

Vision

DocVQADocVQA (2020)75.8%自报
AI2D74.8%自报
VQAv2 (val)62.4%自报
TextVQA57.8%自报
InfoVQA50.0%自报
MMMU (val)48.8%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))
Chat
90
Instruction Following
90
Structured Output
90
Image To Text
70
Grounding
70
Math
60
Multimodal
60
Vision
60
Reasoning
50
General
50
Healthcare
50
Language
40
Legal
40
Factuality
40
Finance
40
Code
40
Physics
30
Biology
30
Chemistry
30

定价

输入价格免费
输出价格免费
混合价格(3:1)$0.0625 / 1M tokens

速度

暂无速度数据

供应商价格排行

供应商价格排行

7 个供应商

最便宜: Kilo Gateway最贵: AI/ML API
供应商输入输出
1Kilo Gateway最便宜
$0.04
$0.05
2Merge Gateway
$0.04
$0.08
3DeepInfra
$0.05
$0.1
4OpenRouter
$0.05
$0.1
5Hugging Face
$0.05
$0.1
6Deep Infra
$0.05
$0.1
7AI/ML API
$0.0529
$0.1058

比较该模型在不同 API 供应商之间的定价。

外部链接