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
SimpleQA
4.0%自报
General
Global-MMLU-Lite
54.5%自报
Language
WMT24++
46.8%自报
MMLU-Pro
43.6%自报
ECLeKTic
4.6%自报
Math
GSM8k
89.2%自报
MATH
75.6%自报
MathVista-Mini
50.0%自报
HiddenMath
43.0%自报
Reasoning
BIG-Bench Hard
72.2%自报
HumanEvalOpenAI (2021)
71.3%自报
Natural2Code
70.3%自报
FACTS Grounding
70.1%自报
ChartQAMasry et al. (2022)
68.8%自报
MBPP
0.63 / 100自报
Bird-SQL (dev)
36.3%自报
GPQANYU + Cohere + Anthropic (2023)
30.8%自报
LiveCodeBench
12.6%自报
BIG-Bench Extra Hard
11.0%自报
Vision
DocVQADocVQA (2020)
75.8%自报
AI2D
74.8%自报
VQAv2 (val)
62.4%自报
TextVQA
57.8%自报
InfoVQA
50.0%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))Chat90
Instruction Following90
Structured Output90
Image To Text70
Grounding70
Math60
Multimodal60
Vision60
Reasoning50
General50
Healthcare50
Language40
Legal40
Factuality40
Finance40
Code40
Physics30
Biology30
Chemistry30
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。