Gemma 3 12B Instruct
GoogleGemmaOpen WeightGemma · Commercial OK
描述
Gemma 3 12B is a 12-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.
發布日期
2025-03-12
參數規模
12.0B
上下文長度
131K
支援模態
image, text
能力雷達圖
23
general
10
coding
31
reasoning
23
science估算
0
agents
80
multimodal
Science 在缺少專門科學評測時使用推理能力代理估算。
排行榜排名
基準測試分數 (LLM Stats)
Biology
GPQA
40.9%自報
Code
HumanEval
85.4%自報
LiveCodeBench
24.6%自報
Factuality
FACTS Grounding
75.8%自報
SimpleQA
6.3%自報
Finance
MMLU-Pro
60.6%自報
General
IFEval
88.9%自報
Natural2Code
80.7%自報
MBPP
0.73 / 100自報
Global-MMLU-Lite
69.5%自報
MMMU (val)
59.6%自報
BIG-Bench Extra Hard
16.3%自報
Image To Text
DocVQA
87.1%自報
VQAv2 (val)
71.6%自報
TextVQA
67.7%自報
Language
BIG-Bench Hard
85.7%自報
WMT24++
51.6%自報
ECLeKTic
10.3%自報
Math
GSM8k
94.4%自報
MATH
83.8%自報
MathVista-Mini
62.9%自報
HiddenMath
54.5%自報
Multimodal
AI2D
84.2%自報
ChartQA
75.7%自報
InfoVQA
64.9%自報
Reasoning
Bird-SQL (dev)
47.9%自報
AA 評測指數
Math Index18.3
Intelligence Index8.8
Coding Index6.3
Math 5000.9
Mmlu Pro0.6
Ifbench0.4
Gpqa0.3
Aime0.2
Aime 250.2
Scicode0.2
Livecodebench0.1
Tau20.1
Lcr0.1
Hle0.0
Terminalbench Hard0.0
LLM Stats 分類評分
Structured Output90
Instruction Following90
Grounding80
Image To Text80
Vision70
Math70
Multimodal70
Code60
Finance60
Healthcare60
Legal60
Reasoning60
General50
Language50
Biology40
Chemistry40
Factuality40
Physics40
定價
輸入價格$0.09 / 1M tokens
輸出價格$0.29 / 1M tokens
混合價格(3:1)$0.14 / 1M tokens
速度
Tokens/秒27.2 tokens/s
首Token延遲1.77s
首回答延遲1.77s
可用提供商
(LS 內部計價單位)暫無提供商資料