Gemma 3 27B Instruct
GoogleGemmaOpen WeightGemma · Commercial OK
描述
Gemma 3 27B is a 27-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 complex question answering, summarization, reasoning, and image understanding tasks.
發布日期
2025-03-12
參數規模
27.0B
上下文長度
131K
支援模態
image, text
能力雷達圖
26
general
12
coding
34
reasoning
28
science估算
0
agents
70
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
42.4%自報
Code
HumanEval
87.8%自報
LiveCodeBench
29.7%自報
Factuality
FACTS Grounding
74.9%自報
SimpleQA
10.0%自報
Finance
MMLU-Pro
67.5%自報
General
IFEval
90.4%自報
Natural2Code
84.5%自報
Global-MMLU-Lite
75.1%自報
MBPP
0.74 / 100自報
MMMU (val)
64.9%自報
BIG-Bench Extra Hard
19.3%自報
Image To Text
DocVQA
86.6%自報
VQAv2 (val)
71.0%自報
TextVQA
65.1%自報
Language
BIG-Bench Hard
87.6%自報
WMT24++
53.4%自報
ECLeKTic
16.7%自報
Math
GSM8k
95.9%自報
MATH
89.0%自報
MathVista-Mini
67.6%自報
HiddenMath
60.3%自報
Multimodal
AI2D
84.5%自報
ChartQA
78.0%自報
InfoVQA
70.6%自報
Reasoning
Bird-SQL (dev)
54.4%自報
AA 評測指數
Math Index20.7
Intelligence Index10.3
Coding Index9.6
Math 5000.9
Mmlu Pro0.7
Gpqa0.4
Ifbench0.3
Aime0.3
Scicode0.2
Aime 250.2
Livecodebench0.1
Tau20.1
Lcr0.1
Hle0.0
Terminalbench Hard0.0
LLM Stats 分類評分
Structured Output90
Instruction Following90
Math80
Vision70
Finance70
Grounding70
Healthcare70
Image To Text70
Legal70
Multimodal70
Code60
General60
Language60
Reasoning60
Biology40
Chemistry40
Factuality40
Physics40
定價
輸入價格$0.11 / 1M tokens
輸出價格$0.25 / 1M tokens
混合價格(3:1)$0.145 / 1M tokens
速度
Tokens/秒31.4 tokens/s
首Token延遲0.73s
首回答延遲0.73s
可用提供商
(LS 內部計價單位)暫無提供商資料