Gemma 3 27B Instruct
GoogleGemma開源權重Gemma · 商用許可
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
23
general
13
coding
34
reasoning
28
science
28
agents
70
multimodal
排行榜排名
基準測試分數 (LLM Stats)
(LLM Stats (zeroeval))Chat
IFEvalGoogle Research (2023)
90.4%自報
Factuality
SimpleQA
10.0%自報
General
Global-MMLU-Lite
75.1%自報
Language
MMLU-Pro
67.5%自報
WMT24++
53.4%自報
ECLeKTic
16.7%自報
Long Context
MRCR v2 (8-needle)
13.5%自報
Math
GSM8k
95.9%自報
MATH
89.0%自報
MathVista-Mini
67.6%自報
HiddenMath
60.3%自報
Reasoning
HumanEvalOpenAI (2021)
87.8%自報
BIG-Bench Hard
87.6%自報
Natural2Code
84.5%自報
ChartQAMasry et al. (2022)
78.0%自報
FACTS Grounding
74.9%自報
MBPP
0.74 / 100自報
Bird-SQL (dev)
54.4%自報
GPQANYU + Cohere + Anthropic (2023)
42.4%自報
LiveCodeBench
29.7%自報
BIG-Bench Extra Hard
19.3%自報
Vision
DocVQADocVQA (2020)
86.6%自報
AI2D
84.5%自報
VQAv2 (val)
71.0%自報
InfoVQA
70.6%自報
TextVQA
65.1%自報
MMMU (val)
64.9%自報
AA 評測指數
(Artificial Analysis)Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))88.3
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))66.9
Gpqa(NYU + Cohere + Anthropic (2023))42.8
Ifbench(Google Research (2023))31.8
Aime(MAA (Mathematical Association of America))25.3
Scicode(UIUC + Argonne National Lab (2024))23.3
Math Index(Artificial Analysis)20.7
Aime 25(MAA (Mathematical Association of America))20.7
Livecodebench(UC Berkeley + MIT + Cornell (2024))13.7
Tau2(Sierra + U Toronto + Vector Institute (2025))10.5
Coding Index(Artificial Analysis)10.1
Lcr(Artificial Analysis)7.3
Intelligence Index(Artificial Analysis)4.9
Terminalbench V2 14.5
Hle(Center for AI Safety + Scale AI (2025))4.4
Terminalbench Hard(Stanford × Laude Institute (2026))3.8
Tau Banking0.8
Terminalbench V4 00.0
LLM Stats 分類評分
(LLM Stats (zeroeval))Chat90
Instruction Following90
Structured Output90
Math80
Image To Text70
Legal70
Multimodal70
Finance70
Grounding70
Healthcare70
Vision70
Language60
Reasoning60
General60
Code60
Physics40
Factuality40
Biology40
Chemistry40
Long Context10
定價
輸入價格免費
輸出價格免費
混合價格(3:1)免費
快取讀取價格$0.04 / 1M tokens
速度
Tokens/秒0.0
首Token延遲0.00s
首回答延遲0.00s
供應商價格排行
供應商價格排行
9 個供應商
最便宜: DeepInfra最貴: STACKIT
供應商輸入輸出
1DeepInfra最便宜
$0
$0
2OpenRouter
$0.08
$0.45
3Hugging Face
$0.08
$0.16
4Deep Infra
$0.08
$0.16
5Kilo Gateway
$0.08
$0.16
6Merge Gateway
$0.08
$0.45
7Nebius Token Factory
$0.1
$0.3
8NovitaAI
$0.119
$0.2
9STACKIT
$0.53
$0.76
比較該模型在不同 API 供應商之間的定價。