Gemma 3 27B Instruct
GoogleGemmaOpen WeightGemma · Commercial OK
Description
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.
Release Date
2025-03-12
Parameters
27.0B
Context Length
131K
Modalities
image, text
Capability Radar
23
general
15
coding
34
reasoning
28
scienceest.
28
agents
70
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 456 | 9.0 | AA |
| General Ranking | 409 | 25.0 | AA |
| Math Reasoning | 247 | 35.0 | AA |
| Multimodal Ranking | 45 | 76.0 | LS |
| Reasoning | 84 | 54.0 | LS |
| Science | 399 | 27.0 | AA |
Benchmark Scores (LLM Stats)
Biology
GPQA
42.4%SR
Code
HumanEval
87.8%SR
LiveCodeBench
29.7%SR
Factuality
FACTS Grounding
74.9%SR
SimpleQA
10.0%SR
Finance
MMLU-Pro
67.5%SR
General
IFEval
90.4%SR
Natural2Code
84.5%SR
Global-MMLU-Lite
75.1%SR
MBPP
0.74 / 100SR
MMMU (val)
64.9%SR
BIG-Bench Extra Hard
19.3%SR
Image To Text
DocVQA
86.6%SR
VQAv2 (val)
71.0%SR
TextVQA
65.1%SR
Language
BIG-Bench Hard
87.6%SR
WMT24++
53.4%SR
ECLeKTic
16.7%SR
Math
GSM8k
95.9%SR
MATH
89.0%SR
MathVista-Mini
67.6%SR
HiddenMath
60.3%SR
Multimodal
AI2D
84.5%SR
ChartQA
78.0%SR
InfoVQA
70.6%SR
Reasoning
Bird-SQL (dev)
54.4%SR
AA Evaluation Indices
Math Index20.7
Intelligence Index4.8
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 Category Scores
Instruction Following90
Structured Output90
Math80
Image To Text70
Legal70
Multimodal70
Finance70
Grounding70
Healthcare70
Vision70
Language60
Reasoning60
General60
Code60
Physics40
Factuality40
Biology40
Chemistry40
Pricing
Input Price$0.11 / 1M tokens
Output Price$0.25 / 1M tokens
Blended Price (3:1)$0.145 / 1M tokens
Speed
Tokens/sec0.0
Time to First Token0.00s
Time to Answer0.00s
Provider Price Ranking
Provider Price Ranking
12 providers
Cheapest: ChutesMost Expensive: STACKIT
ProviderInputOutput
1ChutesCheapest
$0.0272
$0.1087
2Kilo Gateway
$0.03
$0.11
3OpenRouter
$0.08
$0.16
4Nebius Token Factory
$0.1
$0.3
5GooglePRIMARY
$0.11
$0.25
6NovitaAI
$0.119
$0.2
7Amazon Bedrock
$0.12
$0.2
8Venice AI
$0.12
$0.2
9Scaleway
$0.25
$0.5
10LLM Gateway
$0.27
$0.27
11NanoGPT
$0.2992
$0.2992
12STACKIT
$0.49
$0.71
Compare pricing across different API providers for this model.