Gemma 3 12B Instruct
GoogleGemmaOpen WeightGemma · Commercial OK
Description
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.
Release Date
2025-03-12
Parameters
12.0B
Context Length
131K
Modalities
image, text
Capability Radar
20
general
15
coding
31
reasoning
23
scienceest.
26
agents
80
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 459 | 8.0 | AA |
| General Ranking | 421 | 24.0 | AA |
| Math Reasoning | 253 | 33.0 | AA |
| Multimodal Ranking | 46 | 76.0 | LS |
| Reasoning | 96 | 48.0 | LS |
| Science | 431 | 22.0 | AA |
Benchmark Scores (LLM Stats)
Biology
GPQA
40.9%SR
Code
HumanEval
85.4%SR
LiveCodeBench
24.6%SR
Factuality
FACTS Grounding
75.8%SR
SimpleQA
6.3%SR
Finance
MMLU-Pro
60.6%SR
General
IFEval
88.9%SR
Natural2Code
80.7%SR
MBPP
0.73 / 100SR
Global-MMLU-Lite
69.5%SR
MMMU (val)
59.6%SR
BIG-Bench Extra Hard
16.3%SR
Image To Text
DocVQA
87.1%SR
VQAv2 (val)
71.6%SR
TextVQA
67.7%SR
Language
BIG-Bench Hard
85.7%SR
WMT24++
51.6%SR
ECLeKTic
10.3%SR
Math
GSM8k
94.4%SR
MATH
83.8%SR
MathVista-Mini
62.9%SR
HiddenMath
54.5%SR
Multimodal
AI2D
84.2%SR
ChartQA
75.7%SR
InfoVQA
64.9%SR
Reasoning
Bird-SQL (dev)
47.9%SR
AA Evaluation Indices
Math Index18.3
Intelligence Index3.4
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 Category Scores
Instruction Following90
Structured Output90
Image To Text80
Grounding80
Math70
Multimodal70
Vision70
Legal60
Reasoning60
Finance60
Healthcare60
Code60
Language50
General50
Physics40
Factuality40
Biology40
Chemistry40
Pricing
Input Price$0.09 / 1M tokens
Output Price$0.29 / 1M tokens
Blended Price (3:1)$0.14 / 1M tokens
Speed
Tokens/sec0.0
Time to First Token0.00s
Time to Answer0.00s
Provider Price Ranking
Provider Price Ranking
6 providers
Cheapest: ChutesMost Expensive: Cloudflare AI Gateway
ProviderInputOutput
1ChutesCheapest
$0.03
$0.1
2Helicone
$0.05
$0.1
3Amazon Bedrock
$0.05
$0.1
4GooglePRIMARY
$0.09
$0.29
5NanoGPT
$0.272
$0.272
6Cloudflare AI Gateway
$0.35
$0.56
Compare pricing across different API providers for this model.