Google · Open weights
Gemma 3 12B IT
Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions.
- PDF input
- Input
- Text
- Output
- Text
- Discovery tier
- Open weights
Pricing
USD per 1M tokens- Input
- $0.27
- Output
- $0.27
Reference prices as published by the model provider. API example
Specifications
- Context window
- 131.1K
- Max output
- 16.4K
- Average output (7 days)
- 168 tokens
- Longer than 16% of 465 models
Side by side
Compare models
Put Gemma 3 12B IT next to up to three other models. The comparison stays in the link, so you can share it.
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
Intelligence Index
3.8
Better than 0% of 326 scored models
Indexes
Coding Index
5.8Composite of the coding evaluations
Better than 2% of 168 scored models
Math Index
18.3Composite of the math evaluations
Better than 18% of 118 scored models
Agentic work
AutomationBench-AA
0.2%Workflow automation, penalized for guardrail violations
Better than 0% of 173 scored models
AutomationBench-AA tasks completed
0.0%Workflows finished end to end without a guardrail violation
Better than 0% of 173 scored models
Document reasoning
GDP.pdf
1.0%Professional reasoning over PDF documents, all-pass rate
Better than 4% of 171 scored models
AA-LCRv1.1
8.3%Reasoning across long documents
Better than 4% of 309 scored models
Reasoning and knowledge
Humanity’s Last Exam
4.2%Expert-level questions across academic fields
Better than 8% of 323 scored models
GPQA Diamond
34.9%Graduate-level science questions
Better than 3% of 291 scored models
MMLU-Pro
59.5%Multi-subject knowledge and reasoning
Better than 10% of 132 scored models
IFBench
36.7%Following precise output instructions
Better than 17% of 215 scored models
Coding
Terminal-Benchv4.0
0.0%Practical software engineering in a terminal
Better than 0% of 171 scored models
SciCode
16.4%Scientific computing in Python
Better than 1% of 174 scored models
LiveCodeBench
13.7%Recent competitive programming problems
Better than 5% of 129 scored models
Math
AIME 2025
18.3%Competition mathematics, 2025 problems
Better than 18% of 118 scored models
AIME
22.0%Competition mathematics
Better than 29% of 72 scored models
MATH-500
85.3%Competition math problems
Better than 35% of 73 scored models
Legacy evaluations
Terminal-Bench Hard
0.8%Earlier terminal task suite
Better than 1% of 212 scored models
τ²-Bench Telecom
10.8%Tool use in a customer-support simulation
Better than 1% of 214 scored models
AA-LCR (unversioned)
8.3%Long-context reasoning, earlier grading
Better than 4% of 309 scored models
Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis
Live routing data
Performance and reliability
Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.
- Request success (24h)
- 100.0%
- Reliable
- Healthy (98% or more)
- Degraded (90–98%)
- Down (under 90%)
- No requests
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "unsloth/gemma-3-12b-it",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="unsloth/gemma-3-12b-it",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)Related models
Other Google models, starting with the same family.
