Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions.
Context Window
128.0K
Max Output
131.1K
Avg output tokens (7d)
123 tokens
Input Price (Auto)
$0.27/1M
Output Price (Auto)
$0.27/1M
Cache Read (Auto)
$0.14/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
3.8
Coding Index
5.8
Agentic work
AutomationBench-AA
Workflow automation with guardrail penalties
0.2%
Better than 2% of models compared
GDPval-AA v2
Economically valuable tasks (Elo)
-170 Elo
Better than 1% of models compared
Document reasoning
GDP.pdf
Professional PDF reasoning: all-pass rate
1.0%
Better than 9% of models compared
AA-LCR v1.1
Long context reasoning with updated grading
8.3%
Better than 16% of models compared
Reasoning
HLE
Humanity's Last Exam
4.2%
Better than 17% of models compared
IFBench
Instruction-following benchmark
36.7%
Better than 30% of models compared
Coding
Terminal-Bench v4.0
Practical coding and terminal tasks
0.0%
Better than 17% of models compared
SciCode
Python programming for scientific computing
16.4%
Better than 1% of models compared
LiveCodeBench
Contamination-free coding benchmark
13.7%
Better than 13% of models compared
Math
AIME 2025
American Invitational Mathematics Examination 2025
18.3%
Better than 21% of models compared
AIME
American Invitational Mathematics Examination
22.0%
Better than 48% of models compared
Math-500
Diverse mathematical problem solving benchmark
85.3%
Better than 54% of models compared
Knowledge
MMLU-Pro
Professional and academic subject knowledge
59.5%
Better than 23% of models compared
Legacy benchmarks
GPQA Diamond (legacy)
Graduate-level scientific reasoning
34.9%
Better than 11% of models compared
Terminal-Bench Hard (legacy)
Agentic coding and terminal use
0.8%
Better than 13% of models compared
T²-Bench Telecom (legacy)
Conversational AI agents in dual-control scenarios
10.8%
Better than 8% of models compared
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
8.3%
Better than 16% of models compared
Last updated Sep 13, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare Gemma 3 12B IT with similar models from the same provider or model family.
Gemma 3 27B IT
unsloth/gemma-3-27b-itGemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions.
Gemma 3 4B IT
unsloth/gemma-3-4b-itGemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions.
Gemini 3.8 Flash
google/gemini-3.8-flashGoogle's fast multimodal model for agentic workloads, including coding, tool use, image understanding, PDF and document extraction, audio, and video. Its capabilities, limits, reasoning behavior, and pricing currently mirror Gemini 3.7 Flash.
Gemini 3.7 Flash
google/gemini-3.7-flashGoogle's frontier-performance Flash model for multimodal and agentic workloads, including coding, tool use, image understanding, PDF and document extraction, audio, and video. Google reports 65.3% on DeepSWE v1.1, up from 49.0% for Gemini 3.6 Flash, and 34% on GDP.pdf, up from 14%.
Gemini 3.5 Flash Lite
google/gemini-3.5-flash-liteGoogle's cost-efficient Gemini 3.5 Flash Lite model for high-volume multimodal reasoning, tool use, and structured-output workloads.
Gemini 3.6 Flash
google/gemini-3.6-flashGoogle's GA Flash model delivers near-Pro coding and agentic capability at Flash-tier speed and cost, with improved token efficiency over Gemini 3.5 Flash. It is optimized for multi-step orchestration, full-stack code refactoring, general reasoning, and multimodal workflows.