Gemma 3 4B IT
Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions.
- Native PDF input
Pricing
Auto routing · per 1M tokens- Input
- $0.20
- Output
- $0.20
Specifications
- Context window
- 128K
- Max output
- 8.2K
- Parameters
- 4B
- Avg output (7d)
- 46 tokens
- Longer than 3% of models
Benchmarks
Benchmarks
Sourced from Artificial Analysis.
Intelligence Index
4.8
Coding Index
2.7
Agentic work
T²-Bench Telecom (legacy)
Legacy fallback · Conversational AI agents in dual-control scenarios
5.0%
Better than 6% of models compared
Document reasoning
AA-LCR v1.1
Long context reasoning with updated grading
6.7%
Better than 13% of models compared
Reasoning
HLE
Humanity's Last Exam
5.3%
Better than 32% of models compared
IFBench
Instruction-following benchmark
28.3%
Better than 12% of models compared
Coding
Terminal-Bench Hard (legacy)
Legacy fallback · Agentic coding and terminal use
0.8%
Better than 13% of models compared
LiveCodeBench
Contamination-free coding benchmark
11.2%
Better than 9% of models compared
Math
AIME 2025
American Invitational Mathematics Examination 2025
12.7%
Better than 15% of models compared
AIME
American Invitational Mathematics Examination
6.3%
Better than 22% of models compared
Math-500
Diverse mathematical problem solving benchmark
76.6%
Better than 39% of models compared
Knowledge
MMLU-Pro
Professional and academic subject knowledge
41.7%
Better than 9% of models compared
Legacy benchmarks
GPQA Diamond (legacy)
Graduate-level scientific reasoning
29.1%
Better than 5% of models compared
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
6.7%
Better than 13% of models compared
Last updated Oct 3, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…