Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
Tested on 7 benchmarks with 42.2% average. Top scores: Lech Mazur Writing (79.9%), MATH level 5 (74.0%), GeoBench (52.0%).
Multi-language code editing from Aider. Tests editing ability across Python, JavaScript, TypeScript, Java, C++, Go, Rust, and more.
Competition-level math from AMC, AIME, and olympiad problems. Level 5 is the hardest tier, requiring creative problem-solving.
Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.
Writing quality evaluation by Lech Mazur. Tests prose quality, coherence, and stylistic ability.
Geography benchmark testing knowledge of world geography, landmarks, borders, and geopolitical facts.
LiveBench fiction analysis. Tests literary comprehension and creative text understanding.
- Typemultimodal
- Context131K tokens (~66 books)
- ReleasedMar 2025
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.000