Back to Models
google logo
google/gemma-3-27b-it
Not Available

Gemma 3 27B

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, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to [Gemma 2](google/gemma-2-27b-it)

3/12/2025
128,000 tokens
#90 Vision (Overall)
Specifications

Modalities

Input
text
image
Output
text

Supported Parameters

frequency_penalty
logit_bias
max_tokens
min_p
presence_penalty
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_k
top_p

Max Output Tokens

65,536
Leaderboard
Text
๐Ÿ†OverallELO: 1,366
#173
๐Ÿ‡ฏ๐Ÿ‡ตJapaneseELO: 1,310
#132
๐Ÿ‡จ๐Ÿ‡ณChineseELO: 1,373
#183
๐Ÿ‡ฐ๐Ÿ‡ทKoreanELO: 1,324
#140
๐Ÿ‡ฌ๐Ÿ‡งEnglishELO: 1,374
#182
frenchELO: 1,388
#152
germanELO: 1,371
#132
spanishELO: 1,350
#168
russianELO: 1,368
#158
๐Ÿ’ปCodingELO: 1,358
#228
๐ŸงฎMathELO: 1,322
#198
โœ๏ธCreative WritingELO: 1,348
#154
๐Ÿ“Instruction FollowingELO: 1,344
#183
๐ŸŒถ๏ธHard PromptsELO: 1,365
#190
๐Ÿ’ฌMulti-TurnELO: 1,358
#176
Vision
๐Ÿ†OverallELO: 1,159
#90