GE

Gemma 3 - 27B (IT)

Chat modelGemmaGemma 3

Gemma 3 - 27B (IT)

Release date: 2025-03-12Updated: 2025-03-12 22:17:451,494
Live demoGitHubHugging FaceCompare
Parameters
27B
Context length
128K
Chinese support
Supported
Reasoning ability

Gemma 3 - 27B (IT) is an AI model published by Google Deep Mind, released on 2025-03-12, for Chat model, with 27B parameters, and 128K context length, requiring about 54.8GB storage, under the Gemma Terms of Use license, with a 95.90 score on GSM8K.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Gemma 3 - 27B (IT)

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
128K tokens
Max output length
No data
Model type
Chat model
Modality (in / out)
No data
Release date
2025-03-12
Model file size
54.8GB
MoE architecture
No
Total params / Active params
27B / N/A
Knowledge cutoff
No data
Gemma 3 - 27B (IT)

Open source & experience

Code license
Weights license
Gemma Terms of Use- 免费商用授权
GitHub repo
GitHub link unavailable
Live demo
No live demo
Gemma 3 - 27B (IT)

Official resources

Gemma 3 - 27B (IT)

API details

API speed
No data
No public API pricing yet.
Gemma 3 - 27B (IT)

Benchmark Results

Gemma 3 - 27B (IT) currently shows benchmark results led by MATH (6 / 42, score 89), GSM8K (5 / 26, score 95.90), BBH (9 / 20, score 87.60). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking

General Knowledge

5 evaluations
Benchmark / mode
Score
Rank/total
BBH
Standard Mode
87.60
9 / 20
MMLU
Standard Mode
78.60
52 / 65
MMLU Pro
Standard Mode
67.50
96 / 126
GPQA Diamond
Standard Mode
42.40
162 / 179
36.83
13 / 14

Math and Reasoning

3 evaluations
Benchmark / mode
Score
Rank/total
GSM8K
Standard Mode
95.90
5 / 26
MATH
Standard Mode
89
6 / 42
25.30
57 / 62

Coding and Software Engineer

3 evaluations
Benchmark / mode
Score
Rank/total
HumanEval
Standard Mode
87.80
18 / 39
MBPP
Standard Mode
74.40
16 / 28
LiveCodeBench
Standard Mode
29.70
116 / 120

常识推理

1 evaluations
Benchmark / mode
Score
Rank/total
HellaSwag
Standard Mode
85.60
3 / 3

阅读理解

1 evaluations
Benchmark / mode
Score
Rank/total
DROP
Standard Mode
77.20
8 / 9

Common Sense

1 evaluations
Benchmark / mode
Score
Rank/total
SimpleQA
Standard Mode
10
40 / 45

Multimodal Understanding

1 evaluations
Benchmark / mode
Score
Rank/total
MMMU
Standard Mode
64.90
27 / 28

Agent Level Benchmark

1 evaluations
Benchmark / mode
Score
Rank/total
Aider-Polyglot
Standard Mode
4.90
58 / 59

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

Gemma 3 - 27B (IT)

Publisher

Google Deep Mind
View publisher details
Gemma 3 - 27B (IT)

Model Overview

Gemma 3 - 27B (IT) is an AI model published by Google Deep Mind, released on 2025-03-12, for Chat model, with 27B parameters, and 128K context length, requiring about 54.8GB storage, under the Gemma Terms of Use license, with a 95.90 score on GSM8K.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code