Home/Models/Gemma 2 27B
Google DeepMind logo

Gemma 2 27B

by Google DeepMind · Released Jul 2024

Open Source
57.2
avg score
Rank #100
Compare
Better than 64% of all models
Context
8K tokens (~4 books)
Input $/1M
$0.65
Output $/1M
$0.65
Type
text
License
Open Source
Benchmarks
13 tested
Data updated today
About

Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...

Tested on 13 benchmarks with 40.1% average. Top scores: Chatbot Arena Elo — Overall (1288.7%), GSM8K (84.9%), IFEval (79.8%).

Looking for similar performance at lower cost?
Qwen2.5 7B Instruct scores 57.4 (100% as good) at $0.04/1M input · 94% cheaper
Capabilities
reasoning
9.1
#167 globally
math
34.5
#148 globally
knowledge
41.1
#177 globally
language
79.8
#55 globally
general
49.3
#10 globally
Benchmark Scores
Compare All
Tested on 13 benchmarks · Ranked across 6 categories
Score Distribution (all 274 models)
0255075100
▲ You are here
MUSR

HuggingFace MuSR (Multi-Step Reasoning). Tests multi-hop reasoning requiring chaining multiple facts together.

9.1
GSM8K

Grade school math word problems. 8,500 problems testing multi-step arithmetic reasoning. A foundational math benchmark.

84.9
MATH level 5

Competition-level math from AMC, AIME, and olympiad problems. Level 5 is the hardest tier, requiring creative problem-solving.

27.9
MATH Level 5

HuggingFace evaluation of MATH Level 5 problems. Competition math requiring advanced reasoning and proof construction.

23.9
MMLU

Massive Multitask Language Understanding. 57 subjects from STEM, humanities, and social sciences. The most widely-cited knowledge benchmark.

67.6
PIQA

Physical Intuition QA. Tests understanding of everyday physical interactions and commonsense physics.

67.4
MMLU-PRO

HuggingFace MMLU-Pro. Harder version of MMLU with 10 answer choices instead of 4 and more challenging questions.

38.4
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Documentation
BenchGecko API
gemma-2-27b-it
Specifications
  • Typetext
  • Context8K tokens (~4 books)
  • ReleasedJul 2024
  • LicenseOpen Source
  • StatusActive
  • Cost / Message~$0.002
Available On
Google DeepMind logoGoogle DeepMind$0.65
Share & Export
Tweet
Gemma 2 27B is an open-source text AI model by Google DeepMind, released in July 2024. It has an average benchmark score of 57.2. Context window: 8K tokens.