Gemma 3 27B Benchmark Scores & Performance

Benchmark analysis of Gemma 3 27B by Google across 14 tests.

Creator

Google

Source Type

Open Weight

Reasoning

Non-Reasoning

Context Window

32K

Overall Score

36#72 of 88

Knowledge Benchmarks

MMLU
45
GPQA
44
SuperGPQA
42
OpenBookQA
40

Coding Benchmarks

HumanEval
37

Mathematics Benchmarks

AIME 2023
45
AIME 2024
47
AIME 2025
46
HMMT Feb 2023
41
HMMT Feb 2024
43
HMMT Feb 2025
42
BRUMO 2025
44

Reasoning Benchmarks

SimpleQA
43
MuSR
41

Frequently Asked Questions

How does Gemma 3 27B perform overall in AI benchmarks?

Gemma 3 27B ranks #72 out of 88 models with an overall score of 36. It is created by Google and features a 32K context window.

Is Gemma 3 27B good for knowledge and understanding?

Gemma 3 27B ranks #72 out of 88 models in knowledge and understanding benchmarks with an average score of 42.8. There are stronger options in this category.

Is Gemma 3 27B good for coding and programming?

Gemma 3 27B ranks #72 out of 88 models in coding and programming benchmarks with an average score of 37. There are stronger options in this category.

Is Gemma 3 27B good for mathematics?

Gemma 3 27B ranks #72 out of 88 models in mathematics benchmarks with an average score of 44. There are stronger options in this category.

Is Gemma 3 27B good for reasoning and logic?

Gemma 3 27B ranks #72 out of 88 models in reasoning and logic benchmarks with an average score of 42. There are stronger options in this category.

Is Gemma 3 27B open source?

Yes, Gemma 3 27B is an open weight model created by Google, meaning it can be downloaded and run locally or fine-tuned for specific use cases.

What is the context window size of Gemma 3 27B?

Gemma 3 27B has a context window of 32K tokens, which determines how much text it can process in a single interaction.