benchlm.ai

Gemma 3 27B vs GPT-5 (medium)

Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.

Quick Verdict

GPT-5 (medium) wins overall with a score of 70 vs 36 (34 point difference).GPT-5 (medium) wins 4 out of 4 categories.

Gemma 3 27B

CreatorGoogle
TypeOpen Weight
Context32K
Score36

GPT-5 (medium)

CreatorOpenAI
TypeProprietary
Context128K
Score70

Knowledge

GPT-5 (medium)

Gemma 3 27B

42.8

GPT-5 (medium)

88

45
MMLU
91
44
GPQA
89
42
SuperGPQA
87
40
OpenBookQA
85

Coding

GPT-5 (medium)

Gemma 3 27B

37

GPT-5 (medium)

83

37
HumanEval
83

Mathematics

GPT-5 (medium)

Gemma 3 27B

44

GPT-5 (medium)

92

45
AIME 2023
93
47
AIME 2024
95
46
AIME 2025
94
41
HMMT Feb 2023
89
43
HMMT Feb 2024
91
42
HMMT Feb 2025
90
44
BRUMO 2025
92

Reasoning

GPT-5 (medium)

Gemma 3 27B

42

GPT-5 (medium)

86

43
SimpleQA
87
41
MuSR
85

Frequently Asked Questions

Which is better, Gemma 3 27B or GPT-5 (medium)?

GPT-5 (medium) scores higher overall with 70 vs 36, a difference of 34 points across all benchmarks.

Which is better for knowledge tasks, Gemma 3 27B or GPT-5 (medium)?

GPT-5 (medium) leads in knowledge tasks with an average score of 88 vs 42.8.

Which is better for coding, Gemma 3 27B or GPT-5 (medium)?

GPT-5 (medium) leads in coding with an average score of 83 vs 37.

Which is better for math, Gemma 3 27B or GPT-5 (medium)?

GPT-5 (medium) leads in math with an average score of 92 vs 44.

Which is better for reasoning, Gemma 3 27B or GPT-5 (medium)?

GPT-5 (medium) leads in reasoning with an average score of 86 vs 42.

Related Comparisons

Gemma 3 27B vs GPT-5.4Gemma 3 27B vs Gemini 3.1 ProGemma 3 27B vs Claude Opus 4.6Gemma 3 27B vs GPT-5.3 CodexGemma 3 27B vs Grok 4.1Gemma 3 27B vs GPT-5.2