DeepSeek V3.2 (Thinking) vs Gemma 3 27B

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

Quick Verdict

DeepSeek V3.2 (Thinking) wins overall with a score of 69 vs 36 (33 point difference).DeepSeek V3.2 (Thinking) wins 4 out of 4 categories.

Knowledge

DeepSeek V3.2 (Thinking)

DeepSeek V3.2 (Thinking)

84

Gemma 3 27B

42.8

87
MMLU
45
85
GPQA
44
83
SuperGPQA
42
81
OpenBookQA
40

Coding

DeepSeek V3.2 (Thinking)

DeepSeek V3.2 (Thinking)

79

Gemma 3 27B

37

79
HumanEval
37

Mathematics

DeepSeek V3.2 (Thinking)

DeepSeek V3.2 (Thinking)

86

Gemma 3 27B

44

87
AIME 2023
45
89
AIME 2024
47
88
AIME 2025
46
83
HMMT Feb 2023
41
85
HMMT Feb 2024
43
84
HMMT Feb 2025
42
86
BRUMO 2025
44

Reasoning

DeepSeek V3.2 (Thinking)

DeepSeek V3.2 (Thinking)

82

Gemma 3 27B

42

83
SimpleQA
43
81
MuSR
41

Frequently Asked Questions

Which is better, DeepSeek V3.2 (Thinking) or Gemma 3 27B?

DeepSeek V3.2 (Thinking) scores higher overall with 69 vs 36, a difference of 33 points across all benchmarks.

Which is better for knowledge tasks, DeepSeek V3.2 (Thinking) or Gemma 3 27B?

DeepSeek V3.2 (Thinking) leads in knowledge tasks with an average score of 84 vs 42.8.

Which is better for coding, DeepSeek V3.2 (Thinking) or Gemma 3 27B?

DeepSeek V3.2 (Thinking) leads in coding with an average score of 79 vs 37.

Which is better for math, DeepSeek V3.2 (Thinking) or Gemma 3 27B?

DeepSeek V3.2 (Thinking) leads in math with an average score of 86 vs 44.

Which is better for reasoning, DeepSeek V3.2 (Thinking) or Gemma 3 27B?

DeepSeek V3.2 (Thinking) leads in reasoning with an average score of 82 vs 42.