benchlm.ai

Gemma 3 27B vs Kimi K2.5 (Reasoning)

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

Quick Verdict

Kimi K2.5 (Reasoning) wins overall with a score of 71 vs 36 (35 point difference).Kimi K2.5 (Reasoning) wins 4 out of 4 categories.

Gemma 3 27B

CreatorGoogle
TypeOpen Weight
Context32K
Score36

Kimi K2.5 (Reasoning)

CreatorMoonshot AI
TypeOpen Weight
Context128K
Score71

Knowledge

Kimi K2.5 (Reasoning)

Gemma 3 27B

42.8

Kimi K2.5 (Reasoning)

89

45
MMLU
92
44
GPQA
90
42
SuperGPQA
88
40
OpenBookQA
86

Coding

Kimi K2.5 (Reasoning)

Gemma 3 27B

37

Kimi K2.5 (Reasoning)

84

37
HumanEval
84

Mathematics

Kimi K2.5 (Reasoning)

Gemma 3 27B

44

Kimi K2.5 (Reasoning)

93

45
AIME 2023
94
47
AIME 2024
96
46
AIME 2025
95
41
HMMT Feb 2023
90
43
HMMT Feb 2024
92
42
HMMT Feb 2025
91
44
BRUMO 2025
93

Reasoning

Kimi K2.5 (Reasoning)

Gemma 3 27B

42

Kimi K2.5 (Reasoning)

87

43
SimpleQA
88
41
MuSR
86

Frequently Asked Questions

Which is better, Gemma 3 27B or Kimi K2.5 (Reasoning)?

Kimi K2.5 (Reasoning) scores higher overall with 71 vs 36, a difference of 35 points across all benchmarks.

Which is better for knowledge tasks, Gemma 3 27B or Kimi K2.5 (Reasoning)?

Kimi K2.5 (Reasoning) leads in knowledge tasks with an average score of 89 vs 42.8.

Which is better for coding, Gemma 3 27B or Kimi K2.5 (Reasoning)?

Kimi K2.5 (Reasoning) leads in coding with an average score of 84 vs 37.

Which is better for math, Gemma 3 27B or Kimi K2.5 (Reasoning)?

Kimi K2.5 (Reasoning) leads in math with an average score of 93 vs 44.

Which is better for reasoning, Gemma 3 27B or Kimi K2.5 (Reasoning)?

Kimi K2.5 (Reasoning) leads in reasoning with an average score of 87 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