benchlm.ai

DeepSeek V3.1 vs Kimi K2

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

Quick Verdict

DeepSeek V3.1 wins overall with a score of 24 vs 23 (1 point difference).DeepSeek V3.1 wins 4 out of 4 categories.

DeepSeek V3.1

CreatorDeepSeek
TypeOpen Weight
Context128K
Score24

Kimi K2

CreatorMoonshot AI
TypeProprietary
Context128K
Score23

Knowledge

DeepSeek V3.1

DeepSeek V3.1

30.8

Kimi K2

29.8

33
MMLU
32
32
GPQA
31
30
SuperGPQA
29
28
OpenBookQA
27

Coding

DeepSeek V3.1

DeepSeek V3.1

25

Kimi K2

24

25
HumanEval
24

Mathematics

DeepSeek V3.1

DeepSeek V3.1

32

Kimi K2

31

33
AIME 2023
32
35
AIME 2024
34
34
AIME 2025
33
29
HMMT Feb 2023
28
31
HMMT Feb 2024
30
30
HMMT Feb 2025
29
32
BRUMO 2025
31

Reasoning

DeepSeek V3.1

DeepSeek V3.1

30

Kimi K2

29

31
SimpleQA
30
29
MuSR
28

Frequently Asked Questions

Which is better, DeepSeek V3.1 or Kimi K2?

DeepSeek V3.1 scores higher overall with 24 vs 23, a difference of 1 points across all benchmarks.

Which is better for knowledge tasks, DeepSeek V3.1 or Kimi K2?

DeepSeek V3.1 leads in knowledge tasks with an average score of 30.8 vs 29.8.

Which is better for coding, DeepSeek V3.1 or Kimi K2?

DeepSeek V3.1 leads in coding with an average score of 25 vs 24.

Which is better for math, DeepSeek V3.1 or Kimi K2?

DeepSeek V3.1 leads in math with an average score of 32 vs 31.

Which is better for reasoning, DeepSeek V3.1 or Kimi K2?

DeepSeek V3.1 leads in reasoning with an average score of 30 vs 29.

Related Comparisons

DeepSeek V3.1 vs GPT-5.4DeepSeek V3.1 vs Gemini 3.1 ProDeepSeek V3.1 vs Claude Opus 4.6DeepSeek V3.1 vs GPT-5.3 CodexDeepSeek V3.1 vs Grok 4.1DeepSeek V3.1 vs GPT-5.2