DeepSeek V3.2 (Thinking) vs Moonshot v1

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 44 (25 point difference).DeepSeek V3.2 (Thinking) wins 4 out of 4 categories.

Knowledge

DeepSeek V3.2 (Thinking)

DeepSeek V3.2 (Thinking)

84

Moonshot v1

50.8

87
MMLU
53
85
GPQA
52
83
SuperGPQA
50
81
OpenBookQA
48

Coding

DeepSeek V3.2 (Thinking)

DeepSeek V3.2 (Thinking)

79

Moonshot v1

45

79
HumanEval
45

Mathematics

DeepSeek V3.2 (Thinking)

DeepSeek V3.2 (Thinking)

86

Moonshot v1

52

87
AIME 2023
53
89
AIME 2024
55
88
AIME 2025
54
83
HMMT Feb 2023
49
85
HMMT Feb 2024
51
84
HMMT Feb 2025
50
86
BRUMO 2025
52

Reasoning

DeepSeek V3.2 (Thinking)

DeepSeek V3.2 (Thinking)

82

Moonshot v1

50

83
SimpleQA
51
81
MuSR
49

Frequently Asked Questions

Which is better, DeepSeek V3.2 (Thinking) or Moonshot v1?

DeepSeek V3.2 (Thinking) scores higher overall with 69 vs 44, a difference of 25 points across all benchmarks.

Which is better for knowledge tasks, DeepSeek V3.2 (Thinking) or Moonshot v1?

DeepSeek V3.2 (Thinking) leads in knowledge tasks with an average score of 84 vs 50.8.

Which is better for coding, DeepSeek V3.2 (Thinking) or Moonshot v1?

DeepSeek V3.2 (Thinking) leads in coding with an average score of 79 vs 45.

Which is better for math, DeepSeek V3.2 (Thinking) or Moonshot v1?

DeepSeek V3.2 (Thinking) leads in math with an average score of 86 vs 52.

Which is better for reasoning, DeepSeek V3.2 (Thinking) or Moonshot v1?

DeepSeek V3.2 (Thinking) leads in reasoning with an average score of 82 vs 50.