DeepSeek-R1 vs DeepSeek V3.2 (Thinking)

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 35 (34 point difference).DeepSeek V3.2 (Thinking) wins 4 out of 4 categories.

Knowledge

DeepSeek V3.2 (Thinking)

DeepSeek-R1

41.8

DeepSeek V3.2 (Thinking)

84

44
MMLU
87
43
GPQA
85
41
SuperGPQA
83
39
OpenBookQA
81

Coding

DeepSeek V3.2 (Thinking)

DeepSeek-R1

36

DeepSeek V3.2 (Thinking)

79

36
HumanEval
79

Mathematics

DeepSeek V3.2 (Thinking)

DeepSeek-R1

43

DeepSeek V3.2 (Thinking)

86

44
AIME 2023
87
46
AIME 2024
89
45
AIME 2025
88
40
HMMT Feb 2023
83
42
HMMT Feb 2024
85
41
HMMT Feb 2025
84
43
BRUMO 2025
86

Reasoning

DeepSeek V3.2 (Thinking)

DeepSeek-R1

41

DeepSeek V3.2 (Thinking)

82

42
SimpleQA
83
40
MuSR
81

Frequently Asked Questions

Which is better, DeepSeek-R1 or DeepSeek V3.2 (Thinking)?

DeepSeek V3.2 (Thinking) scores higher overall with 69 vs 35, a difference of 34 points across all benchmarks.

Which is better for knowledge tasks, DeepSeek-R1 or DeepSeek V3.2 (Thinking)?

DeepSeek V3.2 (Thinking) leads in knowledge tasks with an average score of 84 vs 41.8.

Which is better for coding, DeepSeek-R1 or DeepSeek V3.2 (Thinking)?

DeepSeek V3.2 (Thinking) leads in coding with an average score of 79 vs 36.

Which is better for math, DeepSeek-R1 or DeepSeek V3.2 (Thinking)?

DeepSeek V3.2 (Thinking) leads in math with an average score of 86 vs 43.

Which is better for reasoning, DeepSeek-R1 or DeepSeek V3.2 (Thinking)?

DeepSeek V3.2 (Thinking) leads in reasoning with an average score of 82 vs 41.