benchlm.ai

DeepSeek V3.2 vs o1-preview

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

Quick Verdict

o1-preview wins overall with a score of 71 vs 66 (5 point difference).o1-preview wins 4 out of 4 categories.

DeepSeek V3.2

CreatorDeepSeek
TypeOpen Weight
Context128K
Score66

o1-preview

CreatorOpenAI
TypeProprietary
Context200K
Score71

Knowledge

o1-preview

DeepSeek V3.2

81.8

o1-preview

89

84
MMLU
92
83
GPQA
90
81
SuperGPQA
88
79
OpenBookQA
86

Coding

o1-preview

DeepSeek V3.2

76

o1-preview

86

76
HumanEval
86

Mathematics

o1-preview

DeepSeek V3.2

83

o1-preview

93

84
AIME 2023
94
86
AIME 2024
96
85
AIME 2025
95
80
HMMT Feb 2023
90
82
HMMT Feb 2024
92
81
HMMT Feb 2025
91
83
BRUMO 2025
93

Reasoning

o1-preview

DeepSeek V3.2

80

o1-preview

87

81
SimpleQA
88
79
MuSR
86

Frequently Asked Questions

Which is better, DeepSeek V3.2 or o1-preview?

o1-preview scores higher overall with 71 vs 66, a difference of 5 points across all benchmarks.

Which is better for knowledge tasks, DeepSeek V3.2 or o1-preview?

o1-preview leads in knowledge tasks with an average score of 89 vs 81.8.

Which is better for coding, DeepSeek V3.2 or o1-preview?

o1-preview leads in coding with an average score of 86 vs 76.

Which is better for math, DeepSeek V3.2 or o1-preview?

o1-preview leads in math with an average score of 93 vs 83.

Which is better for reasoning, DeepSeek V3.2 or o1-preview?

o1-preview leads in reasoning with an average score of 87 vs 80.

Related Comparisons

DeepSeek V3.2 vs GPT-5.4DeepSeek V3.2 vs Gemini 3.1 ProDeepSeek V3.2 vs Claude Opus 4.6DeepSeek V3.2 vs GPT-5.3 CodexDeepSeek V3.2 vs Grok 4.1DeepSeek V3.2 vs GPT-5.2