DeepSeek V3.2 vs GPT-5 mini

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

Quick Verdict

GPT-5 mini wins overall with a score of 68 vs 66 (2 point difference).GPT-5 mini wins 4 out of 4 categories.

Knowledge

GPT-5 mini

DeepSeek V3.2

81.8

GPT-5 mini

85

84
MMLU
88
83
GPQA
86
81
SuperGPQA
84
79
OpenBookQA
82

Coding

GPT-5 mini

DeepSeek V3.2

76

GPT-5 mini

80

76
HumanEval
80

Mathematics

GPT-5 mini

DeepSeek V3.2

83

GPT-5 mini

89

84
AIME 2023
90
86
AIME 2024
92
85
AIME 2025
91
80
HMMT Feb 2023
86
82
HMMT Feb 2024
88
81
HMMT Feb 2025
87
83
BRUMO 2025
89

Reasoning

GPT-5 mini

DeepSeek V3.2

80

GPT-5 mini

83

81
SimpleQA
84
79
MuSR
82

Frequently Asked Questions

Which is better, DeepSeek V3.2 or GPT-5 mini?

GPT-5 mini scores higher overall with 68 vs 66, a difference of 2 points across all benchmarks.

Which is better for knowledge tasks, DeepSeek V3.2 or GPT-5 mini?

GPT-5 mini leads in knowledge tasks with an average score of 85 vs 81.8.

Which is better for coding, DeepSeek V3.2 or GPT-5 mini?

GPT-5 mini leads in coding with an average score of 80 vs 76.

Which is better for math, DeepSeek V3.2 or GPT-5 mini?

GPT-5 mini leads in math with an average score of 89 vs 83.

Which is better for reasoning, DeepSeek V3.2 or GPT-5 mini?

GPT-5 mini leads in reasoning with an average score of 83 vs 80.