DeepSeek Coder 2.0 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 64 (4 point difference).GPT-5 mini wins 3 out of 4 categories.

Knowledge

GPT-5 mini

DeepSeek Coder 2.0

77.8

GPT-5 mini

85

80
MMLU
88
79
GPQA
86
77
SuperGPQA
84
75
OpenBookQA
82

Coding

DeepSeek Coder 2.0

DeepSeek Coder 2.0

82

GPT-5 mini

80

82
HumanEval
80

Mathematics

GPT-5 mini

DeepSeek Coder 2.0

80

GPT-5 mini

89

81
AIME 2023
90
83
AIME 2024
92
82
AIME 2025
91
77
HMMT Feb 2023
86
79
HMMT Feb 2024
88
78
HMMT Feb 2025
87
80
BRUMO 2025
89

Reasoning

GPT-5 mini

DeepSeek Coder 2.0

77

GPT-5 mini

83

78
SimpleQA
84
76
MuSR
82

Frequently Asked Questions

Which is better, DeepSeek Coder 2.0 or GPT-5 mini?

GPT-5 mini scores higher overall with 68 vs 64, a difference of 4 points across all benchmarks.

Which is better for knowledge tasks, DeepSeek Coder 2.0 or GPT-5 mini?

GPT-5 mini leads in knowledge tasks with an average score of 85 vs 77.8.

Which is better for coding, DeepSeek Coder 2.0 or GPT-5 mini?

DeepSeek Coder 2.0 leads in coding with an average score of 82 vs 80.

Which is better for math, DeepSeek Coder 2.0 or GPT-5 mini?

GPT-5 mini leads in math with an average score of 89 vs 80.

Which is better for reasoning, DeepSeek Coder 2.0 or GPT-5 mini?

GPT-5 mini leads in reasoning with an average score of 83 vs 77.