GPT-5 (high) vs Qwen2.5-72B

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

Quick Verdict

GPT-5 (high) wins overall with a score of 72 vs 65 (7 point difference).GPT-5 (high) wins 4 out of 4 categories.

Knowledge

GPT-5 (high)

GPT-5 (high)

90

Qwen2.5-72B

80.8

93
MMLU
83
91
GPQA
82
89
SuperGPQA
80
87
OpenBookQA
78

Coding

GPT-5 (high)

GPT-5 (high)

85

Qwen2.5-72B

75

85
HumanEval
75

Mathematics

GPT-5 (high)

GPT-5 (high)

94

Qwen2.5-72B

83

95
AIME 2023
84
97
AIME 2024
86
96
AIME 2025
85
91
HMMT Feb 2023
80
93
HMMT Feb 2024
82
92
HMMT Feb 2025
81
94
BRUMO 2025
83

Reasoning

GPT-5 (high)

GPT-5 (high)

88

Qwen2.5-72B

79

89
SimpleQA
80
87
MuSR
78

Frequently Asked Questions

Which is better, GPT-5 (high) or Qwen2.5-72B?

GPT-5 (high) scores higher overall with 72 vs 65, a difference of 7 points across all benchmarks.

Which is better for knowledge tasks, GPT-5 (high) or Qwen2.5-72B?

GPT-5 (high) leads in knowledge tasks with an average score of 90 vs 80.8.

Which is better for coding, GPT-5 (high) or Qwen2.5-72B?

GPT-5 (high) leads in coding with an average score of 85 vs 75.

Which is better for math, GPT-5 (high) or Qwen2.5-72B?

GPT-5 (high) leads in math with an average score of 94 vs 83.

Which is better for reasoning, GPT-5 (high) or Qwen2.5-72B?

GPT-5 (high) leads in reasoning with an average score of 88 vs 79.