GPT-5 mini vs Qwen2.5-VL-32B

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

Quick Verdict

GPT-5 mini wins overall with a score of 68 vs 34 (34 point difference).GPT-5 mini wins 4 out of 4 categories.

Knowledge

GPT-5 mini

GPT-5 mini

85

Qwen2.5-VL-32B

40.8

88
MMLU
43
86
GPQA
42
84
SuperGPQA
40
82
OpenBookQA
38

Coding

GPT-5 mini

GPT-5 mini

80

Qwen2.5-VL-32B

35

80
HumanEval
35

Mathematics

GPT-5 mini

GPT-5 mini

89

Qwen2.5-VL-32B

42

90
AIME 2023
43
92
AIME 2024
45
91
AIME 2025
44
86
HMMT Feb 2023
39
88
HMMT Feb 2024
41
87
HMMT Feb 2025
40
89
BRUMO 2025
42

Reasoning

GPT-5 mini

GPT-5 mini

83

Qwen2.5-VL-32B

40

84
SimpleQA
41
82
MuSR
39

Frequently Asked Questions

Which is better, GPT-5 mini or Qwen2.5-VL-32B?

GPT-5 mini scores higher overall with 68 vs 34, a difference of 34 points across all benchmarks.

Which is better for knowledge tasks, GPT-5 mini or Qwen2.5-VL-32B?

GPT-5 mini leads in knowledge tasks with an average score of 85 vs 40.8.

Which is better for coding, GPT-5 mini or Qwen2.5-VL-32B?

GPT-5 mini leads in coding with an average score of 80 vs 35.

Which is better for math, GPT-5 mini or Qwen2.5-VL-32B?

GPT-5 mini leads in math with an average score of 89 vs 42.

Which is better for reasoning, GPT-5 mini or Qwen2.5-VL-32B?

GPT-5 mini leads in reasoning with an average score of 83 vs 40.