GPT-5 mini vs Mistral Large 3

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

Quick Verdict

GPT-5 mini wins overall with a score of 68 vs 61 (7 point difference).GPT-5 mini wins 4 out of 4 categories.

Knowledge

GPT-5 mini

GPT-5 mini

85

Mistral Large 3

73.8

88
MMLU
76
86
GPQA
75
84
SuperGPQA
73
82
OpenBookQA
71

Coding

GPT-5 mini

GPT-5 mini

80

Mistral Large 3

68

80
HumanEval
68

Mathematics

GPT-5 mini

GPT-5 mini

89

Mistral Large 3

75

90
AIME 2023
76
92
AIME 2024
78
91
AIME 2025
77
86
HMMT Feb 2023
72
88
HMMT Feb 2024
74
87
HMMT Feb 2025
73
89
BRUMO 2025
75

Reasoning

GPT-5 mini

GPT-5 mini

83

Mistral Large 3

72

84
SimpleQA
73
82
MuSR
71

Frequently Asked Questions

Which is better, GPT-5 mini or Mistral Large 3?

GPT-5 mini scores higher overall with 68 vs 61, a difference of 7 points across all benchmarks.

Which is better for knowledge tasks, GPT-5 mini or Mistral Large 3?

GPT-5 mini leads in knowledge tasks with an average score of 85 vs 73.8.

Which is better for coding, GPT-5 mini or Mistral Large 3?

GPT-5 mini leads in coding with an average score of 80 vs 68.

Which is better for math, GPT-5 mini or Mistral Large 3?

GPT-5 mini leads in math with an average score of 89 vs 75.

Which is better for reasoning, GPT-5 mini or Mistral Large 3?

GPT-5 mini leads in reasoning with an average score of 83 vs 72.