DeepSeek V3.2 (Thinking) vs Mistral Large 3

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

Quick Verdict

DeepSeek V3.2 (Thinking) wins overall with a score of 69 vs 61 (8 point difference).DeepSeek V3.2 (Thinking) wins 4 out of 4 categories.

Knowledge

DeepSeek V3.2 (Thinking)

DeepSeek V3.2 (Thinking)

84

Mistral Large 3

73.8

87
MMLU
76
85
GPQA
75
83
SuperGPQA
73
81
OpenBookQA
71

Coding

DeepSeek V3.2 (Thinking)

DeepSeek V3.2 (Thinking)

79

Mistral Large 3

68

79
HumanEval
68

Mathematics

DeepSeek V3.2 (Thinking)

DeepSeek V3.2 (Thinking)

86

Mistral Large 3

75

87
AIME 2023
76
89
AIME 2024
78
88
AIME 2025
77
83
HMMT Feb 2023
72
85
HMMT Feb 2024
74
84
HMMT Feb 2025
73
86
BRUMO 2025
75

Reasoning

DeepSeek V3.2 (Thinking)

DeepSeek V3.2 (Thinking)

82

Mistral Large 3

72

83
SimpleQA
73
81
MuSR
71

Frequently Asked Questions

Which is better, DeepSeek V3.2 (Thinking) or Mistral Large 3?

DeepSeek V3.2 (Thinking) scores higher overall with 69 vs 61, a difference of 8 points across all benchmarks.

Which is better for knowledge tasks, DeepSeek V3.2 (Thinking) or Mistral Large 3?

DeepSeek V3.2 (Thinking) leads in knowledge tasks with an average score of 84 vs 73.8.

Which is better for coding, DeepSeek V3.2 (Thinking) or Mistral Large 3?

DeepSeek V3.2 (Thinking) leads in coding with an average score of 79 vs 68.

Which is better for math, DeepSeek V3.2 (Thinking) or Mistral Large 3?

DeepSeek V3.2 (Thinking) leads in math with an average score of 86 vs 75.

Which is better for reasoning, DeepSeek V3.2 (Thinking) or Mistral Large 3?

DeepSeek V3.2 (Thinking) leads in reasoning with an average score of 82 vs 72.