DeepSeek V3.1 (Reasoning) vs Qwen2.5-72B

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

Quick Verdict

Qwen2.5-72B wins overall with a score of 65 vs 25 (40 point difference).Qwen2.5-72B wins 4 out of 4 categories.

Knowledge

Qwen2.5-72B

DeepSeek V3.1 (Reasoning)

31.8

Qwen2.5-72B

80.8

34
MMLU
83
33
GPQA
82
31
SuperGPQA
80
29
OpenBookQA
78

Coding

Qwen2.5-72B

DeepSeek V3.1 (Reasoning)

26

Qwen2.5-72B

75

26
HumanEval
75

Mathematics

Qwen2.5-72B

DeepSeek V3.1 (Reasoning)

33

Qwen2.5-72B

83

34
AIME 2023
84
36
AIME 2024
86
35
AIME 2025
85
30
HMMT Feb 2023
80
32
HMMT Feb 2024
82
31
HMMT Feb 2025
81
33
BRUMO 2025
83

Reasoning

Qwen2.5-72B

DeepSeek V3.1 (Reasoning)

31

Qwen2.5-72B

79

32
SimpleQA
80
30
MuSR
78

Frequently Asked Questions

Which is better, DeepSeek V3.1 (Reasoning) or Qwen2.5-72B?

Qwen2.5-72B scores higher overall with 65 vs 25, a difference of 40 points across all benchmarks.

Which is better for knowledge tasks, DeepSeek V3.1 (Reasoning) or Qwen2.5-72B?

Qwen2.5-72B leads in knowledge tasks with an average score of 80.8 vs 31.8.

Which is better for coding, DeepSeek V3.1 (Reasoning) or Qwen2.5-72B?

Qwen2.5-72B leads in coding with an average score of 75 vs 26.

Which is better for math, DeepSeek V3.1 (Reasoning) or Qwen2.5-72B?

Qwen2.5-72B leads in math with an average score of 83 vs 33.

Which is better for reasoning, DeepSeek V3.1 (Reasoning) or Qwen2.5-72B?

Qwen2.5-72B leads in reasoning with an average score of 79 vs 31.