DeepSeekMath V2 vs Qwen3.5 397B

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

Quick Verdict

Qwen3.5 397B wins overall with a score of 65 vs 64 (1 point difference).Qwen3.5 397B wins 4 out of 4 categories.

Knowledge

Qwen3.5 397B

DeepSeekMath V2

77.8

Qwen3.5 397B

80.8

80
MMLU
83
79
GPQA
82
77
SuperGPQA
80
75
OpenBookQA
78

Coding

Qwen3.5 397B

DeepSeekMath V2

72

Qwen3.5 397B

75

72
HumanEval
75

Mathematics

Qwen3.5 397B

DeepSeekMath V2

79

Qwen3.5 397B

82

80
AIME 2023
83
82
AIME 2024
85
81
AIME 2025
84
76
HMMT Feb 2023
79
78
HMMT Feb 2024
81
77
HMMT Feb 2025
80
79
BRUMO 2025
82

Reasoning

Qwen3.5 397B

DeepSeekMath V2

76

Qwen3.5 397B

79

77
SimpleQA
80
75
MuSR
78

Frequently Asked Questions

Which is better, DeepSeekMath V2 or Qwen3.5 397B?

Qwen3.5 397B scores higher overall with 65 vs 64, a difference of 1 points across all benchmarks.

Which is better for knowledge tasks, DeepSeekMath V2 or Qwen3.5 397B?

Qwen3.5 397B leads in knowledge tasks with an average score of 80.8 vs 77.8.

Which is better for coding, DeepSeekMath V2 or Qwen3.5 397B?

Qwen3.5 397B leads in coding with an average score of 75 vs 72.

Which is better for math, DeepSeekMath V2 or Qwen3.5 397B?

Qwen3.5 397B leads in math with an average score of 82 vs 79.

Which is better for reasoning, DeepSeekMath V2 or Qwen3.5 397B?

Qwen3.5 397B leads in reasoning with an average score of 79 vs 76.