DeepSeek V3.2 (Thinking) vs Qwen3.5 397B (Reasoning)

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

Quick Verdict

Qwen3.5 397B (Reasoning) wins overall with a score of 70 vs 69 (1 point difference).Qwen3.5 397B (Reasoning) wins 4 out of 4 categories.

Knowledge

Qwen3.5 397B (Reasoning)

DeepSeek V3.2 (Thinking)

84

Qwen3.5 397B (Reasoning)

88

87
MMLU
91
85
GPQA
89
83
SuperGPQA
87
81
OpenBookQA
85

Coding

Qwen3.5 397B (Reasoning)

DeepSeek V3.2 (Thinking)

79

Qwen3.5 397B (Reasoning)

83

79
HumanEval
83

Mathematics

Qwen3.5 397B (Reasoning)

DeepSeek V3.2 (Thinking)

86

Qwen3.5 397B (Reasoning)

92

87
AIME 2023
93
89
AIME 2024
95
88
AIME 2025
94
83
HMMT Feb 2023
89
85
HMMT Feb 2024
91
84
HMMT Feb 2025
90
86
BRUMO 2025
92

Reasoning

Qwen3.5 397B (Reasoning)

DeepSeek V3.2 (Thinking)

82

Qwen3.5 397B (Reasoning)

86

83
SimpleQA
87
81
MuSR
85

Frequently Asked Questions

Which is better, DeepSeek V3.2 (Thinking) or Qwen3.5 397B (Reasoning)?

Qwen3.5 397B (Reasoning) scores higher overall with 70 vs 69, a difference of 1 points across all benchmarks.

Which is better for knowledge tasks, DeepSeek V3.2 (Thinking) or Qwen3.5 397B (Reasoning)?

Qwen3.5 397B (Reasoning) leads in knowledge tasks with an average score of 88 vs 84.

Which is better for coding, DeepSeek V3.2 (Thinking) or Qwen3.5 397B (Reasoning)?

Qwen3.5 397B (Reasoning) leads in coding with an average score of 83 vs 79.

Which is better for math, DeepSeek V3.2 (Thinking) or Qwen3.5 397B (Reasoning)?

Qwen3.5 397B (Reasoning) leads in math with an average score of 92 vs 86.

Which is better for reasoning, DeepSeek V3.2 (Thinking) or Qwen3.5 397B (Reasoning)?

Qwen3.5 397B (Reasoning) leads in reasoning with an average score of 86 vs 82.