benchlm.ai

Qwen2.5-72B 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 65 (5 point difference).Qwen3.5 397B (Reasoning) wins 4 out of 4 categories.

Qwen2.5-72B

CreatorAlibaba
TypeOpen Weight
Context128K
Score65

Qwen3.5 397B (Reasoning)

CreatorAlibaba
TypeOpen Weight
Context128K
Score70

Knowledge

Qwen3.5 397B (Reasoning)

Qwen2.5-72B

80.8

Qwen3.5 397B (Reasoning)

88

83
MMLU
91
82
GPQA
89
80
SuperGPQA
87
78
OpenBookQA
85

Coding

Qwen3.5 397B (Reasoning)

Qwen2.5-72B

75

Qwen3.5 397B (Reasoning)

83

75
HumanEval
83

Mathematics

Qwen3.5 397B (Reasoning)

Qwen2.5-72B

83

Qwen3.5 397B (Reasoning)

92

84
AIME 2023
93
86
AIME 2024
95
85
AIME 2025
94
80
HMMT Feb 2023
89
82
HMMT Feb 2024
91
81
HMMT Feb 2025
90
83
BRUMO 2025
92

Reasoning

Qwen3.5 397B (Reasoning)

Qwen2.5-72B

79

Qwen3.5 397B (Reasoning)

86

80
SimpleQA
87
78
MuSR
85

Frequently Asked Questions

Which is better, Qwen2.5-72B or Qwen3.5 397B (Reasoning)?

Qwen3.5 397B (Reasoning) scores higher overall with 70 vs 65, a difference of 5 points across all benchmarks.

Which is better for knowledge tasks, Qwen2.5-72B or Qwen3.5 397B (Reasoning)?

Qwen3.5 397B (Reasoning) leads in knowledge tasks with an average score of 88 vs 80.8.

Which is better for coding, Qwen2.5-72B or Qwen3.5 397B (Reasoning)?

Qwen3.5 397B (Reasoning) leads in coding with an average score of 83 vs 75.

Which is better for math, Qwen2.5-72B or Qwen3.5 397B (Reasoning)?

Qwen3.5 397B (Reasoning) leads in math with an average score of 92 vs 83.

Which is better for reasoning, Qwen2.5-72B or Qwen3.5 397B (Reasoning)?

Qwen3.5 397B (Reasoning) leads in reasoning with an average score of 86 vs 79.

Related Comparisons

Qwen2.5-72B vs GPT-5.4Qwen2.5-72B vs Gemini 3.1 ProQwen2.5-72B vs Claude Opus 4.6Qwen2.5-72B vs GPT-5.3 CodexQwen2.5-72B vs Grok 4.1Qwen2.5-72B vs GPT-5.2