benchlm.ai

Qwen2.5-VL-32B 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 34 (31 point difference).Qwen3.5 397B wins 4 out of 4 categories.

Qwen2.5-VL-32B

CreatorAlibaba
TypeOpen Weight
Context32K
Score34

Qwen3.5 397B

CreatorAlibaba
TypeOpen Weight
Context128K
Score65

Knowledge

Qwen3.5 397B

Qwen2.5-VL-32B

40.8

Qwen3.5 397B

80.8

43
MMLU
83
42
GPQA
82
40
SuperGPQA
80
38
OpenBookQA
78

Coding

Qwen3.5 397B

Qwen2.5-VL-32B

35

Qwen3.5 397B

75

35
HumanEval
75

Mathematics

Qwen3.5 397B

Qwen2.5-VL-32B

42

Qwen3.5 397B

82

43
AIME 2023
83
45
AIME 2024
85
44
AIME 2025
84
39
HMMT Feb 2023
79
41
HMMT Feb 2024
81
40
HMMT Feb 2025
80
42
BRUMO 2025
82

Reasoning

Qwen3.5 397B

Qwen2.5-VL-32B

40

Qwen3.5 397B

79

41
SimpleQA
80
39
MuSR
78

Frequently Asked Questions

Which is better, Qwen2.5-VL-32B or Qwen3.5 397B?

Qwen3.5 397B scores higher overall with 65 vs 34, a difference of 31 points across all benchmarks.

Which is better for knowledge tasks, Qwen2.5-VL-32B or Qwen3.5 397B?

Qwen3.5 397B leads in knowledge tasks with an average score of 80.8 vs 40.8.

Which is better for coding, Qwen2.5-VL-32B or Qwen3.5 397B?

Qwen3.5 397B leads in coding with an average score of 75 vs 35.

Which is better for math, Qwen2.5-VL-32B or Qwen3.5 397B?

Qwen3.5 397B leads in math with an average score of 82 vs 42.

Which is better for reasoning, Qwen2.5-VL-32B or Qwen3.5 397B?

Qwen3.5 397B leads in reasoning with an average score of 79 vs 40.

Related Comparisons

Qwen2.5-VL-32B vs GPT-5.4Qwen2.5-VL-32B vs Gemini 3.1 ProQwen2.5-VL-32B vs Claude Opus 4.6Qwen2.5-VL-32B vs GPT-5.3 CodexQwen2.5-VL-32B vs Grok 4.1Qwen2.5-VL-32B vs GPT-5.2