GPT-OSS 120B vs Qwen2.5-VL-32B

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

Quick Verdict

GPT-OSS 120B wins overall with a score of 42 vs 34 (8 point difference).GPT-OSS 120B wins 4 out of 4 categories.

Knowledge

GPT-OSS 120B

GPT-OSS 120B

48.8

Qwen2.5-VL-32B

40.8

51
MMLU
43
50
GPQA
42
48
SuperGPQA
40
46
OpenBookQA
38

Coding

GPT-OSS 120B

GPT-OSS 120B

43

Qwen2.5-VL-32B

35

43
HumanEval
35

Mathematics

GPT-OSS 120B

GPT-OSS 120B

50

Qwen2.5-VL-32B

42

51
AIME 2023
43
53
AIME 2024
45
52
AIME 2025
44
47
HMMT Feb 2023
39
49
HMMT Feb 2024
41
48
HMMT Feb 2025
40
50
BRUMO 2025
42

Reasoning

GPT-OSS 120B

GPT-OSS 120B

48

Qwen2.5-VL-32B

40

49
SimpleQA
41
47
MuSR
39

Frequently Asked Questions

Which is better, GPT-OSS 120B or Qwen2.5-VL-32B?

GPT-OSS 120B scores higher overall with 42 vs 34, a difference of 8 points across all benchmarks.

Which is better for knowledge tasks, GPT-OSS 120B or Qwen2.5-VL-32B?

GPT-OSS 120B leads in knowledge tasks with an average score of 48.8 vs 40.8.

Which is better for coding, GPT-OSS 120B or Qwen2.5-VL-32B?

GPT-OSS 120B leads in coding with an average score of 43 vs 35.

Which is better for math, GPT-OSS 120B or Qwen2.5-VL-32B?

GPT-OSS 120B leads in math with an average score of 50 vs 42.

Which is better for reasoning, GPT-OSS 120B or Qwen2.5-VL-32B?

GPT-OSS 120B leads in reasoning with an average score of 48 vs 40.