GPT-OSS 120B vs Qwen2.5-1M

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

Quick Verdict

Qwen2.5-1M wins overall with a score of 66 vs 42 (24 point difference).Qwen2.5-1M wins 4 out of 4 categories.

Knowledge

Qwen2.5-1M

GPT-OSS 120B

48.8

Qwen2.5-1M

81.8

51
MMLU
84
50
GPQA
83
48
SuperGPQA
81
46
OpenBookQA
79

Coding

Qwen2.5-1M

GPT-OSS 120B

43

Qwen2.5-1M

76

43
HumanEval
76

Mathematics

Qwen2.5-1M

GPT-OSS 120B

50

Qwen2.5-1M

84

51
AIME 2023
85
53
AIME 2024
87
52
AIME 2025
86
47
HMMT Feb 2023
81
49
HMMT Feb 2024
83
48
HMMT Feb 2025
82
50
BRUMO 2025
84

Reasoning

Qwen2.5-1M

GPT-OSS 120B

48

Qwen2.5-1M

80

49
SimpleQA
81
47
MuSR
79

Frequently Asked Questions

Which is better, GPT-OSS 120B or Qwen2.5-1M?

Qwen2.5-1M scores higher overall with 66 vs 42, a difference of 24 points across all benchmarks.

Which is better for knowledge tasks, GPT-OSS 120B or Qwen2.5-1M?

Qwen2.5-1M leads in knowledge tasks with an average score of 81.8 vs 48.8.

Which is better for coding, GPT-OSS 120B or Qwen2.5-1M?

Qwen2.5-1M leads in coding with an average score of 76 vs 43.

Which is better for math, GPT-OSS 120B or Qwen2.5-1M?

Qwen2.5-1M leads in math with an average score of 84 vs 50.

Which is better for reasoning, GPT-OSS 120B or Qwen2.5-1M?

Qwen2.5-1M leads in reasoning with an average score of 80 vs 48.