GPT-5 (medium) vs GPT-OSS 120B

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

Quick Verdict

GPT-5 (medium) wins overall with a score of 70 vs 42 (28 point difference).GPT-5 (medium) wins 4 out of 4 categories.

Knowledge

GPT-5 (medium)

GPT-5 (medium)

88

GPT-OSS 120B

48.8

91
MMLU
51
89
GPQA
50
87
SuperGPQA
48
85
OpenBookQA
46

Coding

GPT-5 (medium)

GPT-5 (medium)

83

GPT-OSS 120B

43

83
HumanEval
43

Mathematics

GPT-5 (medium)

GPT-5 (medium)

92

GPT-OSS 120B

50

93
AIME 2023
51
95
AIME 2024
53
94
AIME 2025
52
89
HMMT Feb 2023
47
91
HMMT Feb 2024
49
90
HMMT Feb 2025
48
92
BRUMO 2025
50

Reasoning

GPT-5 (medium)

GPT-5 (medium)

86

GPT-OSS 120B

48

87
SimpleQA
49
85
MuSR
47

Frequently Asked Questions

Which is better, GPT-5 (medium) or GPT-OSS 120B?

GPT-5 (medium) scores higher overall with 70 vs 42, a difference of 28 points across all benchmarks.

Which is better for knowledge tasks, GPT-5 (medium) or GPT-OSS 120B?

GPT-5 (medium) leads in knowledge tasks with an average score of 88 vs 48.8.

Which is better for coding, GPT-5 (medium) or GPT-OSS 120B?

GPT-5 (medium) leads in coding with an average score of 83 vs 43.

Which is better for math, GPT-5 (medium) or GPT-OSS 120B?

GPT-5 (medium) leads in math with an average score of 92 vs 50.

Which is better for reasoning, GPT-5 (medium) or GPT-OSS 120B?

GPT-5 (medium) leads in reasoning with an average score of 86 vs 48.