benchlm.ai

GPT-OSS 120B vs o4-mini (high)

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

Quick Verdict

o4-mini (high) wins overall with a score of 65 vs 42 (23 point difference).o4-mini (high) wins 4 out of 4 categories.

GPT-OSS 120B

CreatorOpenAI
TypeOpen Weight
Context128K
Score42

o4-mini (high)

CreatorOpenAI
TypeProprietary
Context200K
Score65

Knowledge

o4-mini (high)

GPT-OSS 120B

48.8

o4-mini (high)

80.5

51
MMLU
82
50
GPQA
82
48
SuperGPQA
80
46
OpenBookQA
78

Coding

o4-mini (high)

GPT-OSS 120B

43

o4-mini (high)

74

43
HumanEval
74

Mathematics

o4-mini (high)

GPT-OSS 120B

50

o4-mini (high)

82

51
AIME 2023
83
53
AIME 2024
85
52
AIME 2025
84
47
HMMT Feb 2023
79
49
HMMT Feb 2024
81
48
HMMT Feb 2025
80
50
BRUMO 2025
82

Reasoning

o4-mini (high)

GPT-OSS 120B

48

o4-mini (high)

79

49
SimpleQA
80
47
MuSR
78

Frequently Asked Questions

Which is better, GPT-OSS 120B or o4-mini (high)?

o4-mini (high) scores higher overall with 65 vs 42, a difference of 23 points across all benchmarks.

Which is better for knowledge tasks, GPT-OSS 120B or o4-mini (high)?

o4-mini (high) leads in knowledge tasks with an average score of 80.5 vs 48.8.

Which is better for coding, GPT-OSS 120B or o4-mini (high)?

o4-mini (high) leads in coding with an average score of 74 vs 43.

Which is better for math, GPT-OSS 120B or o4-mini (high)?

o4-mini (high) leads in math with an average score of 82 vs 50.

Which is better for reasoning, GPT-OSS 120B or o4-mini (high)?

o4-mini (high) leads in reasoning with an average score of 79 vs 48.

Related Comparisons

GPT-OSS 120B vs GPT-5.4GPT-OSS 120B vs Gemini 3.1 ProGPT-OSS 120B vs Claude Opus 4.6GPT-OSS 120B vs GPT-5.3 CodexGPT-OSS 120B vs Grok 4.1GPT-OSS 120B vs GPT-5.2