benchlm.ai

Claude 4.1 Opus vs GPT-OSS 120B

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

Quick Verdict

Claude 4.1 Opus wins overall with a score of 61 vs 42 (19 point difference).Claude 4.1 Opus wins 4 out of 4 categories.

Claude 4.1 Opus

CreatorAnthropic
TypeProprietary
Context200K
Score61

GPT-OSS 120B

CreatorOpenAI
TypeOpen Weight
Context128K
Score42

Knowledge

Claude 4.1 Opus

Claude 4.1 Opus

74.5

GPT-OSS 120B

48.8

76
MMLU
51
76
GPQA
50
74
SuperGPQA
48
72
OpenBookQA
46

Coding

Claude 4.1 Opus

Claude 4.1 Opus

68

GPT-OSS 120B

43

68
HumanEval
43

Mathematics

Claude 4.1 Opus

Claude 4.1 Opus

75

GPT-OSS 120B

50

76
AIME 2023
51
78
AIME 2024
53
77
AIME 2025
52
72
HMMT Feb 2023
47
74
HMMT Feb 2024
49
73
HMMT Feb 2025
48
75
BRUMO 2025
50

Reasoning

Claude 4.1 Opus

Claude 4.1 Opus

73

GPT-OSS 120B

48

74
SimpleQA
49
72
MuSR
47

Frequently Asked Questions

Which is better, Claude 4.1 Opus or GPT-OSS 120B?

Claude 4.1 Opus scores higher overall with 61 vs 42, a difference of 19 points across all benchmarks.

Which is better for knowledge tasks, Claude 4.1 Opus or GPT-OSS 120B?

Claude 4.1 Opus leads in knowledge tasks with an average score of 74.5 vs 48.8.

Which is better for coding, Claude 4.1 Opus or GPT-OSS 120B?

Claude 4.1 Opus leads in coding with an average score of 68 vs 43.

Which is better for math, Claude 4.1 Opus or GPT-OSS 120B?

Claude 4.1 Opus leads in math with an average score of 75 vs 50.

Which is better for reasoning, Claude 4.1 Opus or GPT-OSS 120B?

Claude 4.1 Opus leads in reasoning with an average score of 73 vs 48.

Related Comparisons

Claude 4.1 Opus vs GPT-5.4Claude 4.1 Opus vs Gemini 3.1 ProClaude 4.1 Opus vs Claude Opus 4.6Claude 4.1 Opus vs GPT-5.3 CodexClaude 4.1 Opus vs Grok 4.1Claude 4.1 Opus vs GPT-5.2