benchlm.ai

Claude Sonnet 4.5 vs GPT-OSS 20B

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

Quick Verdict

Claude Sonnet 4.5 wins overall with a score of 74 vs 22 (52 point difference).Claude Sonnet 4.5 wins 4 out of 4 categories.

Claude Sonnet 4.5

CreatorAnthropic
TypeProprietary
Context1M
Score74

GPT-OSS 20B

CreatorOpenAI
TypeOpen Weight
Context128K
Score22

Knowledge

Claude Sonnet 4.5

Claude Sonnet 4.5

92

GPT-OSS 20B

28.8

95
MMLU
31
93
GPQA
30
91
SuperGPQA
28
89
OpenBookQA
26

Coding

Claude Sonnet 4.5

Claude Sonnet 4.5

87

GPT-OSS 20B

23

87
HumanEval
23

Mathematics

Claude Sonnet 4.5

Claude Sonnet 4.5

96

GPT-OSS 20B

30

97
AIME 2023
31
99
AIME 2024
33
98
AIME 2025
32
93
HMMT Feb 2023
27
95
HMMT Feb 2024
29
94
HMMT Feb 2025
28
96
BRUMO 2025
30

Reasoning

Claude Sonnet 4.5

Claude Sonnet 4.5

90

GPT-OSS 20B

28

91
SimpleQA
29
89
MuSR
27

Frequently Asked Questions

Which is better, Claude Sonnet 4.5 or GPT-OSS 20B?

Claude Sonnet 4.5 scores higher overall with 74 vs 22, a difference of 52 points across all benchmarks.

Which is better for knowledge tasks, Claude Sonnet 4.5 or GPT-OSS 20B?

Claude Sonnet 4.5 leads in knowledge tasks with an average score of 92 vs 28.8.

Which is better for coding, Claude Sonnet 4.5 or GPT-OSS 20B?

Claude Sonnet 4.5 leads in coding with an average score of 87 vs 23.

Which is better for math, Claude Sonnet 4.5 or GPT-OSS 20B?

Claude Sonnet 4.5 leads in math with an average score of 96 vs 30.

Which is better for reasoning, Claude Sonnet 4.5 or GPT-OSS 20B?

Claude Sonnet 4.5 leads in reasoning with an average score of 90 vs 28.

Related Comparisons

Claude Sonnet 4.5 vs GPT-5.4Claude Sonnet 4.5 vs Gemini 3.1 ProClaude Sonnet 4.5 vs Claude Opus 4.6Claude Sonnet 4.5 vs GPT-5.3 CodexClaude Sonnet 4.5 vs Grok 4.1Claude Sonnet 4.5 vs GPT-5.2