benchlm.ai

Claude 3.5 Sonnet vs GPT-5 (high)

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

Quick Verdict

GPT-5 (high) wins overall with a score of 72 vs 55 (17 point difference).GPT-5 (high) wins 4 out of 4 categories.

Claude 3.5 Sonnet

CreatorAnthropic
TypeProprietary
Context200K
Score55

GPT-5 (high)

CreatorOpenAI
TypeProprietary
Context128K
Score72

Knowledge

GPT-5 (high)

Claude 3.5 Sonnet

63.5

GPT-5 (high)

90

65
MMLU
93
65
GPQA
91
63
SuperGPQA
89
61
OpenBookQA
87

Coding

GPT-5 (high)

Claude 3.5 Sonnet

57

GPT-5 (high)

85

57
HumanEval
85

Mathematics

GPT-5 (high)

Claude 3.5 Sonnet

64

GPT-5 (high)

94

65
AIME 2023
95
67
AIME 2024
97
66
AIME 2025
96
61
HMMT Feb 2023
91
63
HMMT Feb 2024
93
62
HMMT Feb 2025
92
64
BRUMO 2025
94

Reasoning

GPT-5 (high)

Claude 3.5 Sonnet

62

GPT-5 (high)

88

63
SimpleQA
89
61
MuSR
87

Frequently Asked Questions

Which is better, Claude 3.5 Sonnet or GPT-5 (high)?

GPT-5 (high) scores higher overall with 72 vs 55, a difference of 17 points across all benchmarks.

Which is better for knowledge tasks, Claude 3.5 Sonnet or GPT-5 (high)?

GPT-5 (high) leads in knowledge tasks with an average score of 90 vs 63.5.

Which is better for coding, Claude 3.5 Sonnet or GPT-5 (high)?

GPT-5 (high) leads in coding with an average score of 85 vs 57.

Which is better for math, Claude 3.5 Sonnet or GPT-5 (high)?

GPT-5 (high) leads in math with an average score of 94 vs 64.

Which is better for reasoning, Claude 3.5 Sonnet or GPT-5 (high)?

GPT-5 (high) leads in reasoning with an average score of 88 vs 62.

Related Comparisons

Claude 3.5 Sonnet vs GPT-5.4Claude 3.5 Sonnet vs Gemini 3.1 ProClaude 3.5 Sonnet vs Claude Opus 4.6Claude 3.5 Sonnet vs GPT-5.3 CodexClaude 3.5 Sonnet vs Grok 4.1Claude 3.5 Sonnet vs GPT-5.2