benchlm.ai

Claude 3.5 Sonnet 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 55 (10 point difference).o4-mini (high) wins 4 out of 4 categories.

Claude 3.5 Sonnet

CreatorAnthropic
TypeProprietary
Context200K
Score55

o4-mini (high)

CreatorOpenAI
TypeProprietary
Context200K
Score65

Knowledge

o4-mini (high)

Claude 3.5 Sonnet

63.5

o4-mini (high)

80.5

65
MMLU
82
65
GPQA
82
63
SuperGPQA
80
61
OpenBookQA
78

Coding

o4-mini (high)

Claude 3.5 Sonnet

57

o4-mini (high)

74

57
HumanEval
74

Mathematics

o4-mini (high)

Claude 3.5 Sonnet

64

o4-mini (high)

82

65
AIME 2023
83
67
AIME 2024
85
66
AIME 2025
84
61
HMMT Feb 2023
79
63
HMMT Feb 2024
81
62
HMMT Feb 2025
80
64
BRUMO 2025
82

Reasoning

o4-mini (high)

Claude 3.5 Sonnet

62

o4-mini (high)

79

63
SimpleQA
80
61
MuSR
78

Frequently Asked Questions

Which is better, Claude 3.5 Sonnet or o4-mini (high)?

o4-mini (high) scores higher overall with 65 vs 55, a difference of 10 points across all benchmarks.

Which is better for knowledge tasks, Claude 3.5 Sonnet or o4-mini (high)?

o4-mini (high) leads in knowledge tasks with an average score of 80.5 vs 63.5.

Which is better for coding, Claude 3.5 Sonnet or o4-mini (high)?

o4-mini (high) leads in coding with an average score of 74 vs 57.

Which is better for math, Claude 3.5 Sonnet or o4-mini (high)?

o4-mini (high) leads in math with an average score of 82 vs 64.

Which is better for reasoning, Claude 3.5 Sonnet or o4-mini (high)?

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