benchlm.ai

Claude 3 Haiku 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 46 (19 point difference).o4-mini (high) wins 4 out of 4 categories.

Claude 3 Haiku

CreatorAnthropic
TypeProprietary
Context200K
Score46

o4-mini (high)

CreatorOpenAI
TypeProprietary
Context200K
Score65

Knowledge

o4-mini (high)

Claude 3 Haiku

54.5

o4-mini (high)

80.5

56
MMLU
82
56
GPQA
82
54
SuperGPQA
80
52
OpenBookQA
78

Coding

o4-mini (high)

Claude 3 Haiku

48

o4-mini (high)

74

48
HumanEval
74

Mathematics

o4-mini (high)

Claude 3 Haiku

55

o4-mini (high)

82

56
AIME 2023
83
58
AIME 2024
85
57
AIME 2025
84
52
HMMT Feb 2023
79
54
HMMT Feb 2024
81
53
HMMT Feb 2025
80
55
BRUMO 2025
82

Reasoning

o4-mini (high)

Claude 3 Haiku

53

o4-mini (high)

79

54
SimpleQA
80
52
MuSR
78

Frequently Asked Questions

Which is better, Claude 3 Haiku or o4-mini (high)?

o4-mini (high) scores higher overall with 65 vs 46, a difference of 19 points across all benchmarks.

Which is better for knowledge tasks, Claude 3 Haiku or o4-mini (high)?

o4-mini (high) leads in knowledge tasks with an average score of 80.5 vs 54.5.

Which is better for coding, Claude 3 Haiku or o4-mini (high)?

o4-mini (high) leads in coding with an average score of 74 vs 48.

Which is better for math, Claude 3 Haiku or o4-mini (high)?

o4-mini (high) leads in math with an average score of 82 vs 55.

Which is better for reasoning, Claude 3 Haiku or o4-mini (high)?

o4-mini (high) leads in reasoning with an average score of 79 vs 53.

Related Comparisons

Claude 3 Haiku vs GPT-5.4Claude 3 Haiku vs Gemini 3.1 ProClaude 3 Haiku vs Claude Opus 4.6Claude 3 Haiku vs GPT-5.3 CodexClaude 3 Haiku vs Grok 4.1Claude 3 Haiku vs GPT-5.2