benchlm.ai

o1-preview vs o3

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

Quick Verdict

o1-preview wins overall with a score of 71 vs 67 (4 point difference).o1-preview wins 4 out of 4 categories.

o1-preview

CreatorOpenAI
TypeProprietary
Context200K
Score71

o3

CreatorOpenAI
TypeProprietary
Context200K
Score67

Knowledge

o1-preview

o1-preview

89

o3

85.3

92
MMLU
86
90
GPQA
87
88
SuperGPQA
85
86
OpenBookQA
83

Coding

o1-preview

o1-preview

86

o3

78

86
HumanEval
78

Mathematics

o1-preview

o1-preview

93

o3

87

94
AIME 2023
88
96
AIME 2024
90
95
AIME 2025
89
90
HMMT Feb 2023
84
92
HMMT Feb 2024
86
91
HMMT Feb 2025
85
93
BRUMO 2025
87

Reasoning

o1-preview

o1-preview

87

o3

83

88
SimpleQA
84
86
MuSR
82

Frequently Asked Questions

Which is better, o1-preview or o3?

o1-preview scores higher overall with 71 vs 67, a difference of 4 points across all benchmarks.

Which is better for knowledge tasks, o1-preview or o3?

o1-preview leads in knowledge tasks with an average score of 89 vs 85.3.

Which is better for coding, o1-preview or o3?

o1-preview leads in coding with an average score of 86 vs 78.

Which is better for math, o1-preview or o3?

o1-preview leads in math with an average score of 93 vs 87.

Which is better for reasoning, o1-preview or o3?

o1-preview leads in reasoning with an average score of 87 vs 83.

Related Comparisons

o1-preview vs GPT-5.4o1-preview vs Gemini 3.1 Proo1-preview vs Claude Opus 4.6o1-preview vs GPT-5.3 Codexo1-preview vs Grok 4.1o1-preview vs GPT-5.2