Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
o3-pro wins overall with a score of 68 vs 24 (44 point difference).o3-pro wins 4 out of 4 categories.
DeepSeek V3.1
30.8
o3-pro
87.3
DeepSeek V3.1
25
o3-pro
80
DeepSeek V3.1
32
o3-pro
89
DeepSeek V3.1
30
o3-pro
85
o3-pro scores higher overall with 68 vs 24, a difference of 44 points across all benchmarks.
o3-pro leads in knowledge tasks with an average score of 87.3 vs 30.8.
o3-pro leads in coding with an average score of 80 vs 25.
o3-pro leads in math with an average score of 89 vs 32.
o3-pro leads in reasoning with an average score of 85 vs 30.