Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
o3 wins overall with a score of 67 vs 21 (46 point difference).o3 wins 4 out of 4 categories.
Mistral 7B v0.3
27.8
o3
85.3
Mistral 7B v0.3
22
o3
78
Mistral 7B v0.3
29
o3
87
Mistral 7B v0.3
27
o3
83
o3 scores higher overall with 67 vs 21, a difference of 46 points across all benchmarks.
o3 leads in knowledge tasks with an average score of 85.3 vs 27.8.
o3 leads in coding with an average score of 78 vs 22.
o3 leads in math with an average score of 87 vs 29.
o3 leads in reasoning with an average score of 83 vs 27.