Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
o4-mini (high) wins overall with a score of 65 vs 52 (13 point difference).o4-mini (high) wins 4 out of 4 categories.
Mistral 8x7B
62.8
o4-mini (high)
80.5
Mistral 8x7B
55
o4-mini (high)
74
Mistral 8x7B
64
o4-mini (high)
82
Mistral 8x7B
62
o4-mini (high)
79
o4-mini (high) scores higher overall with 65 vs 52, a difference of 13 points across all benchmarks.
o4-mini (high) leads in knowledge tasks with an average score of 80.5 vs 62.8.
o4-mini (high) leads in coding with an average score of 74 vs 55.
o4-mini (high) leads in math with an average score of 82 vs 64.
o4-mini (high) leads in reasoning with an average score of 79 vs 62.