Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
o4-mini (high) wins overall with a score of 65 vs 50 (15 point difference).o4-mini (high) wins 4 out of 4 categories.
GPT-4 Turbo
58.5
o4-mini (high)
80.5
GPT-4 Turbo
52
o4-mini (high)
74
GPT-4 Turbo
59
o4-mini (high)
82
GPT-4 Turbo
57
o4-mini (high)
79
o4-mini (high) scores higher overall with 65 vs 50, a difference of 15 points across all benchmarks.
o4-mini (high) leads in knowledge tasks with an average score of 80.5 vs 58.5.
o4-mini (high) leads in coding with an average score of 74 vs 52.
o4-mini (high) leads in math with an average score of 82 vs 59.
o4-mini (high) leads in reasoning with an average score of 79 vs 57.