Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GPT-5 mini wins overall with a score of 68 vs 59 (9 point difference).GPT-5 mini wins 4 out of 4 categories.
Claude 4 Sonnet
71.5
GPT-5 mini
85
Claude 4 Sonnet
65
GPT-5 mini
80
Claude 4 Sonnet
72
GPT-5 mini
89
Claude 4 Sonnet
70
GPT-5 mini
83
GPT-5 mini scores higher overall with 68 vs 59, a difference of 9 points across all benchmarks.
GPT-5 mini leads in knowledge tasks with an average score of 85 vs 71.5.
GPT-5 mini leads in coding with an average score of 80 vs 65.
GPT-5 mini leads in math with an average score of 89 vs 72.
GPT-5 mini leads in reasoning with an average score of 83 vs 70.