Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GPT-5 mini wins overall with a score of 68 vs 46 (22 point difference).GPT-5 mini wins 4 out of 4 categories.
Claude 3 Haiku
54.5
GPT-5 mini
85
Claude 3 Haiku
48
GPT-5 mini
80
Claude 3 Haiku
55
GPT-5 mini
89
Claude 3 Haiku
53
GPT-5 mini
83
GPT-5 mini scores higher overall with 68 vs 46, a difference of 22 points across all benchmarks.
GPT-5 mini leads in knowledge tasks with an average score of 85 vs 54.5.
GPT-5 mini leads in coding with an average score of 80 vs 48.
GPT-5 mini leads in math with an average score of 89 vs 55.
GPT-5 mini leads in reasoning with an average score of 83 vs 53.