Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GPT-5 mini wins overall with a score of 68 vs 35 (33 point difference).GPT-5 mini wins 4 out of 4 categories.
DeepSeek-R1
41.8
GPT-5 mini
85
DeepSeek-R1
36
GPT-5 mini
80
DeepSeek-R1
43
GPT-5 mini
89
DeepSeek-R1
41
GPT-5 mini
83
GPT-5 mini scores higher overall with 68 vs 35, a difference of 33 points across all benchmarks.
GPT-5 mini leads in knowledge tasks with an average score of 85 vs 41.8.
GPT-5 mini leads in coding with an average score of 80 vs 36.
GPT-5 mini leads in math with an average score of 89 vs 43.
GPT-5 mini leads in reasoning with an average score of 83 vs 41.