Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GPT-5 mini wins overall with a score of 68 vs 25 (43 point difference).GPT-5 mini wins 4 out of 4 categories.
DeepSeek V3.1 (Reasoning)
31.8
GPT-5 mini
85
DeepSeek V3.1 (Reasoning)
26
GPT-5 mini
80
DeepSeek V3.1 (Reasoning)
33
GPT-5 mini
89
DeepSeek V3.1 (Reasoning)
31
GPT-5 mini
83
GPT-5 mini scores higher overall with 68 vs 25, a difference of 43 points across all benchmarks.
GPT-5 mini leads in knowledge tasks with an average score of 85 vs 31.8.
GPT-5 mini leads in coding with an average score of 80 vs 26.
GPT-5 mini leads in math with an average score of 89 vs 33.
GPT-5 mini leads in reasoning with an average score of 83 vs 31.