Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GPT-4o wins overall with a score of 56 vs 35 (21 point difference).GPT-4o wins 4 out of 4 categories.
DeepSeek-R1
41.8
GPT-4o
64.5
DeepSeek-R1
36
GPT-4o
58
DeepSeek-R1
43
GPT-4o
65
DeepSeek-R1
41
GPT-4o
63
GPT-4o scores higher overall with 56 vs 35, a difference of 21 points across all benchmarks.
GPT-4o leads in knowledge tasks with an average score of 64.5 vs 41.8.
GPT-4o leads in coding with an average score of 58 vs 36.
GPT-4o leads in math with an average score of 65 vs 43.
GPT-4o leads in reasoning with an average score of 63 vs 41.