Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GPT-4o wins overall with a score of 56 vs 46 (10 point difference).GPT-4o wins 4 out of 4 categories.
Claude 3 Haiku
54.5
GPT-4o
64.5
Claude 3 Haiku
48
GPT-4o
58
Claude 3 Haiku
55
GPT-4o
65
Claude 3 Haiku
53
GPT-4o
63
GPT-4o scores higher overall with 56 vs 46, a difference of 10 points across all benchmarks.
GPT-4o leads in knowledge tasks with an average score of 64.5 vs 54.5.
GPT-4o leads in coding with an average score of 58 vs 48.
GPT-4o leads in math with an average score of 65 vs 55.
GPT-4o leads in reasoning with an average score of 63 vs 53.