Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GPT-4 Turbo wins overall with a score of 50 vs 46 (4 point difference).GPT-4 Turbo wins 4 out of 4 categories.
Claude 3 Haiku
54.5
GPT-4 Turbo
58.5
Claude 3 Haiku
48
GPT-4 Turbo
52
Claude 3 Haiku
55
GPT-4 Turbo
59
Claude 3 Haiku
53
GPT-4 Turbo
57
GPT-4 Turbo scores higher overall with 50 vs 46, a difference of 4 points across all benchmarks.
GPT-4 Turbo leads in knowledge tasks with an average score of 58.5 vs 54.5.
GPT-4 Turbo leads in coding with an average score of 52 vs 48.
GPT-4 Turbo leads in math with an average score of 59 vs 55.
GPT-4 Turbo leads in reasoning with an average score of 57 vs 53.