Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GPT-5 (medium) wins overall with a score of 70 vs 51 (19 point difference).GPT-5 (medium) wins 4 out of 4 categories.
Claude 3 Opus
59.5
GPT-5 (medium)
88
Claude 3 Opus
53
GPT-5 (medium)
83
Claude 3 Opus
60
GPT-5 (medium)
92
Claude 3 Opus
58
GPT-5 (medium)
86
GPT-5 (medium) scores higher overall with 70 vs 51, a difference of 19 points across all benchmarks.
GPT-5 (medium) leads in knowledge tasks with an average score of 88 vs 59.5.
GPT-5 (medium) leads in coding with an average score of 83 vs 53.
GPT-5 (medium) leads in math with an average score of 92 vs 60.
GPT-5 (medium) leads in reasoning with an average score of 86 vs 58.