Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GPT-5 (medium) wins overall with a score of 70 vs 60 (10 point difference).GPT-5 (medium) wins 4 out of 4 categories.
GPT-5 (medium)
88
Nemotron 3 Ultra 500B
71.8
GPT-5 (medium)
83
Nemotron 3 Ultra 500B
66
GPT-5 (medium)
92
Nemotron 3 Ultra 500B
73
GPT-5 (medium)
86
Nemotron 3 Ultra 500B
70
GPT-5 (medium) scores higher overall with 70 vs 60, a difference of 10 points across all benchmarks.
GPT-5 (medium) leads in knowledge tasks with an average score of 88 vs 71.8.
GPT-5 (medium) leads in coding with an average score of 83 vs 66.
GPT-5 (medium) leads in math with an average score of 92 vs 73.
GPT-5 (medium) leads in reasoning with an average score of 86 vs 70.