Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Sibling matchup inside the GPT-5 family.
GPT-5 (medium) and GPT-5 nano sit in the same GPT-5 family. This page is less about two unrelated model lineages and more about how the siblings trade off on benchmark shape, token costs, and practical limits like context window.
GPT-5 (medium) is clearly ahead on the aggregate, 82 to 31. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GPT-5 (medium)'s sharpest advantage is in mathematics, where it averages 92 against 85.2. The single biggest benchmark swing on the page is GPQA, 89 to 71.2.
GPT-5 nano gives you the larger context window at 400K, compared with 128K for GPT-5 (medium).
GPT-5 (medium) makes more sense if mathematics is the priority, while GPT-5 nano is the cleaner fit if you need the larger 400K context window.
GPT-5 (medium)
76.7
GPT-5 nano
71.2
GPT-5 (medium)
92
GPT-5 nano
85.2
GPT-5 (medium) and GPT-5 nano are sibling variants in the GPT-5 family, so the right pick depends on whether you value the better benchmark line, cheaper tokens, or the larger context window. GPT-5 (medium) is ahead overall 82 to 31.
GPT-5 (medium) has the edge for knowledge tasks in this comparison, averaging 76.7 versus 71.2. Inside this category, GPQA is the benchmark that creates the most daylight between them.
GPT-5 (medium) has the edge for math in this comparison, averaging 92 versus 85.2. Inside this category, AIME 2025 is the benchmark that creates the most daylight between them.
Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.
Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.