Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Sibling matchup inside the GPT-4.1 family.
GPT-4.1 mini and GPT-4.1 nano sit in the same GPT-4.1 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-4.1 mini is clearly ahead on the aggregate, 35 to 23. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GPT-4.1 mini's sharpest advantage is in mathematics, where it averages 23.1 against 9.8. The single biggest benchmark swing on the page is GPQA, 64.2 to 50.3.
GPT-4.1 mini is also the more expensive model on tokens at $0.40 input / $1.60 output per 1M tokens, versus $0.10 input / $0.40 output per 1M tokens for GPT-4.1 nano. That is roughly 4.0x on output cost alone.
GPT-4.1 mini makes more sense if mathematics is the priority, while GPT-4.1 nano is the cleaner fit if you want the cheaper token bill.
GPT-4.1 mini
75.9
GPT-4.1 nano
65.2
GPT-4.1 mini
23.1
GPT-4.1 nano
9.8
GPT-4.1 mini
88.5
GPT-4.1 nano
83.2
GPT-4.1 mini and GPT-4.1 nano are sibling variants in the GPT-4.1 family, so the right pick depends on whether you value the better benchmark line, cheaper tokens, or the larger context window. GPT-4.1 mini is ahead overall 35 to 23.
GPT-4.1 mini has the edge for knowledge tasks in this comparison, averaging 75.9 versus 65.2. Inside this category, GPQA is the benchmark that creates the most daylight between them.
GPT-4.1 mini has the edge for math in this comparison, averaging 23.1 versus 9.8. Inside this category, AIME 2024 is the benchmark that creates the most daylight between them.
GPT-4.1 mini has the edge for instruction following in this comparison, averaging 88.5 versus 83.2. Inside this category, IFEval 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.