Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
o1-preview is clearly ahead on the aggregate, 83 to 35. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
o1-preview's sharpest advantage is in mathematics, where it averages 93.1 against 23.1. The single biggest benchmark swing on the page is AIME 2024, 96 to 23.1. GPT-4.1 mini does hit back in instruction following, so the answer changes if that is the part of the workload you care about most.
o1-preview is the reasoning model in the pair, while GPT-4.1 mini is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. GPT-4.1 mini gives you the larger context window at 1M, compared with 200K for o1-preview.
Pick o1-preview if you want the stronger benchmark profile. GPT-4.1 mini only becomes the better choice if instruction following is the priority or you need the larger 1M context window.
o1-preview
78
GPT-4.1 mini
75.9
o1-preview
70.3
GPT-4.1 mini
23.6
o1-preview
93.1
GPT-4.1 mini
23.1
o1-preview
88
GPT-4.1 mini
88.5
o1-preview is ahead overall, 83 to 35. The biggest single separator in this matchup is AIME 2024, where the scores are 96 and 23.1.
o1-preview has the edge for knowledge tasks in this comparison, averaging 78 versus 75.9. Inside this category, GPQA is the benchmark that creates the most daylight between them.
o1-preview has the edge for coding in this comparison, averaging 70.3 versus 23.6. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
o1-preview has the edge for math in this comparison, averaging 93.1 versus 23.1. 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 88. 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.