Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
MiniMax M2.5 is clearly ahead on the aggregate, 66 to 23. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
MiniMax M2.5's sharpest advantage is in mathematics, where it averages 73.1 against 9.8. The single biggest benchmark swing on the page is AIME 2024, 75 to 9.8. GPT-4.1 nano does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
MiniMax M2.5 is also the more expensive model on tokens at $0.30 input / $1.20 output per 1M tokens, versus $0.10 input / $0.40 output per 1M tokens for GPT-4.1 nano. That is roughly 3.0x on output cost alone. GPT-4.1 nano gives you the larger context window at 1M, compared with 128K for MiniMax M2.5.
Pick MiniMax M2.5 if you want the stronger benchmark profile. GPT-4.1 nano only becomes the better choice if knowledge is the priority or you want the cheaper token bill.
MiniMax M2.5
61
GPT-4.1 nano
65.2
MiniMax M2.5
73.1
GPT-4.1 nano
9.8
MiniMax M2.5
85
GPT-4.1 nano
83.2
MiniMax M2.5 is ahead overall, 66 to 23. The biggest single separator in this matchup is AIME 2024, where the scores are 75 and 9.8.
GPT-4.1 nano has the edge for knowledge tasks in this comparison, averaging 65.2 versus 61. Inside this category, GPQA is the benchmark that creates the most daylight between them.
MiniMax M2.5 has the edge for math in this comparison, averaging 73.1 versus 9.8. Inside this category, AIME 2024 is the benchmark that creates the most daylight between them.
MiniMax M2.5 has the edge for instruction following in this comparison, averaging 85 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.