Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Llama 4 Maverick is clearly ahead on the aggregate, 42 to 35. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Llama 4 Maverick's sharpest advantage is in mathematics, where it averages 46.8 against 23.1. The single biggest benchmark swing on the page is MMLU, 46 to 87.5. GPT-4.1 mini does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
GPT-4.1 mini is also the more expensive model on tokens at $0.40 input / $1.60 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Llama 4 Maverick. That is roughly Infinityx on output cost alone.
Pick Llama 4 Maverick if you want the stronger benchmark profile. GPT-4.1 mini only becomes the better choice if knowledge is the priority.
Llama 4 Maverick
38.7
GPT-4.1 mini
75.9
Llama 4 Maverick
22
GPT-4.1 mini
23.6
Llama 4 Maverick
46.8
GPT-4.1 mini
23.1
Llama 4 Maverick
68
GPT-4.1 mini
88.5
Llama 4 Maverick is ahead overall, 42 to 35. The biggest single separator in this matchup is MMLU, where the scores are 46 and 87.5.
GPT-4.1 mini has the edge for knowledge tasks in this comparison, averaging 75.9 versus 38.7. Inside this category, MMLU is the benchmark that creates the most daylight between them.
GPT-4.1 mini has the edge for coding in this comparison, averaging 23.6 versus 22. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
Llama 4 Maverick has the edge for math in this comparison, averaging 46.8 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 68. 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.