Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Llama 3.1 405B is clearly ahead on the aggregate, 65 to 51. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Llama 3.1 405B's sharpest advantage is in coding, where it averages 48.3 against 41. The single biggest benchmark swing on the page is MMLU, 70 to 91.8. o1 does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
o1 is the reasoning model in the pair, while Llama 3.1 405B 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. o1 gives you the larger context window at 200K, compared with 128K for Llama 3.1 405B.
Pick Llama 3.1 405B if you want the stronger benchmark profile. o1 only becomes the better choice if knowledge is the priority or you need the larger 200K context window.
Llama 3.1 405B
58.7
o1
83.8
Llama 3.1 405B
48.3
o1
41
Llama 3.1 405B
70.6
o1
74.3
Llama 3.1 405B
86
o1
92.2
Llama 3.1 405B is ahead overall, 65 to 51. The biggest single separator in this matchup is MMLU, where the scores are 70 and 91.8.
o1 has the edge for knowledge tasks in this comparison, averaging 83.8 versus 58.7. Inside this category, MMLU is the benchmark that creates the most daylight between them.
Llama 3.1 405B has the edge for coding in this comparison, averaging 48.3 versus 41. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
o1 has the edge for math in this comparison, averaging 74.3 versus 70.6. Inside this category, AIME 2024 is the benchmark that creates the most daylight between them.
o1 has the edge for instruction following in this comparison, averaging 92.2 versus 86. 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.