Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
o1-preview is clearly ahead on the aggregate, 77 to 27. 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 coding, where it averages 64.6 against 6.2. The single biggest benchmark swing on the page is HumanEval, 86 to 15.
o1-preview is the reasoning model in the pair, while Ministral 3 3B 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-preview gives you the larger context window at 200K, compared with 128K for Ministral 3 3B.
Pick o1-preview if you want the stronger benchmark profile. Ministral 3 3B only becomes the better choice if you would rather avoid the extra latency and token burn of a reasoning model.
o1-preview
75.4
Ministral 3 3B
22.9
o1-preview
64.6
Ministral 3 3B
6.2
o1-preview
75.6
Ministral 3 3B
30.4
o1-preview
86.8
Ministral 3 3B
30.1
o1-preview
71.3
Ministral 3 3B
24.5
o1-preview
88
Ministral 3 3B
67
o1-preview
87.4
Ministral 3 3B
59.7
o1-preview
93.5
Ministral 3 3B
36
o1-preview is ahead overall, 77 to 27. The biggest single separator in this matchup is HumanEval, where the scores are 86 and 15.
o1-preview has the edge for knowledge tasks in this comparison, averaging 71.3 versus 24.5. Inside this category, MMLU is the benchmark that creates the most daylight between them.
o1-preview has the edge for coding in this comparison, averaging 64.6 versus 6.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.
o1-preview has the edge for math in this comparison, averaging 93.5 versus 36. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.
o1-preview has the edge for reasoning in this comparison, averaging 86.8 versus 30.1. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.
o1-preview has the edge for agentic tasks in this comparison, averaging 75.4 versus 22.9. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
o1-preview has the edge for multimodal and grounded tasks in this comparison, averaging 75.6 versus 30.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
o1-preview has the edge for instruction following in this comparison, averaging 88 versus 67. Inside this category, IFEval is the benchmark that creates the most daylight between them.
o1-preview has the edge for multilingual tasks in this comparison, averaging 87.4 versus 59.7. Inside this category, MGSM 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.