Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Mistral Large 2 is clearly ahead on the aggregate, 59 to 55. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Mistral Large 2's sharpest advantage is in coding, where it averages 41.8 against 33. The single biggest benchmark swing on the page is MMMU-Pro, 56 to 70. Ministral 3 14B does hit back in multimodal & grounded, so the answer changes if that is the part of the workload you care about most.
Pick Mistral Large 2 if you want the stronger benchmark profile. Ministral 3 14B only becomes the better choice if multimodal & grounded is the priority.
Mistral Large 2
52.2
Ministral 3 14B
48.4
Mistral Large 2
41.8
Ministral 3 14B
33
Mistral Large 2
61
Ministral 3 14B
70.5
Mistral Large 2
67.5
Ministral 3 14B
63.6
Mistral Large 2
54.6
Ministral 3 14B
50.1
Mistral Large 2
83
Ministral 3 14B
80
Mistral Large 2
79.1
Ministral 3 14B
76.8
Mistral Large 2
73.8
Ministral 3 14B
69.7
Mistral Large 2 is ahead overall, 59 to 55. The biggest single separator in this matchup is MMMU-Pro, where the scores are 56 and 70.
Mistral Large 2 has the edge for knowledge tasks in this comparison, averaging 54.6 versus 50.1. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.
Mistral Large 2 has the edge for coding in this comparison, averaging 41.8 versus 33. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
Mistral Large 2 has the edge for math in this comparison, averaging 73.8 versus 69.7. Inside this category, MATH-500 is the benchmark that creates the most daylight between them.
Mistral Large 2 has the edge for reasoning in this comparison, averaging 67.5 versus 63.6. Inside this category, BBH is the benchmark that creates the most daylight between them.
Mistral Large 2 has the edge for agentic tasks in this comparison, averaging 52.2 versus 48.4. Inside this category, OSWorld-Verified is the benchmark that creates the most daylight between them.
Ministral 3 14B has the edge for multimodal and grounded tasks in this comparison, averaging 70.5 versus 61. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
Mistral Large 2 has the edge for instruction following in this comparison, averaging 83 versus 80. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Mistral Large 2 has the edge for multilingual tasks in this comparison, averaging 79.1 versus 76.8. Inside this category, MMLU-ProX 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.