Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
DeepSeek V3.2 is clearly ahead on the aggregate, 64 to 55. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
DeepSeek V3.2's sharpest advantage is in mathematics, where it averages 82.1 against 69.7. The single biggest benchmark swing on the page is HumanEval, 76 to 58. 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 DeepSeek V3.2 if you want the stronger benchmark profile. Ministral 3 14B only becomes the better choice if multimodal & grounded is the priority.
DeepSeek V3.2
58.8
Ministral 3 14B
48.4
DeepSeek V3.2
43.2
Ministral 3 14B
33
DeepSeek V3.2
66
Ministral 3 14B
70.5
DeepSeek V3.2
75.3
Ministral 3 14B
63.6
DeepSeek V3.2
60
Ministral 3 14B
50.1
DeepSeek V3.2
85
Ministral 3 14B
80
DeepSeek V3.2
82.1
Ministral 3 14B
76.8
DeepSeek V3.2
82.1
Ministral 3 14B
69.7
DeepSeek V3.2 is ahead overall, 64 to 55. The biggest single separator in this matchup is HumanEval, where the scores are 76 and 58.
DeepSeek V3.2 has the edge for knowledge tasks in this comparison, averaging 60 versus 50.1. Inside this category, MMLU is the benchmark that creates the most daylight between them.
DeepSeek V3.2 has the edge for coding in this comparison, averaging 43.2 versus 33. Inside this category, HumanEval is the benchmark that creates the most daylight between them.
DeepSeek V3.2 has the edge for math in this comparison, averaging 82.1 versus 69.7. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.
DeepSeek V3.2 has the edge for reasoning in this comparison, averaging 75.3 versus 63.6. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.
DeepSeek V3.2 has the edge for agentic tasks in this comparison, averaging 58.8 versus 48.4. Inside this category, Terminal-Bench 2.0 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 66. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
DeepSeek V3.2 has the edge for instruction following in this comparison, averaging 85 versus 80. Inside this category, IFEval is the benchmark that creates the most daylight between them.
DeepSeek V3.2 has the edge for multilingual tasks in this comparison, averaging 82.1 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.