Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Sibling matchup inside the Ministral 3 3B family.
Ministral 3 3B (Reasoning) and Ministral 3 3B sit in the same Ministral 3 3B family. This page is less about two unrelated model lineages and more about how the siblings trade off on benchmark shape, token costs, and practical limits like context window.
Ministral 3 3B (Reasoning) is clearly ahead on the aggregate, 31 to 27. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Ministral 3 3B (Reasoning)'s sharpest advantage is in agentic, where it averages 34 against 22.9. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 33 to 19.
Ministral 3 3B (Reasoning) 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.
Ministral 3 3B (Reasoning) makes more sense if agentic is the priority or you want the stronger reasoning-first profile, while Ministral 3 3B is the cleaner fit if you would rather avoid the extra latency and token burn of a reasoning model.
Ministral 3 3B (Reasoning)
34
Ministral 3 3B
22.9
Ministral 3 3B (Reasoning)
7.2
Ministral 3 3B
6.2
Ministral 3 3B (Reasoning)
30.4
Ministral 3 3B
30.4
Ministral 3 3B (Reasoning)
35.3
Ministral 3 3B
30.1
Ministral 3 3B (Reasoning)
25.2
Ministral 3 3B
24.5
Ministral 3 3B (Reasoning)
68
Ministral 3 3B
67
Ministral 3 3B (Reasoning)
59.7
Ministral 3 3B
59.7
Ministral 3 3B (Reasoning)
40.9
Ministral 3 3B
36
Ministral 3 3B (Reasoning) and Ministral 3 3B are sibling variants in the Ministral 3 3B family, so the right pick depends on whether you value the better benchmark line, cheaper tokens, or the larger context window. Ministral 3 3B (Reasoning) is ahead overall 31 to 27.
Ministral 3 3B (Reasoning) has the edge for knowledge tasks in this comparison, averaging 25.2 versus 24.5. Inside this category, MMLU is the benchmark that creates the most daylight between them.
Ministral 3 3B (Reasoning) has the edge for coding in this comparison, averaging 7.2 versus 6.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.
Ministral 3 3B (Reasoning) has the edge for math in this comparison, averaging 40.9 versus 36. Inside this category, MATH-500 is the benchmark that creates the most daylight between them.
Ministral 3 3B (Reasoning) has the edge for reasoning in this comparison, averaging 35.3 versus 30.1. Inside this category, MuSR is the benchmark that creates the most daylight between them.
Ministral 3 3B (Reasoning) has the edge for agentic tasks in this comparison, averaging 34 versus 22.9. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Ministral 3 3B (Reasoning) and Ministral 3 3B are effectively tied for multimodal and grounded tasks here, both landing at 30.4 on average.
Ministral 3 3B (Reasoning) has the edge for instruction following in this comparison, averaging 68 versus 67. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Ministral 3 3B (Reasoning) and Ministral 3 3B are effectively tied for multilingual tasks here, both landing at 59.7 on average.
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.