Nemotron-4 15B vs Ministral 3 3B

Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.

Nemotron-4 15B is clearly ahead on the aggregate, 47 to 27. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Nemotron-4 15B's sharpest advantage is in mathematics, where it averages 61.1 against 36. The single biggest benchmark swing on the page is HumanEval, 46 to 15.

Ministral 3 3B gives you the larger context window at 128K, compared with 32K for Nemotron-4 15B.

Quick Verdict

Pick Nemotron-4 15B if you want the stronger benchmark profile. Ministral 3 3B only becomes the better choice if you need the larger 128K context window.

Agentic

Nemotron-4 15B

Nemotron-4 15B

41.3

Ministral 3 3B

22.9

37
Terminal-Bench 2.0
19
47
BrowseComp
33
42
OSWorld-Verified
20

Coding

Nemotron-4 15B

Nemotron-4 15B

26.5

Ministral 3 3B

6.2

46
HumanEval
15
31
SWE-bench Verified
8
22
LiveCodeBench
7
30
SWE-bench Pro
5

Multimodal & Grounded

Nemotron-4 15B

Nemotron-4 15B

49.6

Ministral 3 3B

30.4

46
MMMU-Pro
25
54
OfficeQA Pro
37

Reasoning

Nemotron-4 15B

Nemotron-4 15B

53.4

Ministral 3 3B

30.1

52
SimpleQA
22
50
MuSR
20
73
BBH
57
52
LongBench v2
32
51
MRCRv2
35

Knowledge

Nemotron-4 15B

Nemotron-4 15B

42.6

Ministral 3 3B

24.5

54
MMLU
24
53
GPQA
23
51
SuperGPQA
21
49
OpenBookQA
19
63
MMLU-Pro
48
5
HLE
1
50
FrontierScience
28

Instruction Following

Nemotron-4 15B

Nemotron-4 15B

79

Ministral 3 3B

67

79
IFEval
67

Multilingual

Nemotron-4 15B

Nemotron-4 15B

72.4

Ministral 3 3B

59.7

75
MGSM
61
71
MMLU-ProX
59

Mathematics

Nemotron-4 15B

Nemotron-4 15B

61.1

Ministral 3 3B

36

54
AIME 2023
23
56
AIME 2024
25
55
AIME 2025
24
50
HMMT Feb 2023
19
52
HMMT Feb 2024
21
51
HMMT Feb 2025
20
53
BRUMO 2025
22
71
MATH-500
53

Frequently Asked Questions

Which is better, Nemotron-4 15B or Ministral 3 3B?

Nemotron-4 15B is ahead overall, 47 to 27. The biggest single separator in this matchup is HumanEval, where the scores are 46 and 15.

Which is better for knowledge tasks, Nemotron-4 15B or Ministral 3 3B?

Nemotron-4 15B has the edge for knowledge tasks in this comparison, averaging 42.6 versus 24.5. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, Nemotron-4 15B or Ministral 3 3B?

Nemotron-4 15B has the edge for coding in this comparison, averaging 26.5 versus 6.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.

Which is better for math, Nemotron-4 15B or Ministral 3 3B?

Nemotron-4 15B has the edge for math in this comparison, averaging 61.1 versus 36. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, Nemotron-4 15B or Ministral 3 3B?

Nemotron-4 15B has the edge for reasoning in this comparison, averaging 53.4 versus 30.1. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Nemotron-4 15B or Ministral 3 3B?

Nemotron-4 15B has the edge for agentic tasks in this comparison, averaging 41.3 versus 22.9. Inside this category, OSWorld-Verified is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Nemotron-4 15B or Ministral 3 3B?

Nemotron-4 15B has the edge for multimodal and grounded tasks in this comparison, averaging 49.6 versus 30.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, Nemotron-4 15B or Ministral 3 3B?

Nemotron-4 15B has the edge for instruction following in this comparison, averaging 79 versus 67. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, Nemotron-4 15B or Ministral 3 3B?

Nemotron-4 15B has the edge for multilingual tasks in this comparison, averaging 72.4 versus 59.7. Inside this category, MGSM is the benchmark that creates the most daylight between them.

Last updated: March 12, 2026

Weekly LLM Benchmark Digest

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.