Nemotron Ultra 253B vs Ministral 3 3B (Reasoning)

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

Nemotron Ultra 253B is clearly ahead on the aggregate, 48 to 31. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Nemotron Ultra 253B's sharpest advantage is in coding, where it averages 33.7 against 7.2. The single biggest benchmark swing on the page is SWE-bench Pro, 38 to 6.

Ministral 3 3B (Reasoning) gives you the larger context window at 128K, compared with 32K for Nemotron Ultra 253B.

Quick Verdict

Pick Nemotron Ultra 253B if you want the stronger benchmark profile. Ministral 3 3B (Reasoning) only becomes the better choice if you need the larger 128K context window.

Agentic

Nemotron Ultra 253B

Nemotron Ultra 253B

46.7

Ministral 3 3B (Reasoning)

34

46
Terminal-Bench 2.0
33
50
BrowseComp
37
45
OSWorld-Verified
33

Coding

Nemotron Ultra 253B

Nemotron Ultra 253B

33.7

Ministral 3 3B (Reasoning)

7.2

41
HumanEval
16
31
SWE-bench Verified
9
30
LiveCodeBench
8
38
SWE-bench Pro
6

Multimodal & Grounded

Nemotron Ultra 253B

Nemotron Ultra 253B

44.7

Ministral 3 3B (Reasoning)

30.4

37
MMMU-Pro
25
54
OfficeQA Pro
37

Reasoning

Nemotron Ultra 253B

Nemotron Ultra 253B

53.3

Ministral 3 3B (Reasoning)

35.3

47
SimpleQA
26
45
MuSR
26
77
BBH
63
55
LongBench v2
37
56
MRCRv2
40

Knowledge

Nemotron Ultra 253B

Nemotron Ultra 253B

42.4

Ministral 3 3B (Reasoning)

25.2

49
MMLU
25
48
GPQA
24
46
SuperGPQA
22
44
OpenBookQA
20
63
MMLU-Pro
49
11
HLE
1
49
FrontierScience
29

Instruction Following

Nemotron Ultra 253B

Nemotron Ultra 253B

78

Ministral 3 3B (Reasoning)

68

78
IFEval
68

Multilingual

Nemotron Ultra 253B

Nemotron Ultra 253B

70.1

Ministral 3 3B (Reasoning)

59.7

74
MGSM
61
68
MMLU-ProX
59

Mathematics

Nemotron Ultra 253B

Nemotron Ultra 253B

59.7

Ministral 3 3B (Reasoning)

40.9

49
AIME 2023
27
51
AIME 2024
29
50
AIME 2025
28
45
HMMT Feb 2023
23
47
HMMT Feb 2024
25
46
HMMT Feb 2025
24
48
BRUMO 2025
26
74
MATH-500
59

Frequently Asked Questions

Which is better, Nemotron Ultra 253B or Ministral 3 3B (Reasoning)?

Nemotron Ultra 253B is ahead overall, 48 to 31. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 38 and 6.

Which is better for knowledge tasks, Nemotron Ultra 253B or Ministral 3 3B (Reasoning)?

Nemotron Ultra 253B has the edge for knowledge tasks in this comparison, averaging 42.4 versus 25.2. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, Nemotron Ultra 253B or Ministral 3 3B (Reasoning)?

Nemotron Ultra 253B has the edge for coding in this comparison, averaging 33.7 versus 7.2. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.

Which is better for math, Nemotron Ultra 253B or Ministral 3 3B (Reasoning)?

Nemotron Ultra 253B has the edge for math in this comparison, averaging 59.7 versus 40.9. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, Nemotron Ultra 253B or Ministral 3 3B (Reasoning)?

Nemotron Ultra 253B has the edge for reasoning in this comparison, averaging 53.3 versus 35.3. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Nemotron Ultra 253B or Ministral 3 3B (Reasoning)?

Nemotron Ultra 253B has the edge for agentic tasks in this comparison, averaging 46.7 versus 34. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Nemotron Ultra 253B or Ministral 3 3B (Reasoning)?

Nemotron Ultra 253B has the edge for multimodal and grounded tasks in this comparison, averaging 44.7 versus 30.4. Inside this category, OfficeQA Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, Nemotron Ultra 253B or Ministral 3 3B (Reasoning)?

Nemotron Ultra 253B has the edge for instruction following in this comparison, averaging 78 versus 68. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, Nemotron Ultra 253B or Ministral 3 3B (Reasoning)?

Nemotron Ultra 253B has the edge for multilingual tasks in this comparison, averaging 70.1 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.