Ministral 3 14B vs LFM2.5-1.2B-Instruct

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

Ministral 3 14B is clearly ahead on the aggregate, 55 to 30. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Ministral 3 14B's sharpest advantage is in multimodal & grounded, where it averages 70.5 against 32.4. The single biggest benchmark swing on the page is AIME 2025, 72 to 25.

Ministral 3 14B gives you the larger context window at 128K, compared with 32K for LFM2.5-1.2B-Instruct.

Quick Verdict

Pick Ministral 3 14B if you want the stronger benchmark profile. LFM2.5-1.2B-Instruct only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.

Agentic

Ministral 3 14B

Ministral 3 14B

48.4

LFM2.5-1.2B-Instruct

25.7

48
Terminal-Bench 2.0
22
55
BrowseComp
31
44
OSWorld-Verified
26

Coding

Ministral 3 14B

Ministral 3 14B

33

LFM2.5-1.2B-Instruct

7.2

58
HumanEval
14
37
SWE-bench Verified
9
31
LiveCodeBench
8
34
SWE-bench Pro
6

Multimodal & Grounded

Ministral 3 14B

Ministral 3 14B

70.5

LFM2.5-1.2B-Instruct

32.4

70
MMMU-Pro
27
71
OfficeQA Pro
39

Reasoning

Ministral 3 14B

Ministral 3 14B

63.6

LFM2.5-1.2B-Instruct

32.1

66
SimpleQA
24
64
MuSR
22
74
BBH
59
60
LongBench v2
34
60
MRCRv2
37

Knowledge

Ministral 3 14B

Ministral 3 14B

50.1

LFM2.5-1.2B-Instruct

26

69
MMLU
26
68
GPQA
25
66
SuperGPQA
23
64
OpenBookQA
21
67
MMLU-Pro
50
5
HLE
1
60
FrontierScience
30

Instruction Following

Tie

Ministral 3 14B

80

LFM2.5-1.2B-Instruct

80

80
IFEval
80

Multilingual

Ministral 3 14B

Ministral 3 14B

76.8

LFM2.5-1.2B-Instruct

60.7

80
MGSM
62
75
MMLU-ProX
60

Mathematics

Ministral 3 14B

Ministral 3 14B

69.7

LFM2.5-1.2B-Instruct

37

68
AIME 2023
24
70
AIME 2024
26
72
AIME 2025
25
64
HMMT Feb 2023
20
66
HMMT Feb 2024
22
65
HMMT Feb 2025
21
67
BRUMO 2025
23
72
MATH-500
54

Frequently Asked Questions

Which is better, Ministral 3 14B or LFM2.5-1.2B-Instruct?

Ministral 3 14B is ahead overall, 55 to 30. The biggest single separator in this matchup is AIME 2025, where the scores are 72 and 25.

Which is better for knowledge tasks, Ministral 3 14B or LFM2.5-1.2B-Instruct?

Ministral 3 14B has the edge for knowledge tasks in this comparison, averaging 50.1 versus 26. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, Ministral 3 14B or LFM2.5-1.2B-Instruct?

Ministral 3 14B has the edge for coding in this comparison, averaging 33 versus 7.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.

Which is better for math, Ministral 3 14B or LFM2.5-1.2B-Instruct?

Ministral 3 14B has the edge for math in this comparison, averaging 69.7 versus 37. Inside this category, AIME 2025 is the benchmark that creates the most daylight between them.

Which is better for reasoning, Ministral 3 14B or LFM2.5-1.2B-Instruct?

Ministral 3 14B has the edge for reasoning in this comparison, averaging 63.6 versus 32.1. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Ministral 3 14B or LFM2.5-1.2B-Instruct?

Ministral 3 14B has the edge for agentic tasks in this comparison, averaging 48.4 versus 25.7. 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, Ministral 3 14B or LFM2.5-1.2B-Instruct?

Ministral 3 14B has the edge for multimodal and grounded tasks in this comparison, averaging 70.5 versus 32.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, Ministral 3 14B or LFM2.5-1.2B-Instruct?

Ministral 3 14B and LFM2.5-1.2B-Instruct are effectively tied for instruction following here, both landing at 80 on average.

Which is better for multilingual tasks, Ministral 3 14B or LFM2.5-1.2B-Instruct?

Ministral 3 14B has the edge for multilingual tasks in this comparison, averaging 76.8 versus 60.7. 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.