LFM2.5-1.2B-Thinking vs Ministral 3 3B (Reasoning)

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

LFM2.5-1.2B-Thinking has the cleaner overall profile here, landing at 33 versus 31. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

LFM2.5-1.2B-Thinking's sharpest advantage is in instruction following, where it averages 72 against 68. The single biggest benchmark swing on the page is MuSR, 31 to 26.

Ministral 3 3B (Reasoning) gives you the larger context window at 128K, compared with 32K for LFM2.5-1.2B-Thinking.

Quick Verdict

Pick LFM2.5-1.2B-Thinking 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

LFM2.5-1.2B-Thinking

LFM2.5-1.2B-Thinking

34.1

Ministral 3 3B (Reasoning)

34

34
Terminal-Bench 2.0
33
37
BrowseComp
37
32
OSWorld-Verified
33

Coding

LFM2.5-1.2B-Thinking

LFM2.5-1.2B-Thinking

8.2

Ministral 3 3B (Reasoning)

7.2

17
HumanEval
16
10
SWE-bench Verified
9
9
LiveCodeBench
8
7
SWE-bench Pro
6

Multimodal & Grounded

LFM2.5-1.2B-Thinking

LFM2.5-1.2B-Thinking

32.4

Ministral 3 3B (Reasoning)

30.4

27
MMMU-Pro
25
39
OfficeQA Pro
37

Reasoning

LFM2.5-1.2B-Thinking

LFM2.5-1.2B-Thinking

38.4

Ministral 3 3B (Reasoning)

35.3

29
SimpleQA
26
31
MuSR
26
67
BBH
63
39
LongBench v2
37
42
MRCRv2
40

Knowledge

LFM2.5-1.2B-Thinking

LFM2.5-1.2B-Thinking

27

Ministral 3 3B (Reasoning)

25.2

27
MMLU
25
26
GPQA
24
24
SuperGPQA
22
22
OpenBookQA
20
51
MMLU-Pro
49
2
HLE
1
31
FrontierScience
29

Instruction Following

LFM2.5-1.2B-Thinking

LFM2.5-1.2B-Thinking

72

Ministral 3 3B (Reasoning)

68

72
IFEval
68

Multilingual

LFM2.5-1.2B-Thinking

LFM2.5-1.2B-Thinking

60.7

Ministral 3 3B (Reasoning)

59.7

62
MGSM
61
60
MMLU-ProX
59

Mathematics

LFM2.5-1.2B-Thinking

LFM2.5-1.2B-Thinking

42.3

Ministral 3 3B (Reasoning)

40.9

28
AIME 2023
27
30
AIME 2024
29
29
AIME 2025
28
24
HMMT Feb 2023
23
26
HMMT Feb 2024
25
25
HMMT Feb 2025
24
27
BRUMO 2025
26
61
MATH-500
59

Frequently Asked Questions

Which is better, LFM2.5-1.2B-Thinking or Ministral 3 3B (Reasoning)?

LFM2.5-1.2B-Thinking is ahead overall, 33 to 31. The biggest single separator in this matchup is MuSR, where the scores are 31 and 26.

Which is better for knowledge tasks, LFM2.5-1.2B-Thinking or Ministral 3 3B (Reasoning)?

LFM2.5-1.2B-Thinking has the edge for knowledge tasks in this comparison, averaging 27 versus 25.2. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, LFM2.5-1.2B-Thinking or Ministral 3 3B (Reasoning)?

LFM2.5-1.2B-Thinking has the edge for coding in this comparison, averaging 8.2 versus 7.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.

Which is better for math, LFM2.5-1.2B-Thinking or Ministral 3 3B (Reasoning)?

LFM2.5-1.2B-Thinking has the edge for math in this comparison, averaging 42.3 versus 40.9. Inside this category, MATH-500 is the benchmark that creates the most daylight between them.

Which is better for reasoning, LFM2.5-1.2B-Thinking or Ministral 3 3B (Reasoning)?

LFM2.5-1.2B-Thinking has the edge for reasoning in this comparison, averaging 38.4 versus 35.3. Inside this category, MuSR is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, LFM2.5-1.2B-Thinking or Ministral 3 3B (Reasoning)?

LFM2.5-1.2B-Thinking has the edge for agentic tasks in this comparison, averaging 34.1 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, LFM2.5-1.2B-Thinking or Ministral 3 3B (Reasoning)?

LFM2.5-1.2B-Thinking has the edge for multimodal and grounded tasks in this comparison, averaging 32.4 versus 30.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, LFM2.5-1.2B-Thinking or Ministral 3 3B (Reasoning)?

LFM2.5-1.2B-Thinking has the edge for instruction following in this comparison, averaging 72 versus 68. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, LFM2.5-1.2B-Thinking or Ministral 3 3B (Reasoning)?

LFM2.5-1.2B-Thinking has the edge for multilingual tasks in this comparison, averaging 60.7 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.