Z-1 vs LFM2-24B-A2B

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

Z-1 is clearly ahead on the aggregate, 47 to 38. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Z-1's sharpest advantage is in instruction following, where it averages 80 against 68. The single biggest benchmark swing on the page is MATH-500, 73 to 57.

Z-1 gives you the larger context window at 128K, compared with 32K for LFM2-24B-A2B.

Quick Verdict

Pick Z-1 if you want the stronger benchmark profile. LFM2-24B-A2B only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.

Agentic

Z-1

Z-1

42.2

LFM2-24B-A2B

33.4

39
Terminal-Bench 2.0
30
49
BrowseComp
38
41
OSWorld-Verified
34

Coding

Z-1

Z-1

26.7

LFM2-24B-A2B

18

44
HumanEval
42
33
SWE-bench Verified
18
22
LiveCodeBench
17
30
SWE-bench Pro
19

Multimodal & Grounded

Z-1

Z-1

50.5

LFM2-24B-A2B

41.7

46
MMMU-Pro
39
56
OfficeQA Pro
45

Reasoning

Z-1

Z-1

54.8

LFM2-24B-A2B

46.6

50
SimpleQA
44
48
MuSR
42
74
BBH
63
56
LongBench v2
48
57
MRCRv2
45

Knowledge

Z-1

Z-1

42.7

LFM2-24B-A2B

35.6

52
MMLU
46
51
GPQA
45
49
SuperGPQA
43
47
OpenBookQA
41
64
MMLU-Pro
51
6
HLE
4
51
FrontierScience
43

Instruction Following

Z-1

Z-1

80

LFM2-24B-A2B

68

80
IFEval
68

Multilingual

Z-1

Z-1

72.7

LFM2-24B-A2B

61.4

74
MGSM
64
72
MMLU-ProX
60

Mathematics

Z-1

Z-1

60.9

LFM2-24B-A2B

50.4

52
AIME 2023
46
54
AIME 2024
48
53
AIME 2025
47
48
HMMT Feb 2023
42
50
HMMT Feb 2024
44
49
HMMT Feb 2025
43
51
BRUMO 2025
45
73
MATH-500
57

Frequently Asked Questions

Which is better, Z-1 or LFM2-24B-A2B?

Z-1 is ahead overall, 47 to 38. The biggest single separator in this matchup is MATH-500, where the scores are 73 and 57.

Which is better for knowledge tasks, Z-1 or LFM2-24B-A2B?

Z-1 has the edge for knowledge tasks in this comparison, averaging 42.7 versus 35.6. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.

Which is better for coding, Z-1 or LFM2-24B-A2B?

Z-1 has the edge for coding in this comparison, averaging 26.7 versus 18. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.

Which is better for math, Z-1 or LFM2-24B-A2B?

Z-1 has the edge for math in this comparison, averaging 60.9 versus 50.4. Inside this category, MATH-500 is the benchmark that creates the most daylight between them.

Which is better for reasoning, Z-1 or LFM2-24B-A2B?

Z-1 has the edge for reasoning in this comparison, averaging 54.8 versus 46.6. Inside this category, MRCRv2 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Z-1 or LFM2-24B-A2B?

Z-1 has the edge for agentic tasks in this comparison, averaging 42.2 versus 33.4. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Z-1 or LFM2-24B-A2B?

Z-1 has the edge for multimodal and grounded tasks in this comparison, averaging 50.5 versus 41.7. Inside this category, OfficeQA Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, Z-1 or LFM2-24B-A2B?

Z-1 has the edge for instruction following in this comparison, averaging 80 versus 68. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, Z-1 or LFM2-24B-A2B?

Z-1 has the edge for multilingual tasks in this comparison, averaging 72.7 versus 61.4. Inside this category, MMLU-ProX 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.