GLM-5 (Reasoning) vs LFM2.5-1.2B-Instruct

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

GLM-5 (Reasoning) is clearly ahead on the aggregate, 78 to 30. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GLM-5 (Reasoning)'s sharpest advantage is in mathematics, where it averages 94.4 against 37. The single biggest benchmark swing on the page is HumanEval, 88 to 14.

GLM-5 (Reasoning) is the reasoning model in the pair, while LFM2.5-1.2B-Instruct is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. GLM-5 (Reasoning) gives you the larger context window at 200K, compared with 32K for LFM2.5-1.2B-Instruct.

Quick Verdict

Pick GLM-5 (Reasoning) if you want the stronger benchmark profile. LFM2.5-1.2B-Instruct only becomes the better choice if you would rather avoid the extra latency and token burn of a reasoning model.

Agentic

GLM-5 (Reasoning)

GLM-5 (Reasoning)

78.3

LFM2.5-1.2B-Instruct

25.7

81
Terminal-Bench 2.0
22
80
BrowseComp
31
74
OSWorld-Verified
26

Coding

GLM-5 (Reasoning)

GLM-5 (Reasoning)

62.5

LFM2.5-1.2B-Instruct

7.2

88
HumanEval
14
62
SWE-bench Verified
9
58
LiveCodeBench
8
67
SWE-bench Pro
6

Multimodal & Grounded

GLM-5 (Reasoning)

GLM-5 (Reasoning)

78.5

LFM2.5-1.2B-Instruct

32.4

74
MMMU-Pro
27
84
OfficeQA Pro
39

Reasoning

GLM-5 (Reasoning)

GLM-5 (Reasoning)

88.9

LFM2.5-1.2B-Instruct

32.1

92
SimpleQA
24
90
MuSR
22
91
BBH
59
86
LongBench v2
34
87
MRCRv2
37

Knowledge

GLM-5 (Reasoning)

GLM-5 (Reasoning)

72

LFM2.5-1.2B-Instruct

26

96
MMLU
26
94
GPQA
25
92
SuperGPQA
23
90
OpenBookQA
21
81
MMLU-Pro
50
29
HLE
1
83
FrontierScience
30

Instruction Following

GLM-5 (Reasoning)

GLM-5 (Reasoning)

92

LFM2.5-1.2B-Instruct

80

92
IFEval
80

Multilingual

GLM-5 (Reasoning)

GLM-5 (Reasoning)

86.4

LFM2.5-1.2B-Instruct

60.7

89
MGSM
62
85
MMLU-ProX
60

Mathematics

GLM-5 (Reasoning)

GLM-5 (Reasoning)

94.4

LFM2.5-1.2B-Instruct

37

98
AIME 2023
24
99
AIME 2024
26
98
AIME 2025
25
94
HMMT Feb 2023
20
96
HMMT Feb 2024
22
95
HMMT Feb 2025
21
96
BRUMO 2025
23
92
MATH-500
54

Frequently Asked Questions

Which is better, GLM-5 (Reasoning) or LFM2.5-1.2B-Instruct?

GLM-5 (Reasoning) is ahead overall, 78 to 30. The biggest single separator in this matchup is HumanEval, where the scores are 88 and 14.

Which is better for knowledge tasks, GLM-5 (Reasoning) or LFM2.5-1.2B-Instruct?

GLM-5 (Reasoning) has the edge for knowledge tasks in this comparison, averaging 72 versus 26. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, GLM-5 (Reasoning) or LFM2.5-1.2B-Instruct?

GLM-5 (Reasoning) has the edge for coding in this comparison, averaging 62.5 versus 7.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.

Which is better for math, GLM-5 (Reasoning) or LFM2.5-1.2B-Instruct?

GLM-5 (Reasoning) has the edge for math in this comparison, averaging 94.4 versus 37. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, GLM-5 (Reasoning) or LFM2.5-1.2B-Instruct?

GLM-5 (Reasoning) has the edge for reasoning in this comparison, averaging 88.9 versus 32.1. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, GLM-5 (Reasoning) or LFM2.5-1.2B-Instruct?

GLM-5 (Reasoning) has the edge for agentic tasks in this comparison, averaging 78.3 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, GLM-5 (Reasoning) or LFM2.5-1.2B-Instruct?

GLM-5 (Reasoning) has the edge for multimodal and grounded tasks in this comparison, averaging 78.5 versus 32.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, GLM-5 (Reasoning) or LFM2.5-1.2B-Instruct?

GLM-5 (Reasoning) has the edge for instruction following in this comparison, averaging 92 versus 80. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, GLM-5 (Reasoning) or LFM2.5-1.2B-Instruct?

GLM-5 (Reasoning) has the edge for multilingual tasks in this comparison, averaging 86.4 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.