Qwen3.5 397B vs LFM2.5-1.2B-Instruct

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

Qwen3.5 397B is clearly ahead on the aggregate, 62 to 30. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Qwen3.5 397B's sharpest advantage is in mathematics, where it averages 81.6 against 37. The single biggest benchmark swing on the page is HumanEval, 75 to 14.

Qwen3.5 397B gives you the larger context window at 128K, compared with 32K for LFM2.5-1.2B-Instruct.

Quick Verdict

Pick Qwen3.5 397B 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

Qwen3.5 397B

Qwen3.5 397B

56.9

LFM2.5-1.2B-Instruct

25.7

58
Terminal-Bench 2.0
22
62
BrowseComp
31
52
OSWorld-Verified
26

Coding

Qwen3.5 397B

Qwen3.5 397B

40.7

LFM2.5-1.2B-Instruct

7.2

75
HumanEval
14
42
SWE-bench Verified
9
39
LiveCodeBench
8
42
SWE-bench Pro
6

Multimodal & Grounded

Qwen3.5 397B

Qwen3.5 397B

61.4

LFM2.5-1.2B-Instruct

32.4

56
MMMU-Pro
27
68
OfficeQA Pro
39

Reasoning

Qwen3.5 397B

Qwen3.5 397B

75.9

LFM2.5-1.2B-Instruct

32.1

80
SimpleQA
24
78
MuSR
22
82
BBH
59
72
LongBench v2
34
71
MRCRv2
37

Knowledge

Qwen3.5 397B

Qwen3.5 397B

59.3

LFM2.5-1.2B-Instruct

26

83
MMLU
26
82
GPQA
25
80
SuperGPQA
23
78
OpenBookQA
21
73
MMLU-Pro
50
10
HLE
1
71
FrontierScience
30

Instruction Following

Qwen3.5 397B

Qwen3.5 397B

82

LFM2.5-1.2B-Instruct

80

82
IFEval
80

Multilingual

Qwen3.5 397B

Qwen3.5 397B

78.8

LFM2.5-1.2B-Instruct

60.7

82
MGSM
62
77
MMLU-ProX
60

Mathematics

Qwen3.5 397B

Qwen3.5 397B

81.6

LFM2.5-1.2B-Instruct

37

83
AIME 2023
24
85
AIME 2024
26
84
AIME 2025
25
79
HMMT Feb 2023
20
81
HMMT Feb 2024
22
80
HMMT Feb 2025
21
82
BRUMO 2025
23
81
MATH-500
54

Frequently Asked Questions

Which is better, Qwen3.5 397B or LFM2.5-1.2B-Instruct?

Qwen3.5 397B is ahead overall, 62 to 30. The biggest single separator in this matchup is HumanEval, where the scores are 75 and 14.

Which is better for knowledge tasks, Qwen3.5 397B or LFM2.5-1.2B-Instruct?

Qwen3.5 397B has the edge for knowledge tasks in this comparison, averaging 59.3 versus 26. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, Qwen3.5 397B or LFM2.5-1.2B-Instruct?

Qwen3.5 397B has the edge for coding in this comparison, averaging 40.7 versus 7.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.

Which is better for math, Qwen3.5 397B or LFM2.5-1.2B-Instruct?

Qwen3.5 397B has the edge for math in this comparison, averaging 81.6 versus 37. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, Qwen3.5 397B or LFM2.5-1.2B-Instruct?

Qwen3.5 397B has the edge for reasoning in this comparison, averaging 75.9 versus 32.1. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Qwen3.5 397B or LFM2.5-1.2B-Instruct?

Qwen3.5 397B has the edge for agentic tasks in this comparison, averaging 56.9 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, Qwen3.5 397B or LFM2.5-1.2B-Instruct?

Qwen3.5 397B has the edge for multimodal and grounded tasks in this comparison, averaging 61.4 versus 32.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, Qwen3.5 397B or LFM2.5-1.2B-Instruct?

Qwen3.5 397B has the edge for instruction following in this comparison, averaging 82 versus 80. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, Qwen3.5 397B or LFM2.5-1.2B-Instruct?

Qwen3.5 397B has the edge for multilingual tasks in this comparison, averaging 78.8 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.