Kimi K2.5 vs LFM2-24B-A2B

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

Kimi K2.5 is clearly ahead on the aggregate, 60 to 38. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Kimi K2.5's sharpest advantage is in mathematics, where it averages 78.7 against 50.4. The single biggest benchmark swing on the page is MMLU, 77 to 46.

Kimi K2.5 is also the more expensive model on tokens at $0.50 input / $2.80 output per 1M tokens, versus $0.03 input / $0.12 output per 1M tokens for LFM2-24B-A2B. That is roughly 23.3x on output cost alone. Kimi K2.5 gives you the larger context window at 128K, compared with 32K for LFM2-24B-A2B.

Quick Verdict

Pick Kimi K2.5 if you want the stronger benchmark profile. LFM2-24B-A2B only becomes the better choice if you want the cheaper token bill.

Agentic

Kimi K2.5

Kimi K2.5

52.3

LFM2-24B-A2B

33.4

51
Terminal-Bench 2.0
30
59
BrowseComp
38
49
OSWorld-Verified
34

Coding

Kimi K2.5

Kimi K2.5

38.9

LFM2-24B-A2B

18

69
HumanEval
42
42
SWE-bench Verified
18
37
LiveCodeBench
17
40
SWE-bench Pro
19

Multimodal & Grounded

Kimi K2.5

Kimi K2.5

64.6

LFM2-24B-A2B

41.7

61
MMMU-Pro
39
69
OfficeQA Pro
45

Reasoning

Kimi K2.5

Kimi K2.5

71.7

LFM2-24B-A2B

46.6

74
SimpleQA
44
72
MuSR
42
81
BBH
63
67
LongBench v2
48
70
MRCRv2
45

Knowledge

Kimi K2.5

Kimi K2.5

57.2

LFM2-24B-A2B

35.6

77
MMLU
46
76
GPQA
45
74
SuperGPQA
43
72
OpenBookQA
41
74
MMLU-Pro
51
11
HLE
4
67
FrontierScience
43

Instruction Following

Kimi K2.5

Kimi K2.5

85

LFM2-24B-A2B

68

85
IFEval
68

Multilingual

Kimi K2.5

Kimi K2.5

79.8

LFM2-24B-A2B

61.4

83
MGSM
64
78
MMLU-ProX
60

Mathematics

Kimi K2.5

Kimi K2.5

78.7

LFM2-24B-A2B

50.4

77
AIME 2023
46
79
AIME 2024
48
78
AIME 2025
47
73
HMMT Feb 2023
42
75
HMMT Feb 2024
44
74
HMMT Feb 2025
43
76
BRUMO 2025
45
82
MATH-500
57

Frequently Asked Questions

Which is better, Kimi K2.5 or LFM2-24B-A2B?

Kimi K2.5 is ahead overall, 60 to 38. The biggest single separator in this matchup is MMLU, where the scores are 77 and 46.

Which is better for knowledge tasks, Kimi K2.5 or LFM2-24B-A2B?

Kimi K2.5 has the edge for knowledge tasks in this comparison, averaging 57.2 versus 35.6. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, Kimi K2.5 or LFM2-24B-A2B?

Kimi K2.5 has the edge for coding in this comparison, averaging 38.9 versus 18. Inside this category, HumanEval is the benchmark that creates the most daylight between them.

Which is better for math, Kimi K2.5 or LFM2-24B-A2B?

Kimi K2.5 has the edge for math in this comparison, averaging 78.7 versus 50.4. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, Kimi K2.5 or LFM2-24B-A2B?

Kimi K2.5 has the edge for reasoning in this comparison, averaging 71.7 versus 46.6. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Kimi K2.5 or LFM2-24B-A2B?

Kimi K2.5 has the edge for agentic tasks in this comparison, averaging 52.3 versus 33.4. 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, Kimi K2.5 or LFM2-24B-A2B?

Kimi K2.5 has the edge for multimodal and grounded tasks in this comparison, averaging 64.6 versus 41.7. Inside this category, OfficeQA Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, Kimi K2.5 or LFM2-24B-A2B?

Kimi K2.5 has the edge for instruction following in this comparison, averaging 85 versus 68. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, Kimi K2.5 or LFM2-24B-A2B?

Kimi K2.5 has the edge for multilingual tasks in this comparison, averaging 79.8 versus 61.4. 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.