Moonshot v1 vs LFM2.5-1.2B-Thinking

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

Moonshot v1 is clearly ahead on the aggregate, 47 to 33. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Moonshot v1's sharpest advantage is in multimodal & grounded, where it averages 52.6 against 32.4. The single biggest benchmark swing on the page is HumanEval, 45 to 17.

LFM2.5-1.2B-Thinking is the reasoning model in the pair, while Moonshot v1 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. Moonshot v1 gives you the larger context window at 128K, compared with 32K for LFM2.5-1.2B-Thinking.

Quick Verdict

Pick Moonshot v1 if you want the stronger benchmark profile. LFM2.5-1.2B-Thinking only becomes the better choice if you want the stronger reasoning-first profile.

Agentic

Moonshot v1

Moonshot v1

42.2

LFM2.5-1.2B-Thinking

34.1

39
Terminal-Bench 2.0
34
49
BrowseComp
37
41
OSWorld-Verified
32

Coding

Moonshot v1

Moonshot v1

26.4

LFM2.5-1.2B-Thinking

8.2

45
HumanEval
17
34
SWE-bench Verified
10
21
LiveCodeBench
9
30
SWE-bench Pro
7

Multimodal & Grounded

Moonshot v1

Moonshot v1

52.6

LFM2.5-1.2B-Thinking

32.4

49
MMMU-Pro
27
57
OfficeQA Pro
39

Reasoning

Moonshot v1

Moonshot v1

55.5

LFM2.5-1.2B-Thinking

38.4

51
SimpleQA
29
49
MuSR
31
73
BBH
67
58
LongBench v2
39
56
MRCRv2
42

Knowledge

Moonshot v1

Moonshot v1

42.3

LFM2.5-1.2B-Thinking

27

53
MMLU
27
52
GPQA
26
50
SuperGPQA
24
48
OpenBookQA
22
64
MMLU-Pro
51
5
HLE
2
49
FrontierScience
31

Instruction Following

Moonshot v1

Moonshot v1

77

LFM2.5-1.2B-Thinking

72

77
IFEval
72

Multilingual

Moonshot v1

Moonshot v1

69.8

LFM2.5-1.2B-Thinking

60.7

73
MGSM
62
68
MMLU-ProX
60

Mathematics

Moonshot v1

Moonshot v1

61

LFM2.5-1.2B-Thinking

42.3

53
AIME 2023
28
55
AIME 2024
30
54
AIME 2025
29
49
HMMT Feb 2023
24
51
HMMT Feb 2024
26
50
HMMT Feb 2025
25
52
BRUMO 2025
27
72
MATH-500
61

Frequently Asked Questions

Which is better, Moonshot v1 or LFM2.5-1.2B-Thinking?

Moonshot v1 is ahead overall, 47 to 33. The biggest single separator in this matchup is HumanEval, where the scores are 45 and 17.

Which is better for knowledge tasks, Moonshot v1 or LFM2.5-1.2B-Thinking?

Moonshot v1 has the edge for knowledge tasks in this comparison, averaging 42.3 versus 27. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, Moonshot v1 or LFM2.5-1.2B-Thinking?

Moonshot v1 has the edge for coding in this comparison, averaging 26.4 versus 8.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.

Which is better for math, Moonshot v1 or LFM2.5-1.2B-Thinking?

Moonshot v1 has the edge for math in this comparison, averaging 61 versus 42.3. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, Moonshot v1 or LFM2.5-1.2B-Thinking?

Moonshot v1 has the edge for reasoning in this comparison, averaging 55.5 versus 38.4. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Moonshot v1 or LFM2.5-1.2B-Thinking?

Moonshot v1 has the edge for agentic tasks in this comparison, averaging 42.2 versus 34.1. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Moonshot v1 or LFM2.5-1.2B-Thinking?

Moonshot v1 has the edge for multimodal and grounded tasks in this comparison, averaging 52.6 versus 32.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, Moonshot v1 or LFM2.5-1.2B-Thinking?

Moonshot v1 has the edge for instruction following in this comparison, averaging 77 versus 72. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, Moonshot v1 or LFM2.5-1.2B-Thinking?

Moonshot v1 has the edge for multilingual tasks in this comparison, averaging 69.8 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.