Claude Haiku 4.5 vs LFM2.5-1.2B-Thinking

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

Claude Haiku 4.5 is clearly ahead on the aggregate, 62 to 33. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Claude Haiku 4.5's sharpest advantage is in multimodal & grounded, where it averages 78.4 against 32.4. The single biggest benchmark swing on the page is MMMU-Pro, 82 to 27.

Claude Haiku 4.5 is also the more expensive model on tokens at $0.80 input / $4.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for LFM2.5-1.2B-Thinking. That is roughly Infinityx on output cost alone. LFM2.5-1.2B-Thinking is the reasoning model in the pair, while Claude Haiku 4.5 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. Claude Haiku 4.5 gives you the larger context window at 200K, compared with 32K for LFM2.5-1.2B-Thinking.

Quick Verdict

Pick Claude Haiku 4.5 if you want the stronger benchmark profile. LFM2.5-1.2B-Thinking only becomes the better choice if you want the cheaper token bill or you want the stronger reasoning-first profile.

Agentic

Claude Haiku 4.5

Claude Haiku 4.5

56.7

LFM2.5-1.2B-Thinking

34.1

53
Terminal-Bench 2.0
34
62
BrowseComp
37
57
OSWorld-Verified
32

Coding

Claude Haiku 4.5

Claude Haiku 4.5

41.7

LFM2.5-1.2B-Thinking

8.2

60
HumanEval
17
48
SWE-bench Verified
10
36
LiveCodeBench
9
46
SWE-bench Pro
7

Multimodal & Grounded

Claude Haiku 4.5

Claude Haiku 4.5

78.4

LFM2.5-1.2B-Thinking

32.4

82
MMMU-Pro
27
74
OfficeQA Pro
39

Reasoning

Claude Haiku 4.5

Claude Haiku 4.5

68.9

LFM2.5-1.2B-Thinking

38.4

65
SimpleQA
29
63
MuSR
31
81
BBH
67
72
LongBench v2
39
70
MRCRv2
42

Knowledge

Claude Haiku 4.5

Claude Haiku 4.5

53.6

LFM2.5-1.2B-Thinking

27

68
MMLU
27
67
GPQA
26
65
SuperGPQA
24
63
OpenBookQA
22
73
MMLU-Pro
51
11
HLE
2
64
FrontierScience
31

Instruction Following

Claude Haiku 4.5

Claude Haiku 4.5

86

LFM2.5-1.2B-Thinking

72

86
IFEval
72

Multilingual

Claude Haiku 4.5

Claude Haiku 4.5

80.1

LFM2.5-1.2B-Thinking

60.7

82
MGSM
62
79
MMLU-ProX
60

Mathematics

Claude Haiku 4.5

Claude Haiku 4.5

73.3

LFM2.5-1.2B-Thinking

42.3

68
AIME 2023
28
70
AIME 2024
30
69
AIME 2025
29
64
HMMT Feb 2023
24
66
HMMT Feb 2024
26
65
HMMT Feb 2025
25
67
BRUMO 2025
27
81
MATH-500
61

Frequently Asked Questions

Which is better, Claude Haiku 4.5 or LFM2.5-1.2B-Thinking?

Claude Haiku 4.5 is ahead overall, 62 to 33. The biggest single separator in this matchup is MMMU-Pro, where the scores are 82 and 27.

Which is better for knowledge tasks, Claude Haiku 4.5 or LFM2.5-1.2B-Thinking?

Claude Haiku 4.5 has the edge for knowledge tasks in this comparison, averaging 53.6 versus 27. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, Claude Haiku 4.5 or LFM2.5-1.2B-Thinking?

Claude Haiku 4.5 has the edge for coding in this comparison, averaging 41.7 versus 8.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.

Which is better for math, Claude Haiku 4.5 or LFM2.5-1.2B-Thinking?

Claude Haiku 4.5 has the edge for math in this comparison, averaging 73.3 versus 42.3. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, Claude Haiku 4.5 or LFM2.5-1.2B-Thinking?

Claude Haiku 4.5 has the edge for reasoning in this comparison, averaging 68.9 versus 38.4. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Claude Haiku 4.5 or LFM2.5-1.2B-Thinking?

Claude Haiku 4.5 has the edge for agentic tasks in this comparison, averaging 56.7 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, Claude Haiku 4.5 or LFM2.5-1.2B-Thinking?

Claude Haiku 4.5 has the edge for multimodal and grounded tasks in this comparison, averaging 78.4 versus 32.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, Claude Haiku 4.5 or LFM2.5-1.2B-Thinking?

Claude Haiku 4.5 has the edge for instruction following in this comparison, averaging 86 versus 72. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, Claude Haiku 4.5 or LFM2.5-1.2B-Thinking?

Claude Haiku 4.5 has the edge for multilingual tasks in this comparison, averaging 80.1 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.