o1 vs LFM2.5-1.2B-Thinking

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

o1 is clearly ahead on the aggregate, 68 to 33. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

o1's sharpest advantage is in knowledge, where it averages 69.6 against 27. The single biggest benchmark swing on the page is MMLU, 91.8 to 27.

o1 is also the more expensive model on tokens at $15.00 input / $60.00 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. o1 gives you the larger context window at 200K, compared with 32K for LFM2.5-1.2B-Thinking.

Quick Verdict

Pick o1 if you want the stronger benchmark profile. LFM2.5-1.2B-Thinking only becomes the better choice if you want the cheaper token bill.

Agentic

o1

o1

65.4

LFM2.5-1.2B-Thinking

34.1

66
Terminal-Bench 2.0
34
72
BrowseComp
37
60
OSWorld-Verified
32

Coding

o1

o1

48.4

LFM2.5-1.2B-Thinking

8.2

41
SWE-bench Verified
10
50
SWE-bench Pro
7
Coming soon
HumanEval
17
Coming soon
LiveCodeBench
9

Multimodal & Grounded

o1

o1

70.7

LFM2.5-1.2B-Thinking

32.4

68
MMMU-Pro
27
74
OfficeQA Pro
39

Reasoning

o1

o1

78.1

LFM2.5-1.2B-Thinking

38.4

79
LongBench v2
39
77
MRCRv2
42
Coming soon
SimpleQA
29
Coming soon
MuSR
31
Coming soon
BBH
67

Knowledge

o1

o1

69.6

LFM2.5-1.2B-Thinking

27

91.8
MMLU
27
75.7
GPQA
26
65
FrontierScience
31
Coming soon
SuperGPQA
24
Coming soon
OpenBookQA
22
Coming soon
MMLU-Pro
51
Coming soon
HLE
2

Instruction Following

o1

o1

92.2

LFM2.5-1.2B-Thinking

72

92.2
IFEval
72

Multilingual

o1

o1

77

LFM2.5-1.2B-Thinking

60.7

77
MMLU-ProX
60
Coming soon
MGSM
62

Mathematics

o1

o1

74.3

LFM2.5-1.2B-Thinking

42.3

74.3
AIME 2024
30
Coming soon
AIME 2023
28
Coming soon
AIME 2025
29
Coming soon
HMMT Feb 2023
24
Coming soon
HMMT Feb 2024
26
Coming soon
HMMT Feb 2025
25
Coming soon
BRUMO 2025
27
Coming soon
MATH-500
61

Frequently Asked Questions

Which is better, o1 or LFM2.5-1.2B-Thinking?

o1 is ahead overall, 68 to 33. The biggest single separator in this matchup is MMLU, where the scores are 91.8 and 27.

Which is better for knowledge tasks, o1 or LFM2.5-1.2B-Thinking?

o1 has the edge for knowledge tasks in this comparison, averaging 69.6 versus 27. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, o1 or LFM2.5-1.2B-Thinking?

o1 has the edge for coding in this comparison, averaging 48.4 versus 8.2. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.

Which is better for math, o1 or LFM2.5-1.2B-Thinking?

o1 has the edge for math in this comparison, averaging 74.3 versus 42.3. Inside this category, AIME 2024 is the benchmark that creates the most daylight between them.

Which is better for reasoning, o1 or LFM2.5-1.2B-Thinking?

o1 has the edge for reasoning in this comparison, averaging 78.1 versus 38.4. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, o1 or LFM2.5-1.2B-Thinking?

o1 has the edge for agentic tasks in this comparison, averaging 65.4 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, o1 or LFM2.5-1.2B-Thinking?

o1 has the edge for multimodal and grounded tasks in this comparison, averaging 70.7 versus 32.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, o1 or LFM2.5-1.2B-Thinking?

o1 has the edge for instruction following in this comparison, averaging 92.2 versus 72. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, o1 or LFM2.5-1.2B-Thinking?

o1 has the edge for multilingual tasks in this comparison, averaging 77 versus 60.7. Inside this category, MMLU-ProX 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.