LFM2.5-1.2B-Instruct Benchmark Scores & Performance

Benchmark analysis of LFM2.5-1.2B-Instruct by LiquidAI across 32 sourced tests on BenchLM.

According to BenchLM.ai, LFM2.5-1.2B-Instruct ranks #120 out of 123 models with an overall score of 30/100. While not a frontier model, it offers specific advantages depending on the use case.

LFM2.5-1.2B-Instruct is a proprietary model with a 32K token context window. It processes queries without explicit chain-of-thought reasoning, offering faster response times and lower token usage.

LFM2.5-1.2B-Instruct sits inside the LFM2.5 1.2B family alongside LFM2.5-1.2B-Thinking.

Its strongest category is Instruction Following (#75), while its weakest is Coding (#120). This performance profile makes it a well-rounded choice across a range of tasks.

Creator

LiquidAI

Source Type

Proprietary

Reasoning

Non-Reasoning

Context Window

32K

Overall Score

30#120 of 123

Arena Elo

1033

Family & Lineage

Family

LFM2.5 1.2B

Instruct

Knowledge Benchmarks

MMLU
26
GPQA
25
SuperGPQA
23
OpenBookQA
21
MMLU-Pro
50
HLE
1
FrontierScience
30

Coding Benchmarks

HumanEval
14
SWE-bench Verified
9
LiveCodeBench
8
SWE-bench Pro
6

Mathematics Benchmarks

AIME 2023
24
AIME 2024
26
AIME 2025
25
HMMT Feb 2023
20
HMMT Feb 2024
22
HMMT Feb 2025
21
BRUMO 2025
23
MATH-500
54

Reasoning Benchmarks

SimpleQA
24
MuSR
22
BBH
59
LongBench v2
34
MRCRv2
37

Agentic Benchmarks

Terminal-Bench 2.0
22
BrowseComp
31
OSWorld-Verified
26

Multimodal & Grounded Benchmarks

MMMU-Pro
27
OfficeQA Pro
39

Instruction Following Benchmarks

IFEval
80

Multilingual Benchmarks

MGSM
62
MMLU-ProX
60

Frequently Asked Questions

How does LFM2.5-1.2B-Instruct perform overall in AI benchmarks?

LFM2.5-1.2B-Instruct ranks #120 out of 123 models with an overall score of 30. It is created by LiquidAI and features a 32K context window.

Is LFM2.5-1.2B-Instruct good for knowledge and understanding?

LFM2.5-1.2B-Instruct ranks #119 out of 123 models in knowledge and understanding benchmarks with an average score of 26. There are stronger options in this category.

Is LFM2.5-1.2B-Instruct good for coding and programming?

LFM2.5-1.2B-Instruct ranks #120 out of 123 models in coding and programming benchmarks with an average score of 7.2. There are stronger options in this category.

Is LFM2.5-1.2B-Instruct good for mathematics?

LFM2.5-1.2B-Instruct ranks #113 out of 123 models in mathematics benchmarks with an average score of 37. There are stronger options in this category.

Is LFM2.5-1.2B-Instruct good for reasoning and logic?

LFM2.5-1.2B-Instruct ranks #119 out of 123 models in reasoning and logic benchmarks with an average score of 32.1. There are stronger options in this category.

Is LFM2.5-1.2B-Instruct good for agentic tool use and computer tasks?

LFM2.5-1.2B-Instruct ranks #120 out of 123 models in agentic tool use and computer tasks benchmarks with an average score of 25.7. There are stronger options in this category.

Is LFM2.5-1.2B-Instruct good for multimodal and grounded tasks?

LFM2.5-1.2B-Instruct ranks #118 out of 123 models in multimodal and grounded tasks benchmarks with an average score of 32.4. There are stronger options in this category.

Is LFM2.5-1.2B-Instruct good for instruction following?

LFM2.5-1.2B-Instruct ranks #75 out of 123 models in instruction following benchmarks with an average score of 80. There are stronger options in this category.

Is LFM2.5-1.2B-Instruct good for multilingual tasks?

LFM2.5-1.2B-Instruct ranks #99 out of 123 models in multilingual tasks benchmarks with an average score of 60.7. There are stronger options in this category.

Which sibling models are related to LFM2.5-1.2B-Instruct?

LFM2.5-1.2B-Instruct belongs to the LFM2.5 1.2B family. Related variants on BenchLM include LFM2.5-1.2B-Thinking.

What is the context window size of LFM2.5-1.2B-Instruct?

LFM2.5-1.2B-Instruct has a context window of 32K, which determines how much text it can process in a single interaction.

Last updated: March 12, 2026

Weekly LLM Updates

New model releases, benchmark scores, and leaderboard changes. Every Friday.

Free. Your signup is stored with a derived country code for compliance routing.