What is the IQ of LFM2.5 2.6B?

LFM2.5 2.6B has an estimated IQ of 84, which ranks #155 out of 159 public models on the AI IQ leaderboard. The score combines seven equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.

Is LFM2.5 2.6B open source?

Yes — LFM2.5 2.6B is an open-weights model: its trained weights are published, so it can be downloaded and self-hosted.

When was LFM2.5 2.6B released?

LFM2.5 2.6B was publicly released on August 4, 2026.

How large is the context window of LFM2.5 2.6B?

LFM2.5 2.6B supports a context window of 131,072 tokens — the amount of text it can consider in a single request.

Liquid

LFM2.5 2.6B

Public AI IQ model profile with source-backed benchmark results and derived ranking context.

IQ

84

EQ

n/a

Effective Cost

n/a

IQ Rank

#155

Release and Capabilities

Public release	2026-08-04
Modalities	text
Context window	131,072 tokens

Open weights for local deployment; a free hosted endpoint is available through OpenRouter

Publisher-reported capabilities

LFM2.5-2.6B is an on-device model post-trained for planning, tool use, and multi-step agent workflows.
It has 2.69B parameters and a 128k-token context window.

Limitations and availability caveats

Liquid AI does not recommend the model for agentic coding or knowledge-heavy tasks.
Weights use the Liquid AI LFM Open License (lfm1.0); review its commercial-use conditions.

Official release and model references

Measured Coverage and Estimates

Lfm2.5 2.6b has 7 of 39 tracked IQ benchmark inputs across 3 of 7 dimensions. Raw benchmark tables contain source-backed results only. Derived IQ combines all six dimensions using the shared scoring methodology, including estimates where direct coverage is incomplete.

Among dimensions with direct benchmark coverage, this profile's highest estimated scores are Academic Reasoning (IQ 95) and Knowledge Work (IQ 92). These dimension estimates can include statistical adjustments or predecessor priors; they are not raw benchmark percentages or claims of real-world task success.

Benchmark versions, evaluation harnesses, and coverage affect comparisons; a missing result is not a score of zero. See the scoring methodology for estimation and uncertainty limits.

IQ Dimensions

Dimension	IQ	Coverage
Abstract Reasoning	78	0/5
Mathematical Reasoning	77	0/5
Academic Reasoning	95	4/6
Programmatic Reasoning	79	0/6
Computer Use	76	0/5
Reliability	90	2/6
Knowledge Work	92	1/6

Benchmark Results

Benchmark	Score	Dimension
AA Long Context Reasoning v1.1	5.6667	Reliability
AA Omniscience	-10.95	Reliability
CritPt	0	Academic Reasoning
GDPval-AA v2.1 normalized score	0	Knowledge Work
GPQA Diamond	55.7576	Academic Reasoning
Humanity's Last Exam	6.2095	Academic Reasoning
SciCode	14.3519	Academic Reasoning

Compare

Frequently Asked Questions

What is the IQ of LFM2.5 2.6B?: LFM2.5 2.6B has an estimated IQ of 84, which ranks #155 out of 159 public models on the AI IQ leaderboard. The score combines seven equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.
Is LFM2.5 2.6B open source?: Yes — LFM2.5 2.6B is an open-weights model: its trained weights are published, so it can be downloaded and self-hosted.
When was LFM2.5 2.6B released?: LFM2.5 2.6B was publicly released on August 4, 2026.
How large is the context window of LFM2.5 2.6B?: LFM2.5 2.6B supports a context window of 131,072 tokens — the amount of text it can consider in a single request.