LFM2 8B A1B

Liquid AI

Verified against Artificial Analysis · Jul 13, 2026

Capability

percentile index

Price /M

$0 / $0

in / out

Context

—

Avg score

17.4

10 benchmarks

AA Intelligence

1.8

index

Weights

Closed

Released

Oct 7, 2025

About

LFM2 8B A1B is a proprietary model in the LFM2 family from Liquid AI. Benchmarked on 10 evals, averaging 17.4.

Benchmark scores · 10

avg 17.4 — higher is better

MMLU-Proartificial-analysis · 2026-07

50.5

GPQA Diamondartificial-analysis · 2026-07

34.4

IFBenchartificial-analysis · 2026-07

26.3

AIMEartificial-analysis · 2026-07

25.3

LiveCodeBenchartificial-analysis · 2026-07

15.1

τ²-benchartificial-analysis · 2026-07

10.5

SciCodeartificial-analysis · 2026-07

6.8

Humanity's Last Examartificial-analysis · 2026-07

4.9

Terminal-Bench Hardartificial-analysis · 2026-07

AA Long-Context Reasoningartificial-analysis · 2026-07

Details

PublisherLiquid AI

FamilyLFM2

Parameters—

License—

WeightsClosed

ReleasedOct 7, 2025

History

full ledger →

Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers

Artificial Analysis$0/M