LFM2 1.2B

Liquid AI

Verified against Artificial Analysis · Jul 13, 2026

Capability

percentile index

Price /M

$0 / $0

in / out

Context

—

Avg score

9.7

10 benchmarks

AA Intelligence

1.1

index

Weights

Closed

Released

Jul 10, 2025

About

LFM2 1.2B is a proprietary model in the LFM2 family from Liquid AI. Benchmarked on 10 evals, averaging 9.7.

Benchmark scores · 10

avg 9.7 — higher is better

MMLU-Proartificial-analysis · 2026-07

25.7

GPQA Diamondartificial-analysis · 2026-07

22.8

IFBenchartificial-analysis · 2026-07

τ²-benchartificial-analysis · 2026-07

12.6

Humanity's Last Examartificial-analysis · 2026-07

5.7

AIMEartificial-analysis · 2026-07

3.3

SciCodeartificial-analysis · 2026-07

2.5

LiveCodeBenchartificial-analysis · 2026-07

Terminal-Bench Hardartificial-analysis · 2026-07

AA Long-Context Reasoningartificial-analysis · 2026-07

Details

PublisherLiquid AI

FamilyLFM2

Parameters—

License—

WeightsClosed

ReleasedJul 10, 2025

History

full ledger →

Capability over time

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

API providers

Artificial Analysis$0/M