LFM 40B

Liquid AI

Verified against Artificial Analysis · Jul 13, 2026

Capability

percentile index

Price /M

$0 / $0

in / out

Context

—

Avg score

24.1

6 benchmarks

AA Intelligence

3.4

index

Weights

Closed

Released

Sep 30, 2024

About

LFM 40B is a proprietary model in the LFM family from Liquid AI. Benchmarked on 6 evals, averaging 24.1.

Benchmark scores · 6

avg 24.1 — higher is better

MATHartificial-analysis · 2026-07

MMLU-Proartificial-analysis · 2026-07

42.5

GPQA Diamondartificial-analysis · 2026-07

32.7

LiveCodeBenchartificial-analysis · 2026-07

9.6

SciCodeartificial-analysis · 2026-07

7.1

Humanity's Last Examartificial-analysis · 2026-07

4.9

Details

FamilyLFM

Parameters—

License—

WeightsClosed

ReleasedSep 30, 2024

History

Capability over time

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

API providers

Artificial Analysis$0/M