readable AI benchmarks

Liquid AI

LFM2.5-8B-A1B

reasoning · open weights · May 28, 2026

Quality Score10.4
Value Score10.7
Reliability33.4
Cache Discountnot available

Model specification

Reasoning
reasoning
Input modalities
text
Output modalities
text
Context window
32,768 tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$0.0000
Output
$0.0000
Cached Input
not available
Cached Output
not available
Cost per task
not available

Capability

Intelligence
8.1
Coding
not available
Agentic
not available
Omniscience
-33.2
Correct
9.3%
Blended price
$0.0000

Answer outcomes

Correct 9.3%Incorrect 42.5%Abstained 48.1%

Artificial Analysis benchmarks

SciCode
8%
Humanity’s Last Exam
7%
GPQA Diamond
51%
CritPt
0%
AA-Omniscience
33%
AA-LCR
0%

Similar models