readable AI benchmarks

Liquid AI

LFM2.5-2.6B

reasoning · open weights · Aug 4, 2026

Quality Score11.4
Value Score11.8
Reliability44.5
Cache Discountnot available

Model specification

Reasoning
reasoning
Input modalities
text
Output modalities
text
Context window
128k 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
$0.0000

Capability

Intelligence
11.0
Coding
7.7
Agentic
2.4
Omniscience
-10.9
Correct
4.3%
Blended price
$0.0000

Answer outcomes

Correct 4.3%Incorrect 15.3%Abstained 80.4%

Artificial Analysis benchmarks

GDPval-AA v2
0%
τ³-Banking
7%
Terminal-Bench v2.1
4%
SciCode
14%
Humanity’s Last Exam
6%
GPQA Diamond
56%
CritPt
0%
AA-Omniscience
45%
AA-LCR
5%

Similar models