readable AI benchmarks

Liquid AI

LFM2.5-1.2B-Thinking

reasoning · open weights · Jan 20, 2026

Quality Score3.2
Value Scorenot available
Reliability10.0
Cache Discountnot available

Model specification

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

Token prices USD per 1M tokens

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

Capability

Intelligence
2.3
Coding
not available
Agentic
not available
Omniscience
-80.0
Correct
7.4%
Blended price
not available

Answer outcomes

Correct 7.4%Incorrect 87.4%Abstained 5.2%

Artificial Analysis benchmarks

SciCode
4%
Humanity’s Last Exam
6%
GPQA Diamond
34%
CritPt
0%
AA-Omniscience
10%
AA-LCR
0%

Similar models