readable AI benchmarks (simplified)

readable AI benchmarks

Liquid AI

LFM3-VL-2B

reasoning · open weights · Oct 27, 2026

LFM3-VL-2B has a Quality Score of 6.9, ranking 282nd among 283 scored models. Per 1M tokens, pricing is $0.100 input, $0.500 output, and $0.020 cached input. It has a 128k token context window. Its Reliability Score is 12.1, ranking 282nd among 288 scored models, below average (total average: 48.2). Its Value Score is 6.3, low compared with the total Value average of 29.3.

Quality Score6.9coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score6.3
Factual reliability12.1
Cache Discount80%

Model specification

Reasoning
reasoning
Input modalities
none
Output modalities
none
Context window
128k tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$0.100
Output
$0.500
Cached Input
$0.020
Cache write
not available
Cost per task
$0.124

Capability

Intelligence
1.7
Omniscience (native net)
-75.9
Correct
8.7%
Blended price
$0.084

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 93.4%

Correct 8.7%Incorrect 84.6%Partial / not attempted 6.6%

Artificial Analysis benchmarks aa-v5

Current Intelligence Index components

AA-Briefcase v1.1
0.0 Elo
AutomationBench-AA
0.2%
private 657-task split from dataset v1.0.6
GDP.pdf
0.0%
FrontierCode v2.0
0.0%
AA Stirrup · 132 tasks, 3 attempts per task
Terminal-Bench v4.0
0.0%
AA mini-swe-agent standardized runs · 66 tasks, pass@1 averaged over 3 repeats per task
AA-Omniscience v1.1
-75.9 native net
HLE-Diamond
4.6%
CritPt v2 Hard
0.0%
AA Stirrup · hard subset, 40 of 70 problems
Terminal-Bench-Science v0.1.0
0.0%

Similar models

Support me! Patreon