K
K2-V2 (low)
Last updated: Recently
Model Type
Text
Max Context
-
Max Output
-
Parameter Scale
-
K2 V2 low by MBZUAI Institute of Foundation Models: Text model.
Input Modality
-
Output Modality
-
Inference Speed
-
Latest Release Date
12/5/2025
SDK Ecosystem
-
artificial-analysismanufactureraa-bootstrap
Model Overview Fields
name
K2-V2 (low)
Release date
12/5/2025
Performance
-
model_creator.name
MBZUAI Institute of Foundation Models
AA Evaluation Scores
AA Intelligence Index
14.4
AA Coding Index
10.5
AA Math Index
35.3
MMLU Pro
0.713
GPQA
0.541
HLE
0.039
LiveCodeBench
0.393
SciCode
0.223
Math-500
-
AIME
-
AIME 2025
0.353
IFBench
0.41
LCR
0.19
TerminalBench Hard
0.045
TAU2
0.208
Output Speed (tokens/s)
-
TTFT (s)
-
First Answer Token (s)
-

