Models

K2-V2 (low)

K2-V2 (low) is a lightweight variant of the K2-V2 model from MBZUAI, optimized for faster inference and lower computational cost. It is designed to provide efficient performance for general-purpose language tasks while maintaining the core capabilities of the K2 series.

FastCheapReasoning
Input / 1M tokens
$0.00
Output / 1M tokens
$0.00
Supported plans
0

Benchmark history

Evaluations

12

TAU2

Measured Jul 10, 2026Source

Score

0.21

Terminalbench Hard

Measured Jul 10, 2026Source

Score

0.05

Lcr

Measured Jul 10, 2026Source

Score

0.19

Ifbench

Measured Jul 10, 2026Source

Score

0.41

Aime 25

Measured Jul 10, 2026Source

Score

0.35

Scicode

Measured Jul 10, 2026Source

Score

0.22

Livecodebench

Measured Jul 10, 2026Source

Score

0.39

Hle

Measured Jul 10, 2026Source

Score

0.04

Gpqa

Measured Jul 10, 2026Source

Score

0.54

Mmlu Pro

Measured Jul 10, 2026Source

Score

0.71

Artificial Analysis Math Index

Measured Jul 10, 2026Source

Score

35.3

Artificial Analysis Intelligence Index

Measured Jul 10, 2026Source

Score

8.6

Plan availability

Products and plans that support this model

0
No products or plans have been linked to this model yet.

User ratings

Loading ratings...

Discussion

Thinking... Make sure you are connected to GitHub server