readable AI benchmarks

MBZUAI Institute of Foundation Models

K2-V2 (medium)

reasoning · open weights · Dec 5, 2025

Quality Score14.1
Value Scorenot available
Reliability25.5
Cache Discountnot available

Model specification

Reasoning
reasoning
Input modalities
text
Output modalities
text
Context window
512k 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
12.4
Coding
not available
Agentic
not available
Omniscience
-49.0
Correct
17.9%
Blended price
not available

Answer outcomes

Correct 17.9%Incorrect 66.9%Abstained 15.1%

Artificial Analysis benchmarks

SciCode
25%
Humanity’s Last Exam
4%
GPQA Diamond
60%
CritPt
0%
AA-Omniscience
26%
AA-LCR
28%

Similar models