K2-V2 (medium)

MBZUAI Institute of Foundation Models

ReasoningApache 2.0

Analysis of MBZUAI Institute of Foundation Models's K2-V2 (medium) and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more.

Context

Release Date: Dec 05, 2025
Window: 512k

PricingPer 1M tokens

Input: $
Output: $
Blended 3:1: $

Capabilities

Input
Output
Reasoning tokens

Benchmarks

Reasoning: ●○○○○
Math: ●●●○○
Coding: ●○○○○
MMLU Pro: 76.1%
GPQA: 59.8%
HLE: 4.4%
SciCode: 25.2%
AIME: 64.7%
LiveCodeBench: 54.1%

Analysis of MBZUAI Institute of Foundation Models's K2-V2 (medium) and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more.