Skip to main content
Back to Explore

K2-V2 (low)

MBZUAI·Released 2025-12-05
Compare

Benchmarks

MMLU-Pro
71.3%
GPQA Diamond
54.1%
HLE
3.9%
LiveCodeBench
39.3%
SciCode
22.3%
TerminalBench Hard
4.5%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
35.3%
IFBench
41.0%
Long Context Recall
19.0%
Tau2
20.8%
Market AverageTop Score

Quick Compare

Similar Models

OpenAI: GPT-4o (2024-05-13)

OpenAI

Q: 8.6$7.50/1M128K ctx
Coding: +13.7

Llama 3.3 Instruct 70B

Meta

Q: 8.6$0.61/1M

Gemini 2.0 Flash-Lite (Preview)

Google

Q: 8.6N/A/1M

Mistral Small 3.1

Mistral

Q: 8.6$0.14/1M
Coding: +3.4

Qwen3 32B (Non-reasoning)

Alibaba

Q: 8.6$0.26/1M

Llama 3.1 Instruct 405B

Meta

Q: 8.5$3.69/1M
Coding: +4.0
Compare all 7 models