GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
IFM
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
IFM
Model Tree
IFM/K2-V2-Instruct
Input Modalities
Output Modalities
Supported Functionality
| Domain | Benchmark | K2 Think V2 |
|---|---|---|
| Math | AIME 2025 | 90.42 |
| Math | HMMT 2025 | 84.79 |
| Code | SciCode | 33.00 |
| Science | GPQA-Diamond | 72.98 |
| Science | Humanity's Last Exam | 9.5 |
Aggregated across four safety dimensions (Safety-4):
K2 Think V2 establishes a robust safety baseline while effectively resolving the "alignment tax" of previous K2 Think releases. Despite strong overall safety performance, there are still opportunities to improve the model with regard to handling sensitive personal information.
| Safety Surface | Macro-Avg | Risk Level |
|---|---|---|
| Content & Public Safety | 98.20 | Low |
| Truthfulness & Reliability | 97.98 | Low |
| Societal Alignment | 97.25 | Low |
| Data & Infrastructure | 83.00 | Critical |
We have employed various techniques to reduce bias, harmful outputs, and other risks in the model. While these efforts help improve safety and reliability, the model, like all Large Language Models, may still generate inaccurate, misleading, biased, or otherwise undesirable content. By downloading, using, or interacting with this model, you acknowledge these limitations and agree to the following:
Prohibited Uses
User Responsibility
No Warranty
If you use K2 Think V2 in your research, please use the following citation:
bibtex
@misc{k2think2026k2think0126,title={K2 {T}hink {V}2: A {F}ully-{S}overeign {R}easoning {M}odel},author={K2 Think Team and Taylor W. Killian and Varad Pimpalkhute and Richard Fan and Haonan Li and Chengqian Gao and Ming Shan Hee and Xudong Han and John Maggs and Guowei He and Zhengzhong Liu and Eric P. Xing},year={2026},url={https://mbzuai.ac.ae/news/k2-think-v2-a-fully-sovereign-reasoning-model},}