# 32.63% on ARC AGI 2 benchmark

**URL:** <https://discourse.numenta.org/t/32-63-on-arc-agi-2-benchmark/12011>\
**Category:** Tangential Theories\
**Tags:** agi\
**Created:** [August 7, 2025, 3:51pm UTC](https://discourse.numenta.org/t/32-63-on-arc-agi-2-benchmark/12011 "2025-08-07T15:51:53Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Tofara\_Moyo](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/tofara_moyo/32/3837_2.png) [@Tofara\_Moyo](https://discourse.numenta.org/u/Tofara_Moyo)\
**Post date:** [August 7, 2025, 3:51pm UTC](https://discourse.numenta.org/t/32-63-on-arc-agi-2-benchmark/12011/1 "2025-08-07T15:51:53Z")

</div>

Continuous-Time Graph Neural Networks for Abstraction and Reasoning Tasks

author:Tofara Moyo

I achieved 32.63% on Arc AGI2 dataset, state of the art with a model with 50k parameters.

code here : [https://colab.research.google.com/drive/1PeTuUeuR2uo-o8mi8toT1Fj0i75syBQs?usp=sharing](https://colab.research.google.com/drive/1e_nqoWs6JutdNiMdfjUdhN54n0d3gwot?usp=sharing)

paper here: [https://www.researchgate.net/publication/394383758\_Continuous-Time\_Graph\_Neural\_Networks\_for\_Abstraction\_and\_Reasoning\_Tasks](https://www.researchgate.net/publication/394383758_Continuous-Time_Graph_Neural_Networks_for_Abstraction_and_Reasoning_Tasks)