Comment by westurner

(Unbelievable that I need to justify this at -4!)

Is the performance or accuracy on this better on FrontierMath or Multi-SWE-bench, given the training in 1,000 languages?

I just read in the Colab release notes that models uploaded to HuggingFace can be opened on Colab with "Open in colab" on HuggingFace