For reference, Mimo-v2.5-Pro scored 19% on DeepSWE 1.1. This is looking great.

Fable scores 70%, Kimi K3 69%, Astra 74% (all on max effort).

https://deepswe.datacurve.ai/blog/deepswe-v1-1

I didn't know 2 thirds of the training data would be source code.

I absolutely love that someone is doing this! Why isn’t IBM for Granite or Google for Gemini?

If you are going to develop a near frontier model, and you don’t think you have special sauce up your sleeve, why not making training runs and RL environment scores etc. visible to the world?

I’m genuinely learning quite a bit just from the dashboard

"Slow down this much openness in AI or we won't get our trillion dollars valuations!"

Google had this GPT long go and a wise man within Google noted:

"We don't have any maot neither does anyone else."

The AI bubble burst is guaranteed and is only delayed by IPOs.

That's the kind of transparency we need! That DeepSWE benchmark puts it in frontier territory: https://artificialanalysis.ai/agents/coding-agents?coding-ag...

The Chinese labs are just making fun of the US labs at this point.

Where is the cool shit from the US labs?