Loading video...

Video Failed to Load

Go Home

Help shape the future of Android Bench. Android Bench provides you with transparency into AI coding assistance. You now have an opportunity to contribute your own tasks, or submit locally run evaluations. Read more to learn how →

19,483 views • 14 days ago •via X (Twitter)

2 Comments

MD ADIL's profile picture
MD ADIL14 days ago

Update it with latest model, 3.8 Flash specifically.

PuneetSingh⚡️'s profile picture
PuneetSingh⚡️14 days ago

locally run evals is the useful bit. once people submit their own tasks, how do you stop the set from overfitting — versioned harness + held-out tasks?

Related Videos