Open Model Benchmarks

​How do you know if your model is actually working?

​We’re gathering builders and researchers to share the unique, weird, and highly specific ways they are testing Gemma 4 and other models.

​Whether you’re trying to get a sense for a model's vibes for a niche application or stress-testing reasoning capabilities in ways the original researchers never intended, we want to see your methodology!

​Limited spaces available, sign up today! Hosted in partnership with Kernel Labs!