git
ask
hub
Privacy
Terms
Sign in with GitHub
hackingdave/modelregression
↗
Stars ·
30
Language ·
Python
Simplify and Visualize This Repo
Scan the safety of this repo
Self Host this repo
Check out more work of Developer: hackingdave
Ask anything about this repo to start.
I want to add a new test category to the ModelRegression benchmark suite. Show me how the existing test structure works and write a sample test that checks whether an AI model correctly handles async Python error handling.
I want to run the ModelRegression benchmark locally against Claude Sonnet and GPT-5. Walk me through setting up the Python orchestrator, pointing it at the models via their CLI tools, and storing results in SQLite.
The ModelRegression dashboard shows a 12% drop in the bug fixing category for one model. How do I read the evidence page to see the original prompt, the model output, and what score the judge gave?
Full explanation on explaingit →
📎
Send
By chatting or signing in you agree to the
Terms
and chat-message logging (revocable in
History
).