Remix.run Logo
LLM-test-kit – Test consistency, latency, cost and behavior of LLM apps(github.com)
1 points by muskanjo 2 days ago | 2 comments
muskanjo 2 days ago | parent | next [-]

I'm the author. Happy to answer questions about the methodology or how the consistency scoring works. Would love feedback on what tests would be most useful to add.

muskanjo 2 days ago | parent | prev [-]

[flagged]