Reactions from ranked influencers
2 posts
We're working on an exciting new way to write evals. DM Jacky if you'd like to try it out!
running openrouter evals to determine the best model for my exact use case surprising results minimax m3 wins out! never would have been on my list if it weren't for the model bakeoff eval always. run. model. evals.
We're working on an exciting new way to write evals. DM Jacky if you'd like to try it out!
running openrouter evals to determine the best model for my exact use case surprising results minimax m3 wins out! never would have been on my list if it weren't for the model bakeoff eval always. run. model. evals.