This commit is contained in:
Paul Gauthier 2024-03-08 08:34:07 -08:00
parent 66d3852fa0
commit f45887d176

View file

@ -11,6 +11,7 @@ highlight_image: /assets/2024-03-07-claude-3.svg
with evals showing better performance on coding tasks. with evals showing better performance on coding tasks.
With that in mind, I've been benchmarking the new models With that in mind, I've been benchmarking the new models
using Aider's code editing benchmark suite. using Aider's code editing benchmark suite.
Claude 3 Opus outperforms all of OpenAI's models, Claude 3 Opus outperforms all of OpenAI's models,
making it the best available model for pair programming with AI. making it the best available model for pair programming with AI.