Datasets
Run Experiments
Re-generate a dataset with a new prompt or a new model and compare the results side-by-side
One of the experiments AI teams find themselves running often is comparing the responses from different models or different prompts on the same dataset.
In Athina, you can run an experiment to compare the responses from different models or prompts side-by-side in a few clicks.
After this, you can:
- Compare the responses from different models or prompts side-by-side.
- Run evaluations on all datasets simultaneously.
- Download the results as a JSON, or Excel file.