SimpleBench Bulk Eval

Here we run the incredible questions from the public dataset of the Simple Bench benchmark comparing the top models and how well they perform against these questions, which are pretty obvious for most humans but tend to trip up LLMs quite badly. If anyone wants to try their hand at competing in the Jan 2025 prompt engineering contest, just duplicate any of the workflows below, save it and then add your saved workflow as another workflow to compare against (it's ok to delete the others too).