Hamed Nilforoshan benchmarks OpenAI Decisions API against Jev for HiringCafe

Hamed Nilforoshan evaluated OpenAI Decisions API against Jev for HiringCafe, a platform serving 2.5 million users. The benchmark tested the models on predicting the relevance of a user query or resume to a job description on a scale of 1 to 10.

According to Nilforoshan's results, OpenAI Decisions API was twice as expensive and performed 5% to 10% worse than Jev on the relevance task.