The Cheapest Model Is Now Too Good to Ignore
For most of my work, the price gap matters more than the leaderboard.
I benchmarked my daily tasks across a few models and the pricey one won maybe a third of them.
For summarizing, tagging, and drafting, a cheap model is indistinguishable to the end user.
The leaderboard says otherwise, but the leaderboard isn't my inbox at 11pm.
I route by task now: cheap for volume, expensive for the few calls where quality shows.
Paying top dollar for a classification is the new waste, and the market is pricing that out as we speak.
