Extract from Ravi Tandon’s article, “How to Select the Best AI Model for Privilege Review and Keep Costs Low.”
Nine models. A 68× cost spread. An 11-point F1 range. The benchmark data shows that spending more on a flagship model does not buy you better privilege review — it buys you a larger invoice.
When a legal team asks which AI model to use for privilege review, the answer they usually get is the name of whatever flagship model their vendor happens to support. The implicit assumption is that the best model — the most capable, the most expensive — produces the best results.
Our benchmark data says otherwise. Across nine models spanning a 68-fold cost range, the most expensive model tested scored lower than models costing 30× less. The performance ceiling is not set by the model — it is set by how the review pipeline is architected. Once that structure is right, a more capable (and more expensive) model has little left to contribute.
This post explains what the data shows, why privilege review has a distinct accuracy calculus compared to responsiveness, and how to select a model that meets your accuracy requirements without leaving money on the table.
