VetEval
Sign in
RESULTS

Comparing models

Using the comparison pages without over-reading a difference.

The comparison pages put two models side by side: index, interval, category breakdown, and the practical measures of cost and latency.

Reading a comparison

  1. Look at the intervals before the ranks. Overlapping intervals mean the two performed comparably.
  2. Look at the categories that matter for your caseload. An emergency practice cares more about triage than about communication.
  3. Look at cost and latency last, and only among models that are actually comparable on accuracy.

Questions we get asked

Was this page helpful?

Scope. VetEval measures model performance on veterinary examination items. It is not clinical advice, and no result here licenses a model for clinical use.