EXTRACTION · EDITORIAL CLASSIFICATION · NOT A BENCHMARK
DO I NEED THE BIG MODEL FOR…
Tag customer feedback by sentiment
Small-model jobNO — START SMALL
“A frontier model will not rescue a vague taxonomy.”
WHY THIS VERDICTSTART WITH
START WITH
THE WORK.
- 01
The work is constrained enough to evaluate cheaply.
- 02
A clear schema, rubric, or example carries much of the workload.
- 03
Most failures can be detected before they become expensive.
RECOMMENDED SETUPSmall, fast model + schema + deterministic checks
NON-NEGOTIABLE
Define edge cases and test sarcasm and mixed sentiment separately.
REASONING1/5
AMBIGUITY2/5
ERROR COST1/5
CONTEXT1/5