BIGMODEL?RUN THE MATHS
RESEARCH · EDITORIAL CLASSIFICATION · NOT A BENCHMARK

DO I NEED THE BIG MODEL FOR…

Summarize one supplied document

Small-model jobNO — START SMALL

Closed-book summarisation rarely needs the flagship model.

START WITH
THE WORK.

  1. 01

    The work is constrained enough to evaluate cheaply.

  2. 02

    A clear schema, rubric, or example carries much of the workload.

  3. 03

    Most failures can be detected before they become expensive.

RECOMMENDED SETUPSmall, fast model + schema + deterministic checks
NON-NEGOTIABLE

Check key numbers, caveats, and quotations against the source.

REASONING2/5
AMBIGUITY2/5
ERROR COST2/5
CONTEXT3/5
CALCULATE THIS WORKLOAD →OPEN THE INTERACTIVE CHECKER →