07 · Measuring Models
GSM8K
Grade School Math 8K
~8,000 grade-school math word problems, used to test step-by-step reasoning.
Concrete example
“If a train leaves at…” style problems, scored on whether the model reaches the right number.
Grade School Math 8K
~8,000 grade-school math word problems, used to test step-by-step reasoning.
“If a train leaves at…” style problems, scored on whether the model reaches the right number.