189 paraphrased fables paired with five candidate morals test narrative understanding and cross-domain generalization.
unassessed
| Category | reasoning |
|---|---|
| Subcategory | narrative moral selection |
| Page status | active |
| Metric | multiple_choice_grade accuracy |
| Direction | higher_is_better |
| Unit | % |
| Dataset size | 189 |
| Publisher | BIG-bench collaboration |
The model reads a short fable and selects the moral that best expresses its lesson. Fables are paraphrased from Aesop-related sources with plausible distractor morals.
Five-choice multiple choice with one correct moral and four distractors.
No model card in ModelSpec reports this benchmark yet.