Study finds inverse scaling in vision-language models on some subtasks
Across 19 models and 558,334 evaluations, 4,342 queries were answered by a smaller model and missed by a larger one.
1 stories, newest first · one card per story
Across 19 models and 558,334 evaluations, 4,342 queries were answered by a smaller model and missed by a larger one.
Today 1.6K readers · 2.4K views · 775 reads · all time 189K views