GPQA perf for DSV3-Base seems wrong

#15

by AChen-qaq - opened 5 days ago

5 days ago

I tested DSV3-Base on GPQA and got acc 53.1 and I noticed that there are two exact same digits on this table. Maybe this is a typo?

5 days ago

Another question is, what's the detail version of this "GPQA"? Is it gpqa-main or gpqa-diamond?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Your need to confirm your account before you can post a new comment.

· Sign up or log in to comment