allenai/reward-bench

add pgrm

hide preview models from leaderboard

Small fix to header

Added asterisk for closed models

update paper link

Update leaderboard/md.py

Add new released models to frozen v1 scores

ignore open_instruct_dev models

rename column names

switch results repo

fix links

update dataset name and citation

Update app.py

clean looks

download button and style

Merge branch 'main' of https://huggingface.co/spaces/allenai/reward-bench-v2

updates

fix average and column names

fix average and column names

fixes

works ish

init v1 port

hard reset repo

sorry this git history is v messy

attempting to widen model column

attempting to widen model column

attempting to widen model column

attempting to widen model column

attempting to widen model column

updated domain names

updated domain names

domains

domains

add domains

reweight domains

updated domains

revert

widen display for longer names

widen display for longer names

widen display for longer names

widen display for longer names

remove ties from score

shape of weights

added 'ties' subset

fix link

links go to v2

rename split to 'test'

fix

fix

fix