gaia-benchmark/leaderboard

Pin Space Gradio SDK version

Fix Space startup and reduce restart churn

Pin gradio to 5.49 and cap leaderboard to top 100 rows (#99)

Drop trust_remote_code=True from load_dataset calls (#98)

Update app.py

Update app.py

Update content.py

Update app.py

added a display of errors for users

rm space debug

reordered file saving step + added new catch

anti spam measures

Update README.md

fix none parsing in answers

added deduplication system, commented for now

gitignore

added debug mode locally, fixed a couple typos

added rate limit

Update README.md

now forces login

fix

new check on file len

fix typo

forbid duplicates

fix num question count

Update content.py

push validation to public dataset

Update app.py

Update app.py

date

Update content.py

Update app.py

Update content.py

Update app.py (#18)

Update README.md

Update app.py

Update requirements.txt

Update app.py

Update content.py

Update README.md

test at the forefront

push privacy fix

`this space` => `this dataset` (#2)

update citation

Added paper link

Added better test messages for failures

ix color

update gradio version

text reorg

text reorg