Spaces:

gujilab
/

chinese-classical-bench-leaderboard

Running

App Files Files Community

chinese-classical-bench-leaderboard / results

Commit History

sync: judge-primary methodology + 6 tasks + canonicity/transparency (repo v1.8 parity)

18d4517
verified

gujilab commited on May 18

data: refresh after idiom-source rescore

64e5020
verified

gujilab commited on May 13

data: refresh after idiom-source rescore

9c24a38
verified

gujilab commited on May 13

data: refresh after idiom-source rescore

5d10066
verified

gujilab commited on May 13

data: refresh after idiom-source rescore

e6c0724
verified

gujilab commited on May 13

data: refresh after idiom-source rescore

384e57e
verified

gujilab commited on May 13

data: refresh after idiom-source rescore

0d15b46
verified

gujilab commited on May 13

data: refresh after idiom-source rescore

2b94986
verified

gujilab commited on May 13

init: Gradio leaderboard (10 models, 5 tasks)

17eaa80
verified

Zion L commited on May 13