Spaces:

Jellyfish042
/

UncheatableEval

Running

App Files Files Community

UncheatableEval

Commit History

show > 40B models

6691fdd

Running

Jellyfish042 commited on 3 days ago

update

7a8d7e9

Jellyfish042 commited on 3 days ago

update

4d69e46

Jellyfish042 commited on 3 days ago

update

150a414

Jellyfish042 commited on 3 days ago

update

ba5ff9c

Jellyfish042 commited on 8 days ago

update

c722fee

Jellyfish042 commited on 8 days ago

update Trinity evaluation data for January 2026 models

fea85a6

Jellyfish042 commited on 11 days ago

update

3a1af8b

Jellyfish042 commited on 19 days ago

update

75e2ac5

Jellyfish042 commited on 19 days ago

update

f0ad847

Jellyfish042 commited on 19 days ago

update

5be0f31

Jellyfish042 commited on 21 days ago

update

1be7b2f

Jellyfish042 commited on 29 days ago

update

c1b1328

Jellyfish042 commited on Jan 18

fix: ensure initial scaling plot uses Pareto frontier by default

d966e65

Jellyfish042 commited on Jan 17

chore: set Pareto Frontier as default fitting method

4904727

Jellyfish042 commited on Jan 17

Merge feature/pareto-frontier into main

6d95996

Jellyfish042 commited on Jan 17

feat: add Pareto frontier fitting option for scaling law

243791d

Jellyfish042 commited on Jan 17

Merge branch 'feature/power-law-with-offset' into main

0836fe4

Jellyfish042 commited on Jan 17

feat: replace linear scaling law with power law with offset

6725455

Jellyfish042 commited on Jan 17

update

dc25c5e

Jellyfish042 commited on Jan 17

2026-01 update

6f67891

Jellyfish042 commited on Jan 17

2026-01 update

6a5b21f

Jellyfish042 commited on Jan 17

upgrade

ff57e83

Jellyfish042 commited on Jan 16

chore: relax pandas version to avoid source compilation timeout

2d605d1

Jellyfish042 commited on Jan 16

2026-01 update

a607ab6

Jellyfish042 commited on Jan 16

update

152f08f

Jellyfish042 commited on Jan 10

update

a88a94e

Jellyfish042 commited on Jan 10

update

b35fc31

Jellyfish042 commited on Jan 9

update

c9dc26f

Jellyfish042 commited on Jan 9

update

db6b574

Jellyfish042 commited on Jan 7

update

6341189

Jellyfish042 commited on Jan 7

update

97c8429

Jellyfish042 commited on Jan 7

update

dce5b5e

Jellyfish042 commited on Jan 6

update

68f14d5

Jellyfish042 commited on Jan 5

update

d9189f1

Jellyfish042 commited on Jan 5

update

1b6a46e

Jellyfish042 commited on Jan 4

.gitignore

ceed5d4

Jellyfish042 commited on Jan 4

update

0bc926e

Jellyfish042 commited on Jan 2

update

ac72b31

Jellyfish042 commited on Jan 2

feat: add scaling law linear fit with category-based visualization

6804102

Jellyfish042 commited on Jan 2

update

7f53fb7

Jellyfish042 commited on Jan 2

update

70a60a8

Jellyfish042 commited on Jan 1

update

5520619

Jellyfish042 commited on Jan 1

update

be9742e

Jellyfish042 commited on Jan 1

update

14f0221

Jellyfish042 commited on Jan 1

update

1f9ad45

Jellyfish042 commited on Dec 31, 2025

update

2e3b053

Jellyfish042 commited on Dec 31, 2025

sdjust

76a7f32

Jellyfish042 commited on Dec 30, 2025

style: update emojis - Data Sources plural, Knowledge use book, Multilingual use globe

dd0e48c

Jellyfish042 commited on Dec 30, 2025

feat: add border styling for Data Source section to match left panel

5c6f4f0

Jellyfish042 commited on Dec 30, 2025