Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

HEx

Benchmarks

Task NameDataset NameSOTA ResultTrend
Safety EvaluationHEx-PHI-FigStep
Safety Score (1-ASR)1
8
Hexagon PackingHEX n=11 (test)
Side Length (L)3.9434
6
Hexagon PackingHEX n=12 (test)
Side Length (L)3.9416
5
Board Game Play11x11 Hex
Win rate91.1
3
Hexagon PackingHEX 24
Side Length (L)5.4848
3
Hexagon PackingHEX 23
Side Length (L)5.4848
3
Hexagon PackingHEX 22
Side Length (L)5.2857
3
Hexagon PackingHEX 21
Side Length (L)5
3
Hexagon PackingHEX 20
Side length (L)5
3
Hexagon PackingHEX 19
Side length (L)4.6188
3
Hexagon PackingHEX 18
Side Length (L)4.6188
3
Hexagon PackingHEX 17
Side Length (L)4.6188
3
Hexagon PackingHEX 16
Side Length (L)4.5275
3
Hexagon PackingHEX 15
Side length (L)4.4541
3
Hexagon PackingHEX 14
Side Length (L)4.2724
3
Hexagon PackingHEX 13
Side length (L)4
3
Hexagon PackingHEX 30
Side length (L)6.0045
2
Hexagon PackingHEX 29
Side Length (L)6
2
Hexagon PackingHEX 28
Side length (L)5.9723
2
Hexagon PackingHEX 27
Side Length (L)5.7142
2
Hexagon PackingHEX 26
Side length (L)5.7142
2
Hexagon PackingHEX 25
Side Length (L)5.651
2
Showing 22 of 22 rows