Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Scene Play Evaluation on OGBench 100% offline dataset
Loading...
81
Success Rate
BESO
-1.16
20.17
41.5
62.83
Feb 11, 2026
Success Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Success Rate
BESO
Dataset size=100%
2026.02
81
GCIQL
Dataset size=100%
2026.02
51
NF-GCIQL
Dataset size=100%
2026.02
50
NF-HIQL
Dataset size=100%
2026.02
40
HIQL
Dataset size=100%
2026.02
38
NF-HIQL
Dataset size=50%
2026.02
36
NF-GCIQL
Dataset size=50%
2026.02
33
CRL
Dataset size=100%
2026.02
19
BESO
Dataset size=50%
2026.02
14
GCIQL
Dataset size=50%
2026.02
8
HIQL
Dataset size=50%
2026.02
6
CRL
Dataset size=50%
2026.02
2
Feedback
Search any
task
Search any
task