Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
cube-single-play on OGBench 100% offline dataset
Loading...
0.7
Success Rate
NF-GCIQL
0.0136
0.1918
0.37
0.5482
Feb 11, 2026
Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate
NF-GCIQL
Dataset size=100%
2026.02
0.7
GCIQL
Dataset size=100%
2026.02
0.68
NF-GCIQL
Dataset size=50%
2026.02
0.4
NF-HIQL
Dataset size=100%
2026.02
0.37
NF-HIQL
Dataset size=50%
2026.02
0.36
BESO
Dataset size=100%
2026.02
0.21
CRL
Dataset size=100%
2026.02
0.19
HIQL
Dataset size=100%
2026.02
0.15
GCIQL
Dataset size=50%
2026.02
0.1
CRL
Dataset size=50%
2026.02
0.06
BESO
Dataset size=50%
2026.02
0.04
HIQL
Dataset size=50%
2026.02
0.04
Feedback
Search any
task
Search any
task
