Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Antmaze Medium Navigation on OGBench 100% offline dataset
Loading...
96
Success Rate
HIQL
21.12
40.56
60
79.44
Feb 11, 2026
Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate
HIQL
Dataset size=100%
2026.02
96
CRL
Dataset size=100%
2026.02
95
NF-HIQL
Dataset size=100%
2026.02
95
BESO
Dataset size=100%
2026.02
85
NF-GCIQL
Dataset size=100%
2026.02
82
NF-HIQL
Dataset size=50%
2026.02
72
GCIQL
Dataset size=100%
2026.02
71
NF-GCIQL
Dataset size=50%
2026.02
64
BESO
Dataset size=50%
2026.02
63
HIQL
Dataset size=50%
2026.02
58
CRL
Dataset size=50%
2026.02
50
GCIQL
Dataset size=50%
2026.02
24
Feedback
Search any
task
Search any
task
