Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Automated Program Optimization on Parameter Golf bpb (val)
Loading...
1.2244
Score (val_bpb)
Naive reference baseline
1.066112
1.107206
1.1483
1.189394
May 7, 2026
Score (val_bpb)
Relative Change vs Start
Number of Trials
Valid Improvements Count
Updated 26d ago
Evaluation Results
Method
Method
Links
Score (val_bpb)
Relative Change vs Start
Number of Trials
Valid Improvements Count
Naive reference baseline
Row=Naive reference ba...
2026.05
1.2244
-
-
-
Public SOTA starting point
Row=Public SOTA starti...
2026.05
1.081
-
-
-
No lineage
Row=No lineage
2026.05
1.0774
-0.33
200
3
Single generalist
Row=Single generalist
2026.05
1.0754
-0.52
200
14
Generic-10
Row=Generic-10
2026.05
1.0745
-0.6
200
10
Role swarm
Row=Role swarm control
2026.05
1.0731
-0.73
200
16
Role swarm
Row=Role swarm, full run
2026.05
1.0722
-0.81
900
36
Feedback
Search any
task
Search any
task