Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
HT on HT
Loading...
367
Generation Score
Rand
47.72
130.61
213.5
296.39
May 28, 2026
Generation Score
FLOPs (10^15)
Updated 5d ago
Evaluation Results
Method
Method
Links
Generation Score
FLOPs (10^15)
Rand
threshold (tau)=0.70,...
2026.05
367
381.23
EXP3.P
threshold (tau)=0.70,...
2026.05
209
213.22
ShinkaEvolve
threshold (tau)=0.50,...
2026.05
201
189.28
UCB
threshold (tau)=0.70,...
2026.05
125
130.55
EXP3.P
threshold (tau)=0.50,...
2026.05
102
108.67
Thompson
threshold (tau)=0.70,...
2026.05
101
104.53
Rand
threshold (tau)=0.50,...
2026.05
92
99.9
Thompson
threshold (tau)=0.50,...
2026.05
74
79.45
UCB
threshold (tau)=0.50,...
2026.05
60
66.9
Feedback
Search any
task
Search any
task
