Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Budget compliance on Human-study paradigms H1–H4
Loading...
70
Win Rate
CUPID
49.2
54.6
60
65.4
May 30, 2026
Win Rate
Draw Rate
Loss Rate
Median Delta
P-Value
RRB Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Win Rate
Draw Rate
Loss Rate
Median Delta
P-Value
RRB Score
CUPID
Setup=H4: open prefere...
2026.05
70
20
10
1
0.047
0.833
CUPID
Setup=H3: open prefere...
2026.05
60
26.7
13.3
1
0.033
0.667
CUPID
Setup=All pooled (H1–H...
2026.05
58.8
29.4
11.8
1
0
0.73
CUPID
Setup=H2: domain exper...
2026.05
58.3
25
16.7
1
0.18
0.556
CUPID
Setup=Text pooled (H1–...
2026.05
56.1
31.7
12.2
1
0.001
0.692
CUPID
Setup=H1: constraints...
2026.05
50
42.9
7.1
0.5
0.031
0.833
Feedback
Search any
task
Search any
task
