Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Partner Ordering Prediction on Deal-or-No-Deal cross-domain transfer n=1695 turn snapshots
Loading...
0.1166
Brier Score
Few-shot
0.108504
0.163152
0.2178
0.272448
May 6, 2026
Brier Score
EMA @ 2
EMA 1:3
NDCG 1:3
Updated 27d ago
Evaluation Results
Method
Method
Links
Brier Score
EMA @ 2
EMA 1:3
NDCG 1:3
Few-shot
strategy=native empirical
2026.05
0.1166
59.81
58.79
85.41
Few-shot
strategy=renamed empir...
2026.05
0.1207
58.45
56.94
84.59
Bayesian transfer
strategy=renamed
2026.05
0.1335
51.26
50.29
79.69
Bayesian transfer
strategy=native
2026.05
0.1438
47.96
48.27
78.52
Rule baseline
2026.05
0.1605
23.69
22.59
56.75
Direct posterior
strategy=renamed
2026.05
0.319
18.06
17.43
51.7
Feedback
Search any
task
Search any
task