Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Question Answering on CAmbigNQ
Loading...
36.66
ROUGE-L
RAC_SFT
9.2768
16.3859
23.495
30.6041
Jan 16, 2026
ROUGE-L
BLEU
METEOR
BERTScore (F1)
ALScore
Par-R
Updated 4d ago
Evaluation Results
Method
Method
Links
ROUGE-L
BLEU
METEOR
BERTScore (F1)
ALScore
Par-R
RAC_SFT
Training=Supervised Fi...
2026.01
36.66
14.81
43.37
88.93
47.62
87.99
RAC_DPO
Training=Direct Prefer...
2026.01
35.47
14.4
41.99
88.89
49.95
88.05
Q-Cond
2026.01
28.41
8.9
33.06
87.17
-
-
QP-Zeroshot
Mode=Zero-shot
2026.01
18.2
4.27
19.48
85.15
-
-
AT-CoT
Reasoning=Chain-of-Tho...
2026.01
10.33
2.1
8.53
84.02
-
-
Feedback
Search any
task
Search any
task