Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Alignment ranking evaluation on GDPVal 44 tasks
Loading...
0.8722
Mean NDCG@8
GSPO Rubric
0.796904
0.816452
0.836
0.855548
Dec 5, 2025
Mean NDCG@8
Std. Dev. NDCG@8
Updated 4d ago
Evaluation Results
Method
Method
Links
Mean NDCG@8
Std. Dev. NDCG@8
GSPO Rubric
Model–Rubric Pair=GSPO...
2025.12
0.8722
0.0985
SFT Rubric
Model–Rubric Pair=SFT...
2025.12
0.8103
0.0881
No-Conv (Base)
Model–Rubric Pair=No-C...
2025.12
0.7998
0.0807
Feedback
Search any
task
Search any
task