Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Dialog on Real-world Dialog Domains Aggregate
Loading...
87.31
Average Accuracy
DFPO
25.4404
41.5027
57.565
73.6273
Feb 5, 2026
Average Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Average Accuracy
DFPO
Training Steps=1000
2026.02
87.31
Baseline
Training Steps=1000
2026.02
86.26
Reinforce++
Training Steps=1000
2026.02
81.15
PPO
Training Steps=1000
2026.02
61.55
Dr.GRPO
Training Steps=1000
2026.02
48.42
GRPO
Training Steps=1000
2026.02
27.82
Feedback
Search any
task
Search any
task