Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Dialog on Social & Entertainment Out-of-Domain
Loading...
87.13
Accuracy
Baseline
23.1388
39.7519
56.365
72.9781
Feb 5, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Baseline
Training Steps=1000
2026.02
87.13
DFPO
Training Steps=1000
2026.02
86.4
Reinforce++
Training Steps=1000
2026.02
85.4
PPO
Training Steps=1000
2026.02
59.7
Dr.GRPO
Training Steps=1000
2026.02
50.8
GRPO
Training Steps=1000
2026.02
25.6
Feedback
Search any
task
Search any
task