Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Query-driven contrastive summarization on Restaurants (test)
Loading...
87
Contrast Win Rate
Q-STRUM Debate
84.92
85.46
86
86.54
Feb 18, 2025
Contrast Win Rate
Relevance Win Rate
Diversity Win Rate
Usefulness Win Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Contrast Win Rate
Relevance Win Rate
Diversity Win Rate
Usefulness Win Rate
Q-STRUM Debate
Evaluation Model=GPT-4...
2025.02
87
57
84
89
Q-STRUM Debate
Evaluation Model=GPT-4...
2025.02
85
57
83
83
Feedback
Search any
task
Search any
task