Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Poem Generation on Poem
Loading...
1.043
Quality
Post-trained
0.69148
0.78274
0.874
0.96526
Feb 6, 2026
Quality
Diversity
Updated 4d ago
Evaluation Results
Method
Method
Links
Quality
Diversity
Post-trained
Backbone=Gemma
2026.02
1.043
0.127
SLR
Backbone=Gemma
2026.02
1.005
0.171
Proxy-Soup
Backbone=Gemma
2026.02
0.998
0.143
Post-trained
Backbone=Qwen
2026.02
0.882
0.152
SLR
Backbone=Qwen
2026.02
0.876
0.19
Post-trained
Backbone=Llama
2026.02
0.79
0.144
Proxy-Soup
Backbone=Llama
2026.02
0.759
0.153
SLR
Backbone=Llama
2026.02
0.754
0.24
Proxy-Soup
Backbone=Qwen
2026.02
0.705
0.179
Feedback
Search any
task
Search any
task