Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-branch story generation on WritingPrompts
Loading...
3.7
Diversity
Ours_local
0.892
1.621
2.35
3.079
Apr 19, 2026
Diversity
Degeneration
Creativity
Coherence
Updated 24d ago
Evaluation Results
Method
Method
Links
Diversity
Degeneration
Creativity
Coherence
Ours_local
Base Model=LLaMA, Eval...
2026.04
3.7
3.7
3.6
4
Ours
Base Model=LLaMA, Eval...
2026.04
3.7
2.1
3.3
3.3
Ours_local
Base Model=LLaDA, Eval...
2026.04
3.4
3.2
3.3
3.3
Ours
Base Model=LLaDA, Eval...
2026.04
3.4
2.2
3.3
3.5
Ours_global
Base Model=LLaMA, Eval...
2026.04
3
2
3
2.8
Naive
Base Model=LLaMA, Eval...
2026.04
2.3
1.4
1.4
1.7
Top-p
Base Model=LLaMA, Eval...
2026.04
2.1
1.5
1.6
1.8
Naive
Base Model=LLaDA, Eval...
2026.04
1.6
1
1.2
1
Top-k
Base Model=LLaMA, Eval...
2026.04
1
1
1
1
Ours_global
Base Model=LLaDA, Eval...
2026.04
1
2.3
1.7
2.6
Feedback
Search any
task
Search any
task