Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Creative Writing on ROCStories + WritingPrompts
Loading...
63.3
QD-Score
QD-LLM
35.324
42.587
49.85
57.113
May 10, 2026
QD-Score
Median (IQR)
Coverage
SB
A
Updated 21d ago
Evaluation Results
Method
Method
Links
QD-Score
Median (IQR)
Coverage
SB
A
QD-LLM
Base LLM=Llama-3-70B-I...
2026.05
63.3
63.1
52
28
96
CMA-ME (ad.)
Prompt embeddings=adap...
2026.05
46.2
46
39
38
-
QDAIF
Base LLM=Llama-3-70B-I...
2026.05
44.8
44.6
37
40
-
Best-of-N+MMR
N=20, Base LLM=Llama-3...
2026.05
40.1
39.9
31
46
-
Diverse Beam Search
λ=0.5, Base LLM=Llama-...
2026.05
38.2
38
28
52
-
Nucleus Sampling
p=0.95, Base LLM=Llama...
2026.05
36.4
36.2
26
56
-
Feedback
Search any
task
Search any
task