Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Length-Constrained Text Generation on TruthfulQA
Loading...
36.91
Win Rate
MARKERGEN
19.2196
23.8123
28.405
32.9977
Feb 19, 2025
Win Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Win Rate
MARKERGEN
Model Series=Qwen2.5,...
2025.02
36.91
Implicit
Model Series=Llama3.1,...
2025.02
33.81
MARKERGEN
Model Series=Llama3.1,...
2025.02
30.31
Implicit
Model Series=Qwen2.5,...
2025.02
28.87
Implicit
Model Series=Qwen2.5,...
2025.02
28.25
MARKERGEN
Model Series=Qwen2.5,...
2025.02
25.62
MARKERGEN
Model Series=Qwen2.5,...
2025.02
24.12
Implicit
Model Series=Qwen2.5,...
2025.02
23.24
MARKERGEN
Model Series=Llama3.1,...
2025.02
20.52
Implicit
Model Series=Llama3.1,...
2025.02
19.9
Feedback
Search any
task
Search any
task
