Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Premise Completion on Crafted Rules Dataset (test)
Loading...
52.7
BLEU
Engine
16.508
25.904
35.3
44.696
Feb 18, 2024
BLEU
Updated 1mo ago
Evaluation Results
Method
Method
Links
BLEU
Engine
backbone=Mistral-7b, m...
2024.02
52.7
GPT-3.5
mode=prompting
2024.02
24.8
GPT-4
mode=prompting
2024.02
17.9
Feedback
Search any
task
Search any
task
