Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Decision making on vignette-based (inference)
Loading...
48.3
Vignette Score
MeTHanol (8B)
9.612
19.656
29.7
39.744
Sep 18, 2024
Vignette Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Vignette Score
MeTHanol (8B)
Model size=similar siz...
2024.09
48.3
GPT-4
Model size=much larger...
2024.09
46.9
Mistral-7B-Instruct
Model size=similar siz...
2024.09
40.2
GPT-3
Model size=much larger...
2024.09
37.5
Llama3-8B-Instruct
Model size=similar siz...
2024.09
23.8
Quiet-STaR (7B)
Model size=similar siz...
2024.09
11.1
Feedback
Search any
task
Search any
task