9.0
Vague prompt
How 20 models handled “Vague prompt” from our eval suite, best score first.
What we look for
Inspect how a model handles a vague prompt.
Prompt
“determinism”
How 20 models handled “Vague prompt” from our eval suite, best score first.
What we look for
Inspect how a model handles a vague prompt.
Prompt
“determinism”