meta/muse-spark-1.3
Meta
Consistency
Needs 20 scored questions.
How often it gives the same answer when asked again. How it's measured →
Alignment
How often its answer is the one most other models gave. Across 22 questions. How it's measured →
Hedging
How often it qualifies its answer or declines to give one. How it's measured →
Answers most like
Answers least like
Measured across the questions both models were asked, at least 20 of them. How it's measured →
Where this model stands apart
4 of the 22 scored questions where its answer wasn't the one most models gave.
10 runs · consistency 41.7
10 runs · consistency 50
10 runs · consistency 44.4
10 runs · consistency 100
10 runs · consistency 26.7
10 runs · consistency 100
10 runs
10 runs · consistency 100
10 runs · consistency 66.7
10 runs · consistency 100
10 runs · consistency 100
10 runs