stepfun/step-3.7-flash
StepFun
Consistency
How often it gives the same answer when asked again. Across 44 questions. How it's measured →
Alignment
How often its answer is the one most other models gave. Across 41 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
12 of the 41 scored questions where its answer wasn't the one most models gave.
20 runs · consistency 44.4
20 runs · consistency 77.8
20 runs · consistency 22.2
20 runs · consistency 25
20 runs · consistency 26.7
10 runs · consistency 30.6
20 runs · consistency 20
20 runs · consistency 20
20 runs · consistency 13.3
20 runs · consistency 100
10 runs · consistency 77.8
20 runs · consistency 33.3
20 runs · consistency 13.3
10 runs · consistency 40
10 runs · consistency 26.7
20 runs · consistency 5.6
19 runs · consistency 8.3
20 runs · consistency 31.8
20 runs · consistency 44.4
20 runs · consistency 100
20 runs · consistency 69.7
20 runs · consistency not scored
20 runs · consistency 77.8
20 runs · consistency 100
20 runs · consistency 46.7
17 runs · consistency 100
10 runs · consistency 100
10 runs · consistency 46.7
10 runs · consistency 26.7
20 runs · consistency 100
10 runs · consistency 100
10 runs · consistency 100
10 runs · consistency 61.1
10 runs
10 runs