stepfun/step-3.7-flash
StepFun
Consistency
How often it gives the same answer when asked again. Across 46 questions. How it's measured →
Alignment
How often its answer is the one most other models gave. Across 42 questions. How it's measured →
Hedging
moderation 2.7%, blocked by the provider and not counted above
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
14 of the 42 scored questions where its answer wasn't the one most models gave.
20 runs · consistency 44.4
+ 20 responses hide responses
20 runs · consistency 77.8
+ 20 responses hide responses
20 runs · consistency 22.2
+ 20 responses hide responses
20 runs · consistency 25
+ 20 responses hide responses
20 runs · consistency 26.7
+ 20 responses hide responses
10 runs · consistency 30.6
+ 10 responses hide responses
20 runs · consistency 20
+ 20 responses hide responses
20 runs · consistency 20
+ 20 responses hide responses
20 runs · consistency 13.3
+ 20 responses hide responses
20 runs · consistency 100
+ 20 responses hide responses
20 runs · consistency 36.1
+ 20 responses hide responses
10 runs · consistency 77.8
+ 10 responses hide responses
20 runs · consistency 66.7
+ 20 responses hide responses
20 runs · consistency 33.3
+ 20 responses hide responses
20 runs · consistency 13.3
+ 20 responses hide responses
10 runs · consistency 40
+ 10 responses hide responses
10 runs · consistency 26.7
+ 10 responses hide responses
20 runs · consistency not scored
+ 20 responses hide responses
20 runs · consistency 5.6
+ 20 responses hide responses
19 runs · consistency 8.3
+ 19 responses hide responses
20 runs · consistency 31.8
+ 20 responses hide responses
20 runs · consistency 100
+ 20 responses hide responses
20 runs · consistency 44.4
+ 20 responses hide responses
20 runs · consistency not scored
+ 20 responses hide responses
20 runs · consistency 100
+ 20 responses hide responses
20 runs · consistency 100
+ 20 responses hide responses
20 runs · consistency 61.1
+ 20 responses hide responses
20 runs · consistency 36.1
+ 20 responses hide responses
10 runs · consistency 50
+ 10 responses hide responses
10 runs · consistency 33.3
+ 10 responses hide responses
20 runs · consistency 69.7
+ 20 responses hide responses
20 runs · consistency not scored
+ 20 responses hide responses
20 runs · consistency 25
+ 20 responses hide responses
20 runs · consistency 77.8
+ 20 responses hide responses
20 runs · consistency 100
+ 20 responses hide responses
20 runs · consistency 46.7
+ 20 responses hide responses
7 runs
+ 7 responses hide responses
17 runs · consistency 100
+ 17 responses hide responses
10 runs · consistency 100
+ 10 responses hide responses
10 runs · consistency 46.7
+ 10 responses hide responses
10 runs · consistency 26.7
+ 10 responses hide responses
10 runs · consistency 66.7
+ 10 responses hide responses
20 runs · consistency 100
+ 20 responses hide responses
10 runs · consistency 100
+ 10 responses hide responses
10 runs · consistency 100
+ 10 responses hide responses
20 runs · consistency 11.1
+ 20 responses hide responses
10 runs · consistency 61.1
+ 10 responses hide responses
10 runs
+ 10 responses hide responses
10 runs