thinkingmachines/inkling
ThinkingMachines
Consistency
How often it gives the same answer when asked again. Across 53 questions. How it's measured →
Alignment
How often its answer is the one most other models gave. Across 49 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
7 of the 49 scored questions where its answer wasn't the one most models gave.
20 runs · consistency 50
20 runs · consistency 27.8
20 runs · consistency 30.6
20 runs · consistency 36.1
20 runs · consistency 40
10 runs · consistency 44.4
20 runs · consistency 40
20 runs · consistency 40
20 runs · consistency 40
20 runs · consistency 46.7
10 runs · consistency 50
20 runs · consistency 33.3
20 runs · consistency 26.7
10 runs · consistency 100
10 runs · consistency 20
20 runs · consistency 27.8
20 runs · consistency 11.1
20 runs · consistency 37.9
20 runs · consistency 100
20 runs · consistency 100
20 runs · consistency not scored
20 runs · consistency 27.8
20 runs · consistency 100
20 runs · consistency 100
20 runs · consistency 40
20 runs · consistency 100
20 runs · consistency 22.2
20 runs · consistency 26.7
20 runs · consistency 100
20 runs · consistency 66.7
20 runs · consistency 46.7
20 runs · consistency 40
20 runs · consistency 66.7
20 runs · consistency 100
20 runs · consistency 100
20 runs · consistency 40
20 runs · consistency 100
20 runs · consistency 100
20 runs · consistency 100
20 runs · consistency 100
20 runs · consistency 100
10 runs · consistency 100
10 runs
10 runs