openai/gpt-oss-120b
OpenAI
Consistency
How often it gives the same answer when asked again. Across 45 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
17 of the 49 scored questions where its answer wasn't the one most models gave.
5 runs
+ 5 responses hide responses
10 runs · consistency 100
+ 10 responses hide responses
30 runs · consistency 33.3
+ 30 responses hide responses
15 runs · consistency 61.1
+ 15 responses hide responses
20 runs · consistency 40
+ 20 responses hide responses
5 runs
+ 5 responses hide responses
10 runs · consistency 44.4
+ 10 responses hide responses
15 runs · consistency 66.7
+ 15 responses hide responses
20 runs · consistency 40
+ 20 responses hide responses
25 runs · consistency 13.3
+ 25 responses hide responses
10 runs · consistency 100
+ 10 responses hide responses
10 runs · consistency 33.3
+ 10 responses hide responses
10 runs · consistency 50
+ 10 responses hide responses
15 runs · consistency 26.7
+ 15 responses hide responses
15 runs · consistency 100
+ 15 responses hide responses
15 runs · consistency 6.7
+ 15 responses hide responses
10 runs · consistency 100
+ 10 responses hide responses
10 runs · consistency 20
+ 10 responses hide responses
10 runs · consistency not scored
+ 10 responses hide responses
15 runs · consistency 77.8
+ 15 responses hide responses
15 runs · consistency 44.4
+ 15 responses hide responses
20 runs · consistency 51.5
+ 20 responses hide responses
15 runs · consistency 58.3
+ 15 responses hide responses
25 runs · consistency 36.1
+ 25 responses hide responses
20 runs · consistency not scored
+ 20 responses hide responses
10 runs · consistency 100
+ 10 responses hide responses
15 runs · consistency 77.8
+ 15 responses hide responses
10 runs · consistency 100
+ 10 responses hide responses
10 runs · consistency 100
+ 10 responses hide responses
10 runs · consistency 100
+ 10 responses hide responses
10 runs · consistency 100
+ 10 responses hide responses
10 runs · consistency 27.8
+ 10 responses hide responses
10 runs
+ 10 responses hide responses
20 runs · consistency not scored
+ 20 responses hide responses
20 runs · consistency 36.1
+ 20 responses hide responses
20 runs · consistency 44.4
+ 20 responses hide responses
10 runs · consistency 100
+ 10 responses hide responses
20 runs · consistency 46.7
+ 20 responses hide responses
20 runs · consistency 46.7
+ 20 responses hide responses
20 runs · consistency 100
+ 20 responses hide responses
19 runs · consistency 46.7
+ 19 responses hide responses
9 runs · consistency 20
+ 9 responses hide responses
10 runs · consistency 46.7
+ 10 responses hide responses
10 runs · consistency 100
+ 10 responses hide responses
19 runs · consistency 100
+ 19 responses hide responses
10 runs · consistency 100
+ 10 responses hide responses
10 runs · consistency 40
+ 10 responses hide responses
20 runs · consistency 19.4
+ 20 responses hide responses
5 runs
+ 5 responses hide responses
4 runs
+ 4 responses hide responses
10 runs · consistency 100
+ 10 responses hide responses
10 runs
+ 10 responses hide responses
10 runs