mirror of
https://github.com/hanzoai/trolley-bench.git
synced 2026-11-02 13:22:03 +00:00
* Packaged the benchmark's working copy with its frozen prompts, runners, raw answers, analysis and built page as committed evidence * Rewrote run-machine paths and left out share credentials, drafts and operator notes; PACKAGING.md lists every exclusion and change * Fixed the models.yaml generator listing rerun models twice, and let the Jev runner take its key from TYPESAFE_API_KEY
34 lines
1.6 KiB
Plaintext
34 lines
1.6 KiB
Plaintext
636 cells compared with their originals; ids, scenario, wording, order, count, k and the three questions identical; JSON keys and key order identical
|
|
Every change, as (removed -> inserted), with how many times it occurs:
|
|
124 'people, strangers to you,' -> 'people'
|
|
76 'people, strangers to you;' -> 'people;'
|
|
76 'people, strangers to you",' -> 'people",'
|
|
72 'person, a stranger to you.' -> 'person.'
|
|
48 'person, a stranger to you;' -> 'person;'
|
|
48 'strangers to you,' -> ''
|
|
42 'person, also a stranger to you.' -> 'person.'
|
|
42 'person, a stranger to you",' -> 'person",'
|
|
42 'person, a stranger to you,' -> 'person'
|
|
36 'a stranger to you,' -> ''
|
|
24 'people, all strangers to you;' -> 'people;'
|
|
24 'people (strangers to you).' -> 'people.'
|
|
24 'there, all strangers,' -> 'there'
|
|
24 'They are strangers to you, and the' -> 'The'
|
|
24 'strangers,' -> ''
|
|
24 'people you have never met;' -> 'people;'
|
|
24 'people, all strangers to you.' -> 'people.'
|
|
24 'track, strangers to you,' -> 'track'
|
|
24 'You do not know them.' -> ''
|
|
24 'people, strangers to you.' -> 'people.'
|
|
24 'people who are strangers to you.' -> 'people.'
|
|
12 'a' -> 'one'
|
|
12 'stranger;' -> 'person;'
|
|
12 'track, strangers to you;' -> 'track;'
|
|
12 'track, strangers to you.' -> 'track.'
|
|
12 'person, a stranger to you' -> 'person'
|
|
12 'person, a stranger to you).' -> 'person).'
|
|
4 'person, strangers to you;' -> 'person;'
|
|
4 'person, strangers to you",' -> 'person",'
|
|
4 'person, strangers to you,' -> 'person'
|
|
changes without stranger wording on the removed side: [('a', 'one')]
|