num-one-dayTypedclean
Instantremind me in one day to check the logs
LightRemind me in one day to check the logs. 1057 ms
PolishRemind me in one day to check the logs in one day. 960 ms
Evaluation run
faithfulness scoring cleanup
Did it hear the words right?
This run graded typed text only, so there is nothing here to have misheard.
Did it clean up correctly and safely?
94%
Light, ships on by default
84/89 cases passed · 254 ms typical
89%
Polish, experimental
79/89 cases passed · 266 ms typical
When a case fails, whose fault is it?
0 the microphone misheard the words · 15 the cleanup itself slipped
Every case
Each case shows the instant on-device cleanup, then what each mode did to it. Added words are marked, removed words are struck. For a spoken case, Heard is what the microphone transcribed and Was said is the reference it is scored against.
89 cases match
num-one-of-themTypedclean
Instantone of them is already broken
LightOne of them is already broken. 197 ms
PolishOne of them is already broken. 195 ms
num-one-on-oneTypedclean
Instantlet's do a one on one tomorrow
LightLet's do a one on one one-on-one tomorrow. 256 ms
PolishLet's do a one on one one-on-one tomorrow. 266 ms
num-one-secTypedclean
Instanti'll be ready in one sec
LightI'll be ready in one sec. 237 ms
PolishI'll be ready in one sec. 241 ms
num-percentTypedclean
Instantrevenue grew 25% last quarter
LightRevenue grew 25% last quarter. 233 ms
PolishRevenue grew 25% last quarter. 231 ms
num-phoneTypedclean
Instantcall me at five five five one two three four
LightCall me at five five five one two three four 555-1234. 333 ms
PolishCall me at five five five one two three four 555-1234. 346 ms
num-rangeTypedclean
Instantit should take 2 to 3 days
LightIt should take 2 to 3 days. 257 ms
PolishIt should take 2 to 3 days. 251 ms
num-roomTypedclean
Instantthe meeting is in room 205
LightThe meeting is in room 205. 250 ms
PolishThe meeting is in room 205. 251 ms
num-room-214Typedclean
Instantthe interview is in room 214
LightThe interview is in room 214. 275 ms
PolishThe interview is in room 214. 286 ms
num-selfcorrectTypedneeds review
Instantthe total comes to 50 no wait $60
LightThe total comes to 50 no wait $60. 221 ms
PolishThe total comes to 50 $60. No wait, $60 the total comes to $50. 409 ms
Why polish?the result still contains “$50” and “no wait”, which this case forbids