← All runs

Evaluation run

post guard-fix rerun

6 July 2026, 11:12 · eval-engine · 54c20aa · 89 cases

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?

79%
Light, ships on by default
70/89 cases passed · 260 ms typical
71%
Polish, experimental
63/89 cases passed · 262 ms typical
When a case fails, whose fault is it?
0 the microphone misheard the words  ·  45 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

grammar-runon-01Typedclean
Instantso i went to the meeting and then i talked to sarah and then we decided to push the launch and also we need to tell the team
LightSo I went to the meeting and then I talked to Sarah and then we decided to push the launch, and also we need to tell the team. 738 ms
PolishSo I went to the meeting and then i talked to Sarah. and then We decided to push the launch and also we need to tell the team. 613 ms
grammar-tense-01Typedneeds review
Instantyesterday i go to the office and i see the new design
Lightyesterday i go to the office and i see the new design 344 msthe cleanup was rejected, so the original was kept
PolishYesterday, I go went to the office and i see saw the new design. 339 ms
Why light?guard rejected
num-chapterTypedclean
Instantlet's start with chapter one
LightLet's start with chapter one. 212 ms
PolishLet's start with chapter one. 196 ms
num-currencyTypedclean
Instantthe plan costs $25 a month
LightThe plan costs $25 a month. 231 ms
PolishThe plan costs $25 a month. 228 ms
num-decimalTypedclean
Instantthe download is 3 point 5 gigabytes
LightThe download is 3 point 5 3.5 gigabytes. 257 ms
PolishThe download is 3 point 5 3.5 gigabytes. 258 ms
num-decimal-pctTypedclean
Instantwe hit 99 point 9% uptime
LightWe hit 99 point 9% 99.9% uptime. 284 ms
PolishWe hit 99 point 9% 99.9% uptime. 280 ms
num-first-placeTypedclean
Instantshe came in first place at the meet
LightShe came in first place at the meet. 243 ms
PolishShe came in first place at the meet. 232 ms
num-halfTypedclean
Instantgive me half a second to think
LightGive me half a second to think. 267 ms
PolishGive me half a second to think. 215 ms
num-largeTypedclean
Instantwe shipped 120 units
LightWe shipped 120 units. 218 ms
PolishWe shipped 120 units. 213 ms
num-no-oneTypedclean
Instantno one showed up to the review
LightNo one showed up to the review. 213 ms
PolishNo one showed up to for the review. 242 ms