Take audit: uSedCITM1TtNRgr5tQGRh
2026-08-22T09:30:22.327Z — ray
0/13 judged · keyboard: Space play/pause, ↑/↓ focus, P pass, T Translation failure, F fail
Do a blind check (transcripts hidden)
Ground Truth
What the Tester actually said. Never pre-filled from an Engine — type what you hear.
Transcripts
mini_prod_baseline gpt-4o-mini-transcribe · degraded · en · bare
— MER accuracy pending Ground Truth · 584 ms · verdict: unjudged
我要用卡付錢,Is that OK?
mini_auto_bare_deg gpt-4o-mini-transcribe · degraded · auto · bare
— MER accuracy pending Ground Truth · 732 ms · verdict: unjudged
我要用卡付錢,is that OK?
mini_auto_bare_clean gpt-4o-mini-transcribe · clean · auto · bare
— MER accuracy pending Ground Truth · 753 ms · verdict: unjudged
我要用卡付錢,is that ok?
mini_auto_prompt_deg gpt-4o-mini-transcribe · degraded · auto · mixed prompt
— MER accuracy pending Ground Truth · 563 ms · verdict: unjudged
我要用卡付錢,Is that OK?
mini_auto_prompt_clean gpt-4o-mini-transcribe · clean · auto · mixed prompt
— MER accuracy pending Ground Truth · 615 ms · verdict: unjudged
我要用卡付錢,Is that OK?
mini_auto_prompt_64k gpt-4o-mini-transcribe · 64k · auto · mixed prompt
— MER accuracy pending Ground Truth · 544 ms · verdict: unjudged
我要用卡付錢,Is that ok?
mini_zh_prompt_deg gpt-4o-mini-transcribe · degraded · zh · mixed prompt
— MER accuracy pending Ground Truth · 514 ms · verdict: unjudged
我要用卡付錢,Is that OK?
mini_zh_prompt_clean gpt-4o-mini-transcribe · clean · zh · mixed prompt
— MER accuracy pending Ground Truth · 615 ms · verdict: unjudged
我要用卡付錢,Is that OK?
gpt_tw_en_bare_deg gpt-transcribe · degraded · zh-tw + en · bare
— MER accuracy pending Ground Truth · 539 ms · verdict: unjudged
我要用 car 付錢 is that OK?
gpt_tw_en_prompt_deg gpt-transcribe · degraded · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 776 ms · verdict: unjudged
我要用 car 付錢 is that OK?
gpt_tw_en_prompt_clean gpt-transcribe · clean · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 688 ms · verdict: unjudged
我要用 car 付錢，is that OK?
gpt_tw_en_prompt_64k gpt-transcribe · 64k · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 876 ms · verdict: unjudged
我要用 car 付錢，is that OK?
gpt_tw_only_prompt_deg gpt-transcribe · degraded · zh-tw · mixed prompt
— MER accuracy pending Ground Truth · 614 ms · verdict: unjudged
我要用卡付錢 is that OK?
Winning configuration
Record the variant and rationale to hand to qa-rails after reviewing this Take.