Take audit: yeDinL9rAoCHN7gaWHazr
2026-08-22T09:41:49.554Z — 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 · 445 ms · verdict: unjudged
這是我的box,Is this my box?
mini_auto_bare_deg gpt-4o-mini-transcribe · degraded · auto · bare
— MER accuracy pending Ground Truth · 528 ms · verdict: unjudged
這是我的box,is this my box?
mini_auto_bare_clean gpt-4o-mini-transcribe · clean · auto · bare
— MER accuracy pending Ground Truth · 474 ms · verdict: unjudged
這是我的box,Is this my box?
mini_auto_prompt_deg gpt-4o-mini-transcribe · degraded · auto · mixed prompt
— MER accuracy pending Ground Truth · 607 ms · verdict: unjudged
這是我的box,Is this my box?
mini_auto_prompt_clean gpt-4o-mini-transcribe · clean · auto · mixed prompt
— MER accuracy pending Ground Truth · 708 ms · verdict: unjudged
這是我的box,is this my box?
mini_auto_prompt_64k gpt-4o-mini-transcribe · 64k · auto · mixed prompt
— MER accuracy pending Ground Truth · 662 ms · verdict: unjudged
這是我的box, Is this my box?
mini_zh_prompt_deg gpt-4o-mini-transcribe · degraded · zh · mixed prompt
— MER accuracy pending Ground Truth · 592 ms · verdict: unjudged
這是我的box, is this my box?
mini_zh_prompt_clean gpt-4o-mini-transcribe · clean · zh · mixed prompt
— MER accuracy pending Ground Truth · 3533 ms · verdict: unjudged
這是我的box, is this my box?
gpt_tw_en_bare_deg gpt-transcribe · degraded · zh-tw + en · bare
— MER accuracy pending Ground Truth · 680 ms · verdict: unjudged
這是我的 box. Is this my box?
gpt_tw_en_prompt_deg gpt-transcribe · degraded · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 705 ms · verdict: unjudged
這是我的 box. Is this my box?
gpt_tw_en_prompt_clean gpt-transcribe · clean · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 547 ms · verdict: unjudged
這是我的 box, is this my box.
gpt_tw_en_prompt_64k gpt-transcribe · 64k · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 711 ms · verdict: unjudged
這是我的 box. Is this my box?
gpt_tw_only_prompt_deg gpt-transcribe · degraded · zh-tw · mixed prompt
— MER accuracy pending Ground Truth · 547 ms · verdict: unjudged
這是我的 box. Is this my box?
Winning configuration
Record the variant and rationale to hand to qa-rails after reviewing this Take.