  wikipedia_search           pw-aria          OK     705ms 
  wikipedia_search           pw-aria          OK     751ms 
  hn_comments                pw-aria          OK    1339ms 
  hn_comments                pw-aria          OK    1341ms 
  govuk_search               pw-aria          FAIL   6500ms no_match:Search GOV.UK
  govuk_search               pw-aria          FAIL   6566ms no_match:Search GOV.UK
  github_issues              pw-aria          FAIL   1506ms wrong_outcome:title='GitHub - microsoft/playwright: Playwrigh'
  github_issues              pw-aria          OK     878ms 
  bbc_sport_football         pw-aria          OK    1364ms 
  bbc_sport_football         pw-aria          OK    1343ms 
  ddg_search                 pw-aria          OK     750ms 
  ddg_search                 pw-aria          OK     764ms 
  nhs_search                 pw-aria          OK     977ms 
  nhs_search                 pw-aria          OK     886ms 
  amazon_search              pw-aria          FAIL   2141ms wrong_outcome:title='Amazon.co.uk : usb cable'
  amazon_search              pw-aria          FAIL   2295ms wrong_outcome:title='Amazon.co.uk : usb cable'

scenario                   impl                ok  ms(med) steps tok(med)  saw  fail
amazon_search              pw-aria          0/2       2218     3    15473 2/2  wrong_outcome:title='Amazon.co.uk : usb cable'
bbc_sport_football         pw-aria          2/2       1354     3    55086 2/2  
ddg_search                 pw-aria          2/2        757     2     2614 2/2  
github_issues              pw-aria          1/2       1192     2    15884 2/2  wrong_outcome:title='GitHub - microsoft/playwright: Playwrigh'
govuk_search               pw-aria          0/2       6533     2     6125 2/2  no_match:Search GOV.UK
hn_comments                pw-aria          2/2       1340     2   142731 2/2  
nhs_search                 pw-aria          2/2        932     3     5706 2/2  
wikipedia_search           pw-aria          2/2        728     2    94394 2/2  
TOTAL pw-aria: success 11/16  median_ms=1340  median_tokens=15473
