  wikipedia_search           sb-1.4-lite-max  OK    1181ms 
  wikipedia_search           sb-1.4-lite-max  OK    1053ms 
  hn_comments                sb-1.4-lite-max  OK    2070ms 
  hn_comments                sb-1.4-lite-max  OK    2090ms 
  govuk_search               sb-1.4-lite-max  OK    1733ms 
  govuk_search               sb-1.4-lite-max  OK     888ms 
  github_issues              sb-1.4-lite-max  OK    1771ms 
  github_issues              sb-1.4-lite-max  OK    1466ms 
  bbc_sport_football         sb-1.4-lite-max  OK    1662ms 
  bbc_sport_football         sb-1.4-lite-max  OK    1623ms 
  ddg_search                 sb-1.4-lite-max  OK     960ms 
  ddg_search                 sb-1.4-lite-max  OK     994ms 
  nhs_search                 sb-1.4-lite-max  OK    1575ms 
  nhs_search                 sb-1.4-lite-max  OK    1340ms 
  amazon_search              sb-1.4-lite-max  OK    3359ms 
  amazon_search              sb-1.4-lite-max  OK    3692ms 

scenario                   impl                ok  ms(med) steps tok(med)  saw  fail
amazon_search              sb-1.4-lite-max  2/2       3526     2     2557 2/2  
bbc_sport_football         sb-1.4-lite-max  2/2       1642     3     3799 2/2  
ddg_search                 sb-1.4-lite-max  2/2        977     2     1906 2/2  
github_issues              sb-1.4-lite-max  2/2       1618     2     2586 2/2  
govuk_search               sb-1.4-lite-max  2/2       1310     3     2624 2/2  
hn_comments                sb-1.4-lite-max  2/2       2080     2     2550 2/2  
nhs_search                 sb-1.4-lite-max  2/2       1458     3     1830 2/2  
wikipedia_search           sb-1.4-lite-max  2/2       1117     2     2514 2/2  
TOTAL sb-1.4-lite-max: success 16/16  median_ms=1599  median_tokens=2550
