{"i":24,"slug":"haiku-retry-or-escalate","chart":{"id":"retry-escalate-time-per-correct","title":"Expected wall time per correct answer, by retry policy (calculation)","subtitle":"Tries run one after another, so a failed try adds its time","kind":"bar","unit":"seconds","yLabel":"Seconds per correct answer","series":[{"name":"Time per correct answer (calculation)","points":{"$k":["label","value","n","highlight"],"$r":[["Sonnet 5.5 low effort once (calculation)",7.07,16,false],["Sonnet 5.5 every time (calculation)",8.24,24,true],["Haiku, one retry, then Sonnet (calculation)",71.54,48,false],["Haiku once (calculation)",91.47,24,false],["Haiku up to 3 tries, then Sonnet (calculation)",93.42,48,false]]}}],"note":"Calculation, not a run. These are median-input scenarios, not measured mean times. Each task’s median total call time (CLI start-up included), summed over the tries a policy expects to run, divided by the expected number of correct answers. Tries are assumed to run one after another. Parallel tries were not tested. One host, one network. A calculation has no confidence interval. Highlighted: the baseline, Sonnet 5.5 every time.","sourceIds":["calc-repricing","agent-provider-h2h-hard","agent-effort-ladder","price-anthropic"]}}