{"updated":"2026-09-24T00:00:10.346256+00:00","models":[{"id":"GPT-6 Astra|xhigh","name":"GPT-6 Astra","provider":"OpenAI","color":"#39786d","effort":"xhigh","score":60.0,"ci":[41.666666666666664,78.33333333333333],"n":60,"successes":36.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.6666666666666666,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.6666666666666666,"002--frappe--07-desk-and-queue-outage-64526986":0.6666666666666666,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":1.0,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.6666666666666666,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.6666666666666666,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":1.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":1.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":1.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.0,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":1.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":1.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":1.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.6666666666666666,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":1.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":3.7952941610169493,"costN":59,"usageEstimatedN":0,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":7.371427777777778,"timeN":60,"unreviewed":6,"releaseDate":"2026-09-03"},{"id":"Claude Opus 5.5|medium","name":"Claude Opus 5.5","provider":"Anthropic","color":"#dc7045","effort":"medium","score":58.333333333333336,"ci":[43.33333333333333,73.33333333333333],"n":60,"successes":35.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.6666666666666666,"001--frappe--07-desk-and-queue-oom-0669b8e8":1.0,"002--frappe--07-desk-and-queue-outage-64526986":0.3333333333333333,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":1.0,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":1.0,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.6666666666666666,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":1.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":1.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":1.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.3333333333333333,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.3333333333333333,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.3333333333333333,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.6666666666666666,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.3333333333333333,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.3333333333333333,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.3333333333333333,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":1.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.3333333333333333},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":1.7784212533333332,"costN":60,"usageEstimatedN":60,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":7.453633333333333,"timeN":60,"unreviewed":38,"releaseDate":"2026-09-22"},{"id":"GPT-6 Astra|low","name":"GPT-6 Astra","provider":"OpenAI","color":"#39786d","effort":"low","score":58.333333333333336,"ci":[41.666666666666664,75.0],"n":60,"successes":35.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":1.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.6666666666666666,"002--frappe--07-desk-and-queue-outage-64526986":0.3333333333333333,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":1.0,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.6666666666666666,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.3333333333333333,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.3333333333333333,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":1.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":1.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":1.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.3333333333333333,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.6666666666666666,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.6666666666666666,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.6666666666666666,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":1.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":1.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":2.3439090803571427,"costN":56,"usageEstimatedN":0,"tierUncertainN":2,"allTaskCount":20,"allN":60,"minutes":3.767233333333333,"timeN":60,"unreviewed":6,"releaseDate":"2026-09-03"},{"id":"Claude Fable 5.1|medium","name":"Claude Fable 5.1","provider":"Anthropic","color":"#b66147","effort":"medium","score":54.99999999999999,"ci":[41.666666666666664,68.33333333333333],"n":60,"successes":33.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.3333333333333333,"001--frappe--07-desk-and-queue-oom-0669b8e8":1.0,"002--frappe--07-desk-and-queue-outage-64526986":0.6666666666666666,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.3333333333333333,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.3333333333333333,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.6666666666666666,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":1.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.6666666666666666,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.3333333333333333,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.6666666666666666,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.3333333333333333,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":1.0,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.3333333333333333,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.3333333333333333,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.6666666666666666,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.6666666666666666,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":1.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.6666666666666666},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":4.7173248291666665,"costN":60,"usageEstimatedN":60,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":7.945794444444444,"timeN":60,"unreviewed":6,"releaseDate":"2026-09-01"},{"id":"GPT-6 Astra|max","name":"GPT-6 Astra","provider":"OpenAI","color":"#39786d","effort":"max","score":53.333333333333336,"ci":[33.33333333333333,71.66666666666667],"n":60,"successes":32.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.3333333333333333,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.6666666666666666,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":1.0,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.6666666666666666,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.3333333333333333,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":1.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":1.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":1.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.0,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":1.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":1.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":1.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":1.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.6666666666666666},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":4.7053981694915255,"costN":59,"usageEstimatedN":0,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":10.864758333333333,"timeN":60,"unreviewed":6,"releaseDate":"2026-09-03"},{"id":"GPT-6 Astra|medium","name":"GPT-6 Astra","provider":"OpenAI","color":"#39786d","effort":"medium","score":51.66666666666666,"ci":[33.33333333333333,70.0],"n":60,"successes":31.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.3333333333333333,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.3333333333333333,"002--frappe--07-desk-and-queue-outage-64526986":0.6666666666666666,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":1.0,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.6666666666666666,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.6666666666666666,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":1.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":1.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":1.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.0,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":1.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.3333333333333333,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.3333333333333333,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":1.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":1.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":3.069465149122807,"costN":57,"usageEstimatedN":0,"tierUncertainN":3,"allTaskCount":20,"allN":60,"minutes":5.872019444444445,"timeN":60,"unreviewed":6,"releaseDate":"2026-09-03"},{"id":"GPT-6 Astra|high","name":"GPT-6 Astra","provider":"OpenAI","color":"#39786d","effort":"high","score":50.0,"ci":[33.33333333333333,66.66666666666666],"n":60,"successes":30.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.3333333333333333,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.6666666666666666,"002--frappe--07-desk-and-queue-outage-64526986":0.6666666666666666,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":1.0,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.0,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.6666666666666666,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.6666666666666666,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":1.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":1.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.3333333333333333,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.6666666666666666,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.6666666666666666,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.6666666666666666,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.6666666666666666,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":1.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":3.699250807017544,"costN":57,"usageEstimatedN":0,"tierUncertainN":2,"allTaskCount":20,"allN":60,"minutes":6.926144444444445,"timeN":60,"unreviewed":6,"releaseDate":"2026-09-03"},{"id":"GPT-6 Sol|medium","name":"GPT-6 Sol","provider":"OpenAI","color":"#1a9b88","effort":"medium","score":46.666666666666664,"ci":[31.666666666666664,61.66666666666667],"n":60,"successes":28.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.6666666666666666,"002--frappe--07-desk-and-queue-outage-64526986":0.6666666666666666,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":1.0,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.3333333333333333,"005--frappe--07-writes-and-queue-oom-df74aa9f":1.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.6666666666666666,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.3333333333333333,"008--slack-spine--06-F4-maintenance-collision-cc222870":1.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":1.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.3333333333333333,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.6666666666666666,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.6666666666666666,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.3333333333333333,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.3333333333333333,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.3333333333333333},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":0.653509205,"costN":60,"usageEstimatedN":0,"tierUncertainN":1,"allTaskCount":20,"allN":60,"minutes":5.762794444444444,"timeN":60,"unreviewed":30,"releaseDate":"2026-09-22"},{"id":"Claude Opus 5.5|xhigh","name":"Claude Opus 5.5","provider":"Anthropic","color":"#dc7045","effort":"xhigh","score":43.333333333333336,"ci":[28.333333333333332,60.0],"n":60,"successes":26.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.6666666666666666,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.3333333333333333,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.0,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.3333333333333333,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":1.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":1.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.6666666666666666,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.3333333333333333,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.3333333333333333,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.3333333333333333,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.6666666666666666,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.6666666666666666,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":1.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":1.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.3333333333333333},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":4.814895076666667,"costN":60,"usageEstimatedN":60,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":14.405219444444445,"timeN":60,"unreviewed":37,"releaseDate":"2026-09-22"},{"id":"Claude Fable 5.1|xhigh","name":"Claude Fable 5.1","provider":"Anthropic","color":"#b66147","effort":"xhigh","score":43.33333333333333,"ci":[28.333333333333332,58.333333333333336],"n":60,"successes":26.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.3333333333333333,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.3333333333333333,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.6666666666666666,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.3333333333333333,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":1.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.6666666666666666,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":1.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":1.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.3333333333333333,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.6666666666666666,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.3333333333333333,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.6666666666666666,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.6666666666666666,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.6666666666666666,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":9.303344957627118,"costN":59,"usageEstimatedN":59,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":15.091841666666665,"timeN":60,"unreviewed":6,"releaseDate":"2026-09-01"},{"id":"Claude Fable 5.1|high","name":"Claude Fable 5.1","provider":"Anthropic","color":"#b66147","effort":"high","score":41.66666666666667,"ci":[25.0,60.0],"n":60,"successes":25.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.3333333333333333,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.3333333333333333,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.3333333333333333,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.3333333333333333,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.3333333333333333,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":1.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":1.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":1.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.3333333333333333,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":1.0,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.3333333333333333,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":1.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":1.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":6.549909425,"costN":60,"usageEstimatedN":60,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":11.029719444444446,"timeN":60,"unreviewed":6,"releaseDate":"2026-09-01"},{"id":"Claude Opus 5.5|max","name":"Claude Opus 5.5","provider":"Anthropic","color":"#dc7045","effort":"max","score":41.666666666666664,"ci":[23.333333333333332,60.0],"n":60,"successes":25.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.0,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":1.0,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.0,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.3333333333333333,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.6666666666666666,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":1.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":1.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.6666666666666666,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.6666666666666666,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.0,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.3333333333333333,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":1.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.3333333333333333,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":1.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.3333333333333333},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":8.299163123333333,"costN":60,"usageEstimatedN":60,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":21.19351388888889,"timeN":60,"unreviewed":39,"releaseDate":"2026-09-22"},{"id":"GPT-5.6 Sol|high","name":"GPT-5.6 Sol","provider":"OpenAI","color":"#60a296","effort":"high","score":41.666666666666664,"ci":[25.0,60.0],"n":60,"successes":25.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.3333333333333333,"002--frappe--07-desk-and-queue-outage-64526986":0.3333333333333333,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":1.0,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.6666666666666666,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.3333333333333333,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":1.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":1.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":1.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.3333333333333333,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":1.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.6666666666666666,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.6666666666666666},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":2.4572699333333334,"costN":57,"usageEstimatedN":0,"tierUncertainN":2,"allTaskCount":20,"allN":60,"minutes":7.686019444444444,"timeN":60,"unreviewed":6,"releaseDate":"2026-07-09"},{"id":"GPT-5.6 Terra|max","name":"GPT-5.6 Terra","provider":"OpenAI","color":"#97aaa1","effort":"max","score":41.666666666666664,"ci":[25.0,58.333333333333336],"n":60,"successes":25.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":1.0,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.6666666666666666,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.3333333333333333,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.0,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":1.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.6666666666666666,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.6666666666666666,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.3333333333333333,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.3333333333333333,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":1.0,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":1.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.6666666666666666,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.6666666666666666},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":2.219049924074074,"costN":54,"usageEstimatedN":0,"tierUncertainN":2,"allTaskCount":20,"allN":60,"minutes":12.752894444444445,"timeN":60,"unreviewed":6,"releaseDate":"2026-07-09"},{"id":"GPT-6 Sol|low","name":"GPT-6 Sol","provider":"OpenAI","color":"#1a9b88","effort":"low","score":41.666666666666664,"ci":[25.0,58.333333333333336],"n":60,"successes":25.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.3333333333333333,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.6666666666666666,"002--frappe--07-desk-and-queue-outage-64526986":0.3333333333333333,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.3333333333333333,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":1.0,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.6666666666666666,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.0,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":1.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.3333333333333333,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.6666666666666666,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.3333333333333333,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":1.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":1.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.6666666666666666},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":0.42812876,"costN":60,"usageEstimatedN":0,"tierUncertainN":2,"allTaskCount":20,"allN":60,"minutes":4.175822222222222,"timeN":60,"unreviewed":27,"releaseDate":"2026-09-22"},{"id":"GPT-6 Sol|high","name":"GPT-6 Sol","provider":"OpenAI","color":"#1a9b88","effort":"high","score":41.666666666666664,"ci":[26.666666666666668,58.333333333333336],"n":60,"successes":25.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.3333333333333333,"001--frappe--07-desk-and-queue-oom-0669b8e8":1.0,"002--frappe--07-desk-and-queue-outage-64526986":1.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.6666666666666666,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.0,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.6666666666666666,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.0,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.3333333333333333,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.6666666666666666,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.6666666666666666,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":1.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.3333333333333333,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.0,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":1.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.3333333333333333,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.3333333333333333,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":0.8564640711864407,"costN":59,"usageEstimatedN":0,"tierUncertainN":3,"allTaskCount":20,"allN":60,"minutes":8.013175,"timeN":60,"unreviewed":28,"releaseDate":"2026-09-22"},{"id":"Claude Fable 5.1|max","name":"Claude Fable 5.1","provider":"Anthropic","color":"#b66147","effort":"max","score":40.0,"ci":[21.666666666666668,60.0],"n":60,"successes":24.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.0,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.0,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.0,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.3333333333333333,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":1.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":1.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":1.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":1.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":1.0,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.6666666666666666,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.3333333333333333,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":1.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.6666666666666666,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":11.948579396551724,"costN":58,"usageEstimatedN":58,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":19.51866111111111,"timeN":60,"unreviewed":6,"releaseDate":"2026-09-01"},{"id":"Claude Opus 5.5|high","name":"Claude Opus 5.5","provider":"Anthropic","color":"#dc7045","effort":"high","score":40.0,"ci":[23.333333333333332,56.666666666666664],"n":60,"successes":24.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.3333333333333333,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":1.0,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.6666666666666666,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.3333333333333333,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.6666666666666666,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":1.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":1.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.3333333333333333,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.6666666666666666,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.3333333333333333,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.3333333333333333,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.3333333333333333,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":1.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":2.555906894915254,"costN":59,"usageEstimatedN":59,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":9.718377777777778,"timeN":60,"unreviewed":38,"releaseDate":"2026-09-22"},{"id":"Claude Opus 5.5|low","name":"Claude Opus 5.5","provider":"Anthropic","color":"#dc7045","effort":"low","score":38.33333333333333,"ci":[21.666666666666668,55.00000000000001],"n":60,"successes":23.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.3333333333333333,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.3333333333333333,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":1.0,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":1.0,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.3333333333333333,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.6666666666666666,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":1.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":1.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.6666666666666666,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.6666666666666666,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.3333333333333333,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.3333333333333333},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":0.82037111,"costN":60,"usageEstimatedN":60,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":4.265644444444444,"timeN":60,"unreviewed":35,"releaseDate":"2026-09-22"},{"id":"GPT-5.6 Sol|xhigh","name":"GPT-5.6 Sol","provider":"OpenAI","color":"#60a296","effort":"xhigh","score":38.33333333333333,"ci":[20.0,56.666666666666664],"n":60,"successes":23.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.3333333333333333,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.6666666666666666,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.3333333333333333,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.3333333333333333,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.6666666666666666,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":1.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":1.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":1.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.0,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":1.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":1.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.3333333333333333,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":3.0161968068965517,"costN":58,"usageEstimatedN":0,"tierUncertainN":2,"allTaskCount":20,"allN":60,"minutes":12.941772222222223,"timeN":60,"unreviewed":6,"releaseDate":"2026-07-09"},{"id":"GPT-6 Sol|xhigh","name":"GPT-6 Sol","provider":"OpenAI","color":"#1a9b88","effort":"xhigh","score":38.33333333333333,"ci":[21.666666666666668,55.00000000000001],"n":60,"successes":23.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.6666666666666666,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.3333333333333333,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":1.0,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.3333333333333333,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.0,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.3333333333333333,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":1.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":1.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.3333333333333333,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.0,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":1.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.3333333333333333,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.6666666666666666,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.6666666666666666},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":1.0320861559322034,"costN":59,"usageEstimatedN":0,"tierUncertainN":2,"allTaskCount":20,"allN":60,"minutes":10.00461111111111,"timeN":60,"unreviewed":28,"releaseDate":"2026-09-22"},{"id":"Claude Fable 5.1|low","name":"Claude Fable 5.1","provider":"Anthropic","color":"#b66147","effort":"low","score":36.666666666666664,"ci":[23.333333333333332,50.0],"n":60,"successes":22.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.3333333333333333,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.3333333333333333,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.6666666666666666,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.3333333333333333,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.6666666666666666,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":1.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.6666666666666666,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":1.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.3333333333333333,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.6666666666666666,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.3333333333333333,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.3333333333333333,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.3333333333333333,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.3333333333333333},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":3.864248827586207,"costN":58,"usageEstimatedN":58,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":6.956527777777778,"timeN":60,"unreviewed":6,"releaseDate":"2026-09-01"},{"id":"GPT-5.6 Sol|low","name":"GPT-5.6 Sol","provider":"OpenAI","color":"#60a296","effort":"low","score":36.666666666666664,"ci":[21.666666666666664,53.333333333333336],"n":60,"successes":22.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.3333333333333333,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.0,"002--frappe--07-desk-and-queue-outage-64526986":0.6666666666666666,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.6666666666666666,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.3333333333333333,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.3333333333333333,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":1.0,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":1.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.6666666666666666,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.0,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":1.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.3333333333333333,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.6666666666666666,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.3333333333333333},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":1.581917849122807,"costN":57,"usageEstimatedN":0,"tierUncertainN":1,"allTaskCount":20,"allN":60,"minutes":5.355213888888889,"timeN":60,"unreviewed":6,"releaseDate":"2026-07-09"},{"id":"GPT-5.6 Sol|medium","name":"GPT-5.6 Sol","provider":"OpenAI","color":"#60a296","effort":"medium","score":36.666666666666664,"ci":[25.0,50.0],"n":60,"successes":22.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.3333333333333333,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.0,"002--frappe--07-desk-and-queue-outage-64526986":0.3333333333333333,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.3333333333333333,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.3333333333333333,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.3333333333333333,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.6666666666666666,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.3333333333333333,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":1.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.3333333333333333,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.3333333333333333,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":1.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.6666666666666666,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.6666666666666666,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.3333333333333333,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.3333333333333333},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":2.1204213929824562,"costN":57,"usageEstimatedN":0,"tierUncertainN":3,"allTaskCount":20,"allN":60,"minutes":6.710222222222223,"timeN":60,"unreviewed":6,"releaseDate":"2026-07-09"},{"id":"GPT-6 Sol|max","name":"GPT-6 Sol","provider":"OpenAI","color":"#1a9b88","effort":"max","score":36.666666666666664,"ci":[20.0,53.333333333333336],"n":59,"successes":22.0,"taskCount":20,"expectedN":60,"pendingN":1,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.6666666666666666,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":1.0,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.3333333333333333,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.3333333333333333,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.6666666666666666,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":1.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.6666666666666666,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.3333333333333333,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":1.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.3333333333333333,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":1.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":2,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":1.2706802379310345,"costN":58,"usageEstimatedN":0,"tierUncertainN":3,"allTaskCount":20,"allN":59,"minutes":11.208217514124295,"timeN":59,"unreviewed":26,"releaseDate":"2026-09-22"},{"id":"GPT-5.6 Sol|max","name":"GPT-5.6 Sol","provider":"OpenAI","color":"#60a296","effort":"max","score":35.0,"ci":[20.0,51.66666666666666],"n":60,"successes":21.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.3333333333333333,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.3333333333333333,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.6666666666666666,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.3333333333333333,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.3333333333333333,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":1.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":1.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":1.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.3333333333333333,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":1.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.3333333333333333,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.3333333333333333,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":4.275781941818182,"costN":55,"usageEstimatedN":0,"tierUncertainN":3,"allTaskCount":20,"allN":60,"minutes":14.029213888888888,"timeN":60,"unreviewed":6,"releaseDate":"2026-07-09"},{"id":"Claude Opus 5|low","name":"Claude Opus 5","provider":"Anthropic","color":"#cf986f","effort":"low","score":31.666666666666664,"ci":[18.333333333333332,44.99999999999999],"n":60,"successes":19.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.6666666666666666,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.3333333333333333,"002--frappe--07-desk-and-queue-outage-64526986":0.3333333333333333,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":1.0,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.3333333333333333,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.6666666666666666,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.3333333333333333,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.6666666666666666,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.6666666666666666,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.3333333333333333,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.6666666666666666,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.3333333333333333,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":2.2518308103448277,"costN":58,"usageEstimatedN":58,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":6.261136111111111,"timeN":60,"unreviewed":6,"releaseDate":"2026-07-24"},{"id":"GPT-5.6 Terra|xhigh","name":"GPT-5.6 Terra","provider":"OpenAI","color":"#97aaa1","effort":"xhigh","score":30.0,"ci":[16.666666666666664,43.33333333333333],"n":60,"successes":18.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.6666666666666666,"002--frappe--07-desk-and-queue-outage-64526986":0.6666666666666666,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.6666666666666666,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.0,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.3333333333333333,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.6666666666666666,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.6666666666666666,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.3333333333333333,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.6666666666666666,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.3333333333333333,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.3333333333333333,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.6666666666666666},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":1.279756475862069,"costN":58,"usageEstimatedN":0,"tierUncertainN":3,"allTaskCount":20,"allN":60,"minutes":8.436877777777777,"timeN":60,"unreviewed":6,"releaseDate":"2026-07-09"},{"id":"GLM-5.3|medium","name":"GLM-5.3","provider":"Z.ai","color":"#8673b3","effort":"medium","score":28.333333333333332,"ci":[13.333333333333334,43.333333333333336],"n":60,"successes":17.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.6666666666666666,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.3333333333333333,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.0,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.3333333333333333,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.6666666666666666,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":1.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.3333333333333333,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.6666666666666666,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.0,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.6666666666666666,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":1.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":11.549463530526316,"costN":57,"usageEstimatedN":57,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":16.506166666666665,"timeN":60,"unreviewed":6,"releaseDate":"2026-08-14"},{"id":"GPT-5.6 Terra|medium","name":"GPT-5.6 Terra","provider":"OpenAI","color":"#97aaa1","effort":"medium","score":28.333333333333332,"ci":[15.0,41.666666666666664],"n":60,"successes":17.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.3333333333333333,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.6666666666666666,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":1.0,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.0,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.6666666666666666,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.3333333333333333,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.6666666666666666,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.3333333333333333,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.6666666666666666,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.3333333333333333,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.3333333333333333,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.3333333333333333},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":0.7257046271186441,"costN":59,"usageEstimatedN":0,"tierUncertainN":3,"allTaskCount":20,"allN":60,"minutes":3.543272222222222,"timeN":60,"unreviewed":6,"releaseDate":"2026-07-09"},{"id":"Claude Opus 5|max","name":"Claude Opus 5","provider":"Anthropic","color":"#cf986f","effort":"max","score":26.666666666666668,"ci":[15.0,38.33333333333333],"n":60,"successes":16.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.3333333333333333,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.3333333333333333,"002--frappe--07-desk-and-queue-outage-64526986":0.3333333333333333,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.6666666666666666,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.3333333333333333,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.3333333333333333,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.6666666666666666,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.6666666666666666,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.6666666666666666,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.3333333333333333,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.6666666666666666,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":3.406733465517241,"costN":58,"usageEstimatedN":58,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":10.052016666666667,"timeN":60,"unreviewed":6,"releaseDate":"2026-07-24"},{"id":"Claude Opus 5|high","name":"Claude Opus 5","provider":"Anthropic","color":"#cf986f","effort":"high","score":25.0,"ci":[13.333333333333334,38.33333333333333],"n":60,"successes":15.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.3333333333333333,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.3333333333333333,"002--frappe--07-desk-and-queue-outage-64526986":0.3333333333333333,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":1.0,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.3333333333333333,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.3333333333333333,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.3333333333333333,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.3333333333333333,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.3333333333333333,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.3333333333333333,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":1.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":2.8510030889830507,"costN":59,"usageEstimatedN":59,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":7.712741666666667,"timeN":60,"unreviewed":6,"releaseDate":"2026-07-24"},{"id":"GLM-5.3|high","name":"GLM-5.3","provider":"Z.ai","color":"#8673b3","effort":"high","score":25.0,"ci":[11.666666666666666,40.0],"n":60,"successes":15.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.0,"002--frappe--07-desk-and-queue-outage-64526986":0.3333333333333333,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.3333333333333333,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.0,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.3333333333333333,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":1.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.6666666666666666,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.3333333333333333,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.6666666666666666,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.6666666666666666,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.6666666666666666,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":11.443684541016948,"costN":59,"usageEstimatedN":59,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":20.294369444444445,"timeN":60,"unreviewed":6,"releaseDate":"2026-08-14"},{"id":"GLM-5.3|xhigh","name":"GLM-5.3","provider":"Z.ai","color":"#8673b3","effort":"xhigh","score":25.0,"ci":[11.666666666666666,40.0],"n":60,"successes":15.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.0,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":1.0,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.3333333333333333,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.0,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.3333333333333333,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.3333333333333333,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.6666666666666666,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":1.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.3333333333333333,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.6666666666666666,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.3333333333333333,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":10.135644831333332,"costN":60,"usageEstimatedN":60,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":24.89546111111111,"timeN":60,"unreviewed":6,"releaseDate":"2026-08-14"},{"id":"Grok 4.7|low","name":"Grok 4.7","provider":"xAI","color":"#657487","effort":"low","score":25.0,"ci":[10.0,40.0],"n":60,"successes":15.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.0,"002--frappe--07-desk-and-queue-outage-64526986":0.3333333333333333,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":1.0,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.6666666666666666,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.3333333333333333,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.3333333333333333,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.6666666666666666,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.6666666666666666,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":1.0,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":3.4397350666666666,"costN":45,"usageEstimatedN":0,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":10.185122222222223,"timeN":60,"unreviewed":27,"releaseDate":"2026-09-21"},{"id":"Muse Spark 1.3|max","name":"Muse Spark 1.3","provider":"Meta","color":"#467fc1","effort":"max","score":25.0,"ci":[11.666666666666666,40.0],"n":60,"successes":15.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.3333333333333333,"001--frappe--07-desk-and-queue-oom-0669b8e8":1.0,"002--frappe--07-desk-and-queue-outage-64526986":0.3333333333333333,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.6666666666666666,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.3333333333333333,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.6666666666666666,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.6666666666666666,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.0,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":1.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":0.268858265,"costN":60,"usageEstimatedN":0,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":1.992902777777778,"timeN":60,"unreviewed":24,"releaseDate":"2026-09-02"},{"id":"GLM-5.3|max","name":"GLM-5.3","provider":"Z.ai","color":"#8673b3","effort":"max","score":23.333333333333332,"ci":[11.666666666666666,35.0],"n":60,"successes":14.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.3333333333333333,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.6666666666666666,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.6666666666666666,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.0,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.6666666666666666,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.3333333333333333,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.3333333333333333,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.3333333333333333,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.0,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.6666666666666666,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.3333333333333333,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.3333333333333333,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":9.862438489152542,"costN":59,"usageEstimatedN":59,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":25.01635,"timeN":60,"unreviewed":6,"releaseDate":"2026-08-14"},{"id":"Grok 4.7|xhigh","name":"Grok 4.7","provider":"xAI","color":"#657487","effort":"xhigh","score":23.333333333333332,"ci":[8.333333333333332,40.0],"n":60,"successes":14.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.3333333333333333,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.0,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":1.0,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.3333333333333333,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.3333333333333333,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":1.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":1.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.6666666666666666,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":6.305022761904762,"costN":42,"usageEstimatedN":0,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":17.90011666666667,"timeN":60,"unreviewed":27,"releaseDate":"2026-09-21"},{"id":"GPT-5.6 Terra|low","name":"GPT-5.6 Terra","provider":"OpenAI","color":"#97aaa1","effort":"low","score":21.666666666666668,"ci":[8.333333333333332,36.666666666666664],"n":60,"successes":13.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.3333333333333333,"002--frappe--07-desk-and-queue-outage-64526986":0.3333333333333333,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.0,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.0,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.3333333333333333,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.6666666666666666,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":1.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.0,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":1.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.6666666666666666},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":0.6096556916666667,"costN":60,"usageEstimatedN":0,"tierUncertainN":1,"allTaskCount":20,"allN":60,"minutes":3.0403888888888893,"timeN":60,"unreviewed":6,"releaseDate":"2026-07-09"},{"id":"GPT-5.6 Terra|high","name":"GPT-5.6 Terra","provider":"OpenAI","color":"#97aaa1","effort":"high","score":21.666666666666664,"ci":[10.0,35.0],"n":60,"successes":13.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.6666666666666666,"002--frappe--07-desk-and-queue-outage-64526986":0.3333333333333333,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.3333333333333333,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.3333333333333333,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.0,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.6666666666666666,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.6666666666666666,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":1.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.3333333333333333,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":1.1481346101694916,"costN":59,"usageEstimatedN":0,"tierUncertainN":2,"allTaskCount":20,"allN":60,"minutes":6.287333333333334,"timeN":60,"unreviewed":6,"releaseDate":"2026-07-09"},{"id":"Claude Opus 5|medium","name":"Claude Opus 5","provider":"Anthropic","color":"#cf986f","effort":"medium","score":20.0,"ci":[8.333333333333332,33.33333333333333],"n":60,"successes":12.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.3333333333333333,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.6666666666666666,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.3333333333333333,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.0,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.3333333333333333,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.3333333333333333,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.3333333333333333,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":1.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.6666666666666666,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":2.802289686440678,"costN":59,"usageEstimatedN":59,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":7.918369444444445,"timeN":60,"unreviewed":6,"releaseDate":"2026-07-24"},{"id":"Claude Opus 5|xhigh","name":"Claude Opus 5","provider":"Anthropic","color":"#cf986f","effort":"xhigh","score":16.666666666666664,"ci":[6.666666666666667,28.333333333333332],"n":60,"successes":10.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.6666666666666666,"002--frappe--07-desk-and-queue-outage-64526986":0.6666666666666666,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.3333333333333333,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.0,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.3333333333333333,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.0,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.6666666666666666,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.3333333333333333,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.3333333333333333,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":3.172811763157895,"costN":57,"usageEstimatedN":57,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":8.430961111111111,"timeN":60,"unreviewed":6,"releaseDate":"2026-07-24"},{"id":"GLM-5.3|low","name":"GLM-5.3","provider":"Z.ai","color":"#8673b3","effort":"low","score":16.666666666666664,"ci":[6.666666666666667,28.333333333333332],"n":60,"successes":10.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.3333333333333333,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.6666666666666666,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.6666666666666666,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.0,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.3333333333333333,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.3333333333333333,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.6666666666666666,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.0,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.3333333333333333,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":7.423047233333333,"costN":57,"usageEstimatedN":57,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":13.533233333333333,"timeN":60,"unreviewed":6,"releaseDate":"2026-08-14"},{"id":"Grok 4.7|medium","name":"Grok 4.7","provider":"xAI","color":"#657487","effort":"medium","score":13.333333333333334,"ci":[3.3333333333333335,25.0],"n":60,"successes":8.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.3333333333333333,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.6666666666666666,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.0,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.0,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.6666666666666666,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.6666666666666666,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.3333333333333333,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":4.669354,"costN":44,"usageEstimatedN":0,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":12.897655555555556,"timeN":60,"unreviewed":27,"releaseDate":"2026-09-21"},{"id":"Muse Spark 1.3|xhigh","name":"Muse Spark 1.3","provider":"Meta","color":"#467fc1","effort":"xhigh","score":13.333333333333334,"ci":[1.6666666666666667,26.666666666666668],"n":60,"successes":8.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.0,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":1.0,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.0,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.6666666666666666,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.6666666666666666,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.0,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.3333333333333333,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":0.8533420791666666,"costN":60,"usageEstimatedN":0,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":38.270361111111114,"timeN":60,"unreviewed":24,"releaseDate":"2026-09-02"},{"id":"Grok 4.7|high","name":"Grok 4.7","provider":"xAI","color":"#657487","effort":"high","score":11.666666666666666,"ci":[1.6666666666666667,23.333333333333332],"n":60,"successes":7.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.0,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.3333333333333333,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.0,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.6666666666666666,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.6666666666666666,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.6666666666666666,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.0,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":5.474280540540541,"costN":37,"usageEstimatedN":0,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":16.429419444444445,"timeN":60,"unreviewed":27,"releaseDate":"2026-09-21"},{"id":"Muse Spark 1.3|low","name":"Muse Spark 1.3","provider":"Meta","color":"#467fc1","effort":"low","score":11.666666666666666,"ci":[1.6666666666666667,23.333333333333332],"n":60,"successes":7.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.6666666666666666,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.6666666666666666,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.3333333333333333,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.0,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.6666666666666666,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.0,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":0.616480145,"costN":60,"usageEstimatedN":0,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":32.49355555555555,"timeN":60,"unreviewed":24,"releaseDate":"2026-09-02"},{"id":"Muse Spark 1.3|medium","name":"Muse Spark 1.3","provider":"Meta","color":"#467fc1","effort":"medium","score":10.0,"ci":[1.6666666666666667,21.666666666666668],"n":60,"successes":6.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.0,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.3333333333333333,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.3333333333333333,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.0,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":1.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.0,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.3333333333333333},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":0.713007255,"costN":60,"usageEstimatedN":0,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":31.39070277777778,"timeN":60,"unreviewed":24,"releaseDate":"2026-09-02"},{"id":"Muse Spark 1.3|high","name":"Muse Spark 1.3","provider":"Meta","color":"#467fc1","effort":"high","score":10.0,"ci":[1.6666666666666667,20.0],"n":60,"successes":6.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.0,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.6666666666666666,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.0,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.3333333333333333,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.6666666666666666,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.0,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.3333333333333333,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.0,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":0.790957915,"costN":60,"usageEstimatedN":0,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":34.39953055555556,"timeN":60,"unreviewed":24,"releaseDate":"2026-09-02"},{"id":"Muse Spark 1.3|minimal","name":"Muse Spark 1.3","provider":"Meta","color":"#467fc1","effort":"minimal","score":5.0,"ci":[0.0,10.0],"n":60,"successes":3.0,"taskCount":20,"expectedN":60,"pendingN":0,"taskMeans":{"000--frappe--07-deletes-and-jobs-fail-194d9279":0.0,"001--frappe--07-desk-and-queue-oom-0669b8e8":0.3333333333333333,"002--frappe--07-desk-and-queue-outage-64526986":0.0,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":0.3333333333333333,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":0.0,"005--frappe--07-writes-and-queue-oom-df74aa9f":0.0,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":0.0,"007--slack-spine--06-F3-split-sequencer-eef5b438":0.0,"008--slack-spine--06-F4-maintenance-collision-cc222870":0.0,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":0.0,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":0.0,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":0.0,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":0.0,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":0.0,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":0.0,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":0.0,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":0.0,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":0.0,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":0.3333333333333333,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":0.0},"taskTrialCounts":{"000--frappe--07-deletes-and-jobs-fail-194d9279":3,"001--frappe--07-desk-and-queue-oom-0669b8e8":3,"002--frappe--07-desk-and-queue-outage-64526986":3,"003--frappe--07-new-records-and-jobs-fail-f3320b4c":3,"004--frappe--07-new-records-and-queue-oom-8ccfd9e7":3,"005--frappe--07-writes-and-queue-oom-df74aa9f":3,"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4":3,"007--slack-spine--06-F3-split-sequencer-eef5b438":3,"008--slack-spine--06-F4-maintenance-collision-cc222870":3,"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23":3,"010--slack-spine--06-logins-unread-sends-slower-cccddfb2":3,"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480":3,"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739":3,"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739":3,"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235":3,"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c":3,"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383":3,"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9":3,"018--slack-spine--09-I1-seq-lock-leak-0b7c2973":3,"019--slack-spine--13-P1-distractor-volume-shell-f73987d7":3},"cost":0.6770170025,"costN":60,"usageEstimatedN":0,"tierUncertainN":0,"allTaskCount":20,"allN":60,"minutes":33.482366666666664,"timeN":60,"unreviewed":24,"releaseDate":"2026-09-02"}],"tasks":[{"id":"000--frappe--07-deletes-and-jobs-fail-194d9279","number":0,"title":"Deletes fail. Jobs stop.","slug":"000--frappe--07-deletes-and-jobs-fail","system":"Frappe","version":13,"score":19.333333333333332,"n":150,"hasSample":true,"sampleModel":"GPT-6 Astra","summary":"Deleting anything in Frappe returns an error. Records can still be created and edited, and browsing, search, and dashboards all work. Nothing handed to the background completes either: queued emails and report exports never arrive, and scheduled jobs do not run."},{"id":"001--frappe--07-desk-and-queue-oom-0669b8e8","number":1,"title":"Desk errors & queue exhaustion","slug":"001--frappe--07-desk-and-queue-oom","system":"Frappe","version":13,"score":42.0,"n":150,"hasSample":false,"sampleModel":null,"summary":"When traffic gets busy, pages that worked a moment ago start returning errors and some users are refused outright. Browsing, search, and dashboards recover once the rush passes. Background work stays stuck even when traffic is quiet: queued emails, report exports, and scheduled jobs never run."},{"id":"002--frappe--07-desk-and-queue-outage-64526986","number":2,"title":"Desk & background queue outage","slug":"002--frappe--07-desk-and-queue-outage","system":"Frappe","version":13,"score":21.333333333333336,"n":150,"hasSample":true,"sampleModel":"GPT-6 Astra","summary":"Busy periods are knocking users out of Desk. Pages that worked a moment earlier return errors until traffic settles, then browsing, search, and dashboards recover. Background work is broken even during quiet hours: queued emails and report exports never arrive, and scheduled jobs do not run."},{"id":"003--frappe--07-new-records-and-jobs-fail-f3320b4c","number":3,"title":"New records & jobs fail","slug":"003--frappe--07-new-records-and-jobs-fail","system":"Frappe","version":20,"score":68.0,"n":150,"hasSample":true,"sampleModel":"Claude Fable 5.1","summary":"Creating anything new in Frappe returns an error, including records, comments, and uploads. Existing records can still be edited, and browsing works. Background submissions are accepted, but queued emails, exports, and scheduled jobs never finish."},{"id":"004--frappe--07-new-records-and-queue-oom-8ccfd9e7","number":4,"title":"New records & queue exhaustion","slug":"004--frappe--07-new-records-and-queue-oom","system":"Frappe","version":13,"score":33.33333333333333,"n":150,"hasSample":true,"sampleModel":"GPT-6 Astra","summary":"People can still edit existing records and use browsing, search, and dashboards. Creating something new is broken: records, comments, and file uploads all return a server error. Background work has stopped too: queued emails, report exports, and scheduled jobs sit without ever running."},{"id":"005--frappe--07-writes-and-queue-oom-df74aa9f","number":5,"title":"Writes fail & queues fill up","slug":"005--frappe--07-writes-and-queue-oom","system":"Frappe","version":18,"score":10.0,"n":150,"hasSample":false,"sampleModel":null,"summary":"Saving anything in Frappe now fails. Edits, comments, and new records all return errors, though browsing, search, and dashboards still work. Background work has stopped too: queued emails, report exports, and scheduled jobs sit without ever running."},{"id":"006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4","number":6,"title":"Statement timeout canary","slug":"006--saleor-spine--10-T1-statement-timeout-canary","system":"Saleor","version":14,"score":35.333333333333336,"n":150,"hasSample":true,"sampleModel":"GPT-6 Astra","summary":"Checkout failures line up with storefront traffic spikes, but they\u2019re intermittent. Between bursts, the Saleor API looks healthy. That\u2019s made the cause hard to catch."},{"id":"007--slack-spine--06-F3-split-sequencer-eef5b438","number":7,"title":"Split sequencer","slug":"007--slack-spine--06-F3-split-sequencer","system":"Slack","version":8,"score":1.3333333333333335,"n":150,"hasSample":true,"sampleModel":"GPT-6 Astra","summary":"Normal traffic looks fine, but concurrent sends keep making message delivery unreliable. Track down the problem and fix it without losing any accepted messages or changing their order. Make sure the repair survives a message-service restart and stays healthy while traffic continues."},{"id":"008--slack-spine--06-F4-maintenance-collision-cc222870","number":8,"title":"Maintenance collision","slug":"008--slack-spine--06-F4-maintenance-collision","system":"Slack","version":8,"score":66.0,"n":150,"hasSample":true,"sampleModel":"GPT-6 Astra","summary":"Message writes slow down during each recurring peak, then recover on their own. Track down the pattern and fix it without disabling routine maintenance. Message delivery and maintenance both need to stay healthy when the next peak arrives."},{"id":"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23","number":9,"title":"Logins, unread counts & sends slow","slug":"009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon","system":"Slack","version":9,"score":56.666666666666664,"n":150,"hasSample":true,"sampleModel":"Muse Spark 1.3","summary":"Around noon, signing in, loading unread counts, and sending messages into busy channels all slowed down together. Nothing was deployed."},{"id":"010--slack-spine--06-logins-unread-sends-slower-cccddfb2","number":10,"title":"Every interaction gets slower","slug":"010--slack-spine--06-logins-unread-sends-slower","system":"Slack","version":9,"score":54.0,"n":150,"hasSample":true,"sampleModel":"Claude Fable 5.1","summary":"The workspace has felt slow since around noon. Sign-ins lag, unread counts take a beat to load, and sending a message into a busy channel drags. All three symptoms started at the same time, with no deployment."},{"id":"011--slack-spine--06-sends-crawl-then-store-slows-3e65c480","number":11,"title":"Sends crawl. Then storage slows.","slug":"011--slack-spine--06-sends-crawl-then-store-slows","system":"Slack","version":9,"score":22.666666666666664,"n":150,"hasSample":true,"sampleModel":"GPT-6 Astra","summary":"Message sends worked normally all morning. At one specific moment they began failing outright, and sign-ins became slow at exactly the same time. Neither has recovered, and there was no deployment."},{"id":"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739","number":12,"title":"Strict mode, plausible pool","slug":"012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool","system":"Slack","version":9,"score":6.0,"n":150,"hasSample":true,"sampleModel":"GPT-6 Astra","summary":"Message sends were normal all morning. Then they all began failing at the same moment, and none have recovered. Nothing was deployed."},{"id":"013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739","number":13,"title":"Strict mode breaks sends","slug":"013--slack-spine--06-sends-fail-after-strict-mode-turns-on","system":"Slack","version":9,"score":33.33333333333333,"n":150,"hasSample":true,"sampleModel":"GPT-6 Astra","summary":"Message sends worked normally all morning. At one particular moment they stopped working completely. This is an outright failure rather than a slowdown, and sends have not recovered since. Nothing was deployed."},{"id":"014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235","number":14,"title":"Compliance window failures","slug":"014--slack-spine--06-sends-fail-during-compliance-window","system":"Slack","version":8,"score":58.666666666666664,"n":150,"hasSample":true,"sampleModel":"GPT-6 Astra","summary":"Today\u2019s compliance window is active again, so the channel service is running in strict read-consistency mode during busy periods. Policy requires this, and the window must stay on. While it is active, message sends hang and then fail. They recover the moment it is switched off, but turning it off is not allowed."},{"id":"015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c","number":15,"title":"Strict mode, pool of sixteen","slug":"015--slack-spine--06-sends-fail-strict-pool-16","system":"Slack","version":8,"score":4.697986577181208,"n":149,"hasSample":true,"sampleModel":"GPT-6 Astra","summary":"Message sends were normal all morning. Then they all began failing at the same moment, and none have recovered. Nothing was deployed."},{"id":"016--slack-spine--06-sends-slow-and-stall-every-minute-83867383","number":16,"title":"Slow sends & periodic stalls","slug":"016--slack-spine--06-sends-slow-and-stall-every-minute","system":"Slack","version":8,"score":19.333333333333332,"n":150,"hasSample":true,"sampleModel":"GPT-6 Astra","summary":"During busy periods, sending a message hangs for many seconds and sometimes times out. It goes back to normal once traffic settles. There is another pattern too: sends that do get through freeze for several seconds at the same point in each busy period, about once a minute. People have learned to wait it out, and quiet days have not made it go away."},{"id":"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9","number":17,"title":"Minute-long stalls become a crawl","slug":"017--slack-spine--06-stall-every-minute-and-later-every-send-crawls","system":"Slack","version":8,"score":30.666666666666664,"n":150,"hasSample":true,"sampleModel":"GPT-6 Astra","summary":"Sends are still going through, but they freeze for several seconds at the same point in each busy period. The stall comes about once a minute. A few minutes into the working day, every send also started to crawl regardless of traffic, and that slowdown has stayed with us."},{"id":"018--slack-spine--09-I1-seq-lock-leak-0b7c2973","number":18,"title":"Sequencer lock leak","slug":"018--slack-spine--09-I1-seq-lock-leak","system":"Slack","version":8,"score":44.0,"n":150,"hasSample":true,"sampleModel":"GPT-6 Astra","summary":"Message delivery keeps going flaky even though traffic looks normal. Track down"},{"id":"019--slack-spine--13-P1-distractor-volume-shell-f73987d7","number":19,"title":"The distracting volume","slug":"019--slack-spine--13-P1-distractor-volume-shell","system":"Slack","version":8,"score":27.333333333333332,"n":150,"hasSample":true,"sampleModel":"GPT-6 Astra","summary":"The message delivery path has been flaky even though traffic looks normal."}],"pricing":{"checkedAt":"2026-09-23","currency":"USD","unit":"per million tokens","tier":"Public standard API; no batch, contributor, regional, or negotiated discounts","rates":[{"name":"GPT-6 Astra","input":10,"cached":1,"write":12.5,"output":50,"threshold":272000,"longInputMultiplier":2,"longOutputMultiplier":1.5,"source":"https://developers.openai.com/api/docs/models/gpt-6-astra"},{"name":"GPT-6 Sol","input":2,"cached":0.2,"write":2.5,"output":10,"threshold":272000,"longInputMultiplier":2,"longOutputMultiplier":1.5,"source":"https://developers.openai.com/api/docs/models/gpt-6-sol"},{"name":"GPT-5.6 Sol","input":4,"cached":0.4,"write":5,"output":20,"threshold":272000,"longInputMultiplier":2,"longOutputMultiplier":1.5,"source":"https://developers.openai.com/api/docs/models/gpt-5.6-sol"},{"name":"GPT-5.6 Terra","input":2,"cached":0.2,"write":2.5,"output":12,"threshold":272000,"longInputMultiplier":2,"longOutputMultiplier":1.5,"source":"https://developers.openai.com/api/docs/models/gpt-5.6-terra"},{"name":"Claude Fable 5.1","input":10,"cached":0.25,"write":12.5,"writeHour":20,"output":50,"source":"https://platform.claude.com/docs/en/about-claude/pricing"},{"name":"Claude Opus 5.5","input":4,"cached":0.2,"write":5,"writeHour":8,"output":20,"source":"https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5"},{"name":"Claude Opus 5","input":5,"cached":0.5,"write":6.25,"writeHour":10,"output":25,"source":"https://platform.claude.com/docs/en/about-claude/pricing"},{"name":"GLM-5.3","input":1.4,"cached":0.26,"write":null,"output":4.4,"source":"https://fireworks.ai/models/fireworks/glm-5p3"},{"name":"Muse Spark 1.3","input":1.25,"cached":0.15,"write":null,"output":4.25,"source":"https://dev.meta.ai/docs/pricing-rate-limits"},{"name":"Grok 4.7","input":2,"cached":0.5,"write":null,"output":6,"threshold":200000,"longInputMultiplier":2,"longOutputMultiplier":2,"source":"https://docs.x.ai/developers/release-notes"}],"notes":["GPT-5.6 Sol uses the current promotional standard rate, guaranteed by OpenAI at least through November 21, 2026.","Input tokens are split into uncached reads, cached reads, 5-minute cache writes and 1-hour cache writes before pricing; each token is charged once.","Reasoning tokens are included in completion/output tokens and are not added a second time.","Long-context premiums are applied per request, never to cumulative trial input. Aggregate-only records use base rates and are identified as tier-uncertain.","GLM logs with zero reported usage use the public zai-org/GLM-5.3 tokenizer on the visible conversation, with no assumed cache savings. Unlogged system prompts/tool definitions and context truncation cannot be recovered; these are transcript-based estimates, not provider-metered usage.","Anthropic output counters in these logs often capture only the start of streamed output. When visible output tokenization exceeds that counter, output is estimated with cl100k_base; input, cache reads, and cache-write counts remain provider-reported.","No-op and oracle costs, environment compute, and QA/verifier charges are excluded. These estimates are public-API-equivalent model costs, not invoices."]},"efforts":["minimal","low","medium","high","xhigh","max"],"counts":{"trials":3000,"pending":1,"settings":50,"eligible":2882,"rankedTrials":2999,"rankedTasks":20,"rankedTaskIds":["000--frappe--07-deletes-and-jobs-fail-194d9279","001--frappe--07-desk-and-queue-oom-0669b8e8","002--frappe--07-desk-and-queue-outage-64526986","003--frappe--07-new-records-and-jobs-fail-f3320b4c","004--frappe--07-new-records-and-queue-oom-8ccfd9e7","005--frappe--07-writes-and-queue-oom-df74aa9f","006--saleor-spine--10-T1-statement-timeout-canary-c7dcd6d4","007--slack-spine--06-F3-split-sequencer-eef5b438","008--slack-spine--06-F4-maintenance-collision-cc222870","009--slack-spine--06-logins-unread-and-sends-all-slow-since-noon-16e3fd23","010--slack-spine--06-logins-unread-sends-slower-cccddfb2","011--slack-spine--06-sends-crawl-then-store-slows-3e65c480","012--slack-spine--06-sends-fail-after-strict-mode-plausible-pool-d18e8739","013--slack-spine--06-sends-fail-after-strict-mode-turns-on-728f0739","014--slack-spine--06-sends-fail-during-compliance-window-1f4b1235","015--slack-spine--06-sends-fail-strict-pool-16-66fa1a7c","016--slack-spine--06-sends-slow-and-stall-every-minute-83867383","017--slack-spine--06-stall-every-minute-and-later-every-send-crawls-bd50bae9","018--slack-spine--09-I1-seq-lock-leak-0b7c2973","019--slack-spine--13-P1-distractor-volume-shell-f73987d7"],"rawLogInfraFailures":36,"controls":40,"families":10,"excluded":{"HARNESS_ERROR":37,"BAD_FAILURE":37,"BAD_SUCCESS":7,"RAW_LOG_INFRA_FAILURE":36},"qa":{"GOOD_FAILURE":1378,"GOOD_SUCCESS":782,"HARNESS_ERROR":37,"UNREVIEWED":758,"BAD_FAILURE":37,"BAD_SUCCESS":7}},"methodology":{"ci":"95% task-cluster percentile bootstrap: 10,000 resamples, fixed seed 6400447, with bounds at the 2.5th and 97.5th percentiles (2.5% in each tail). Each sampled task carries all its repeated trials together. This estimates task-sampling uncertainty for similar incidents, not repeatability on this fixed suite. Only 20 tasks are available, and related incident variants may weaken independence. Best-per-model intervals are not adjusted for selecting the highest-scoring effort.","score":"Headline raw pass@1 is the equal-weight mean of per-task success fractions across all 20 tasks, with 3 trials per task. For configurations with all 60 trials complete, this equals successes / 60. In-progress trials are excluded until a final reward is available; partially completed settings are marked provisional. It measures success on one attempt, not whether any of three attempts passed. Original rewards are retained without QA exclusions.","cost":"Model costs are estimated from reported or reconstructed token usage at public API rates. Averages use trials with available usage; coverage is shown for each configuration.","time":"Mean recorded agent-execution minutes per trial across all 20 tasks; environment setup and verifier time excluded.","pareto":"A configuration is dominated when another has no higher resource use and no lower score, with at least one strict improvement. Frontier calculated across all configurations on all 20 tasks, regardless of family."}}