← Back to benchmark

Raw run data

Every individual run — read only. Click a row to inspect its scores, checker verdict, efficiency, and final report.

126 of 126 runs

Per-metric comparison

Success

codex
97%
claude
95%
cursor
81%

Evidence rigor

codex
100%
claude
85%
cursor
83%

Adherence

claude
100%
codex
100%
cursor
93%

Tokens

cursor
763,708
codex
1,198,552
claude
1,221,837

Agent time

codex
140s
cursor
147s
claude
279s

Commands

codex
39.4
claude
54.3
cursor
79.8
RunTaskAgentArmSuccessAdher.RigorTokensCostAgent timeCmds
2026-10-19T14:51:59.588Z
s4-persistence-huntclaudeno-skill110.51,247,383$2.716378.4s43
2026-10-19T15:04:36.924Z
s4-persistence-huntcursorskill0.7110530,356~$0.51274.5s62
2026-10-19T15:07:54.169Z
s4-persistence-huntclaudeskill110.51,321,701$1.117226.2s41 (2)
2026-10-19T15:13:46.813Z
s4-persistence-huntcursorno-skill0.7911190,237~$0.31863.6s47
2026-10-19T15:44:55.222Z
s4-persistence-huntcodexskill1111,002,665—130.1s41 (1)
2026-10-19T15:49:09.648Z
s4-persistence-huntcodexno-skill111445,896—90.6s15
2026-10-19T16:13:02.544Z
s6-pipeline-oidcclaudeskill1111,049,472$0.947302.6s38 (3)
2026-10-19T16:20:08.745Z
s6-pipeline-oidccursorskill111775,673~$0.67993.2s74 (2)
2026-10-19T16:23:45.890Z
s6-pipeline-oidcclaudeno-skill0.9510.5675,397$1.413242.2s38 (3)
2026-10-19T16:30:51.782Z
s6-pipeline-oidccodexno-skill111767,982—116.4s48 (1)
2026-10-19T16:38:11.743Z
s6-pipeline-oidccodexskill1111,519,145—178.6s53 (1)
2026-10-19T17:08:16.812Z
s6-pipeline-oidcclaudeno-skill111424,452$0.536150.1s28
2026-10-19T18:12:33.978Z
s4-persistence-huntcodexno-skill111344,711—84.7s24 (1)
2026-10-19T18:16:04.971Z
s4-persistence-huntcodexno-skill111261,799—72s22
2026-10-19T20:08:44.688Z
s1-ci-key-escalationcursorskill0.8611855,153~$0.72581.6s104 (5)
2026-10-19T20:12:10.497Z
s1-ci-key-escalationcursorno-skill0.911372,145~$0.46778.3s57 (2)
2026-10-19T20:15:34.694Z
s1-ci-key-escalationcodexskill1111,435,845—125.7s51 (2)
2026-10-19T20:19:46.365Z
s1-ci-key-escalationclaudeskill1111,012,155$0.859167.8s60 (3)
2026-10-19T20:24:39.990Z
s1-ci-key-escalationclaudeno-skill111574,886$0.603154s25 (2)
2026-10-19T20:29:20.704Z
s1-ci-key-escalationcodexno-skill0.911478,212—90.8s18
2026-10-19T20:32:53.341Z
s1-ci-key-escalationcursorskill0.95111,525,991~$1.126331.7s63 (3)
2026-10-19T20:40:28.858Z
s1-ci-key-escalationclaudeskill0.95111,215,632$1.001215s50 (1)
2026-10-19T22:08:26.330Z
s1-ci-key-escalationclaudeskill1111,387,559$1.132177.7s80 (2)
2026-10-19T22:13:27.831Z
s1-ci-key-escalationcursorskill111577,455~$0.568142s55 (5)
2026-10-19T22:16:36.808Z
s1-ci-key-escalationcodexskill0.95111,699,278—134.1s50 (1)
2026-10-19T22:20:54.828Z
s1-ci-key-escalationcodexskill1111,002,195—113.3s44 (1)
2026-10-19T22:22:57.681Z
s1-ci-key-escalationcodexno-skill0.911764,718—112.2s35 (2)
2026-10-19T22:26:54.723Z
s1-ci-key-escalationclaudeno-skill110.5681,468$0.705122.2s56
2026-10-19T22:31:00.754Z
s1-ci-key-escalationcursorno-skill0.9511435,877~$0.521112.9s64 (4)
2026-10-19T22:34:59.949Z
s1-ci-key-escalationcodexno-skill111489,636—89.8s21
2026-10-19T22:38:36.653Z
s1-ci-key-escalationclaudeno-skill111563,146$0.614129.2s24
2026-10-19T22:42:53.849Z
s1-ci-key-escalationcursorno-skill0.810.5375,558~$0.40296.8s72 (7)
2026-10-19T23:02:46.301Z
s3-ransomware-blindspotcursorno-skill0.7510.5745,348~$0.68289.7s82 (2)
2026-10-19T23:06:18.512Z
s3-ransomware-blindspotcodexno-skill0.8611220,968—68.1s17 (1)
2026-10-19T23:12:59.292Z
s3-ransomware-blindspotclaudeskill0.73101,445,908$1.328183.2s45 (1)
2026-10-19T23:18:04.547Z
s3-ransomware-blindspotcodexskill111869,413—104.4s25 (1)
2026-10-19T23:21:50.993Z
s3-ransomware-blindspotcursorskill1111,054,787~$0.82885s115 (9)
2026-10-19T23:25:18.236Z
s3-ransomware-blindspotcursorskill111614,534~$0.55996.3s62 (1)
2026-10-19T23:28:56.877Z
s3-ransomware-blindspotcodexno-skill0.9211355,011—70.9s16 (1)
2026-10-19T23:32:09.930Z
s3-ransomware-blindspotcodexskill111972,684—94.4s23 (1)
2026-10-19T23:35:46.702Z
s3-ransomware-blindspotclaudeskill1111,608,593$1.254162.5s51
2026-10-20T00:33:14.065Z
s3-ransomware-blindspotclaudeskill1111,251,932$1.104187.7s65 (2)
2026-10-20T00:38:23.900Z
s3-ransomware-blindspotcodexskill1111,069,991—111.2s29 (1)
2026-10-20T00:42:17.424Z
s3-ransomware-blindspotcodexno-skill0.8611330,906—67.9s10
2026-10-20T00:45:27.656Z
s3-ransomware-blindspotcursorskill111624,510~$0.582145.4s103 (2)
2026-10-20T01:07:45.689Z
s5-snapshot-exfilcursorskill0.76111,353,153~$1.055647.4s66 (3)
2026-10-20T01:20:34.792Z
s5-snapshot-exfilclaudeskill1111,315,098$1.167223.8s56 (1)
2026-10-20T01:26:20.039Z
s5-snapshot-exfilcodexno-skill0.911347,493—78.8s30
2026-10-20T01:29:40.351Z
s5-snapshot-exfilcursorno-skill0.55111,070,147~$0.938120.8s73 (3)
2026-10-20T01:33:42.495Z
s5-snapshot-exfilclaudeno-skill0.4311493,301$0.631142.8s37 (2)
2026-10-20T01:38:06.585Z
s5-snapshot-exfilcodexskill1111,329,329—141.1s43 (2)
2026-10-20T01:42:28.934Z
s5-snapshot-exfilcodexskill1111,422,059—157.5s46 (3)
2026-10-20T01:47:07.702Z
s5-snapshot-exfilcodexno-skill111497,954—90.8s37
2026-10-20T01:50:39.786Z
s5-snapshot-exfilclaudeno-skill110.51,137,406$2.766319s58 (2)
2026-10-20T02:15:48.775Z
s5-snapshot-exfilcursorskill0.55111,096,173~$0.901220.5s48 (4)
2026-10-20T02:34:52.734Z
s5-snapshot-exfilcursorno-skill0.1810.5883,612~$0.836114.1s92 (5)
2026-10-20T02:38:48.310Z
s5-snapshot-exfilclaudeskill110.51,243,003$1.098327.1s56 (2)
2026-10-20T02:46:16.748Z
s5-snapshot-exfilcodexno-skill0.9511443,747—83.3s45 (1)
2026-10-20T02:49:41.394Z
s5-snapshot-exfilcodexskill1114,070,833—206.7s55 (2)
2026-10-20T03:01:30.632Z
s7-sagemaker-model-theftcodexno-skill111632,796—117.5s41 (1)
2026-10-20T03:05:29.541Z
s7-sagemaker-model-theftcursorno-skill0.710.5642,848~$0.53362.2s59
2026-10-20T03:08:35.625Z
s7-sagemaker-model-theftclaudeskill1111,678,851$1.371190.5s75 (2)
2026-10-20T03:13:49.427Z
s7-sagemaker-model-theftclaudeno-skill111978,317$0.865153.5s57 (1)
2026-10-20T03:18:26.247Z
s7-sagemaker-model-theftcodexskill0.95111,419,137—183.6s60 (1)
2026-10-20T03:23:33.235Z
s7-sagemaker-model-theftcursorskill0.710.5918,397~$0.86689s131 (2)
2026-10-20T03:27:05.573Z
s7-sagemaker-model-theftcodexskill1111,767,074—225.2s49 (3)
2026-10-20T03:32:54.082Z
s7-sagemaker-model-theftcodexno-skill111732,423—123.8s37
2026-10-20T03:37:01.246Z
s7-sagemaker-model-theftclaudeskill0.9111,965,978$1.334238s81 (2)
2026-10-20T03:43:02.509Z
s7-sagemaker-model-theftcursorskill0.7311790,457~$0.697115.4s90 (1)
2026-10-20T03:47:01.289Z
s7-sagemaker-model-theftclaudeno-skill111943,038$0.785199.4s50 (4)
2026-10-20T03:52:23.942Z
s7-sagemaker-model-theftcursorno-skill0.66111,297,339~$1.094410.1s92 (3)
2026-10-20T04:18:30.323Z
s7-sagemaker-model-theftcodexskill1111,340,035—138.5s45 (1)
2026-10-20T04:22:52.286Z
s7-sagemaker-model-theftcursorno-skill0.6111897,389~$0.80099.9s108 (4)
2026-10-20T04:26:35.900Z
s7-sagemaker-model-theftcursorskill0.77111,283,623~$0.963106.7s147 (6)
2026-10-20T04:30:26.024Z
s7-sagemaker-model-theftclaudeno-skill111973,598$0.901134.4s58 (1)
2026-10-20T04:34:43.825Z
s7-sagemaker-model-theftclaudeskill0.9113,455,244$1.984330.9s118
2026-10-20T04:42:18.111Z
s7-sagemaker-model-theftcodexno-skill111673,515—115.3s42 (4)
2026-10-20T13:17:29.989Z
s2-instance-cred-ssmcodexno-skill111564,907—157.6s41 (1)
2026-10-20T13:22:09.342Z
s2-instance-cred-ssmclaudeno-skill0.9511579,302$0.662369s47 (2)
2026-10-20T13:39:15.100Z
s2-instance-cred-ssmcursorno-skill0.8210.5431,463~$0.463100.1s56 (1)
2026-10-20T13:42:57.547Z
s2-instance-cred-ssmcursorskill0.890.51903,938~$0.774101.8s84 (4)
2026-10-20T13:46:41.027Z
s2-instance-cred-ssmclaudeskill0.93112,611,507$3.179577.3s99 (2)
2026-10-20T16:09:40.070Z
s2-instance-cred-ssmcodexno-skill0.8511683,377—109.8s41 (1)
2026-10-20T16:13:31.615Z
s2-instance-cred-ssmclaudeno-skill1111,104,588$0.867404.3s71 (2)
2026-10-20T16:22:17.782Z
s2-instance-cred-ssmcursorno-skill0.9711401,511~$0.60082.3s63 (4)
2026-10-20T16:32:48.599Z
s2-instance-cred-ssmclaudeskill0.93113,284,752$3.7311,594.1s116 (2)
2026-10-20T20:11:39.163Z
s2-instance-cred-ssmclaudeno-skill0.910.51,419,230$2.696690s58 (1)
2026-10-20T20:29:44.304Z
s2-instance-cred-ssmclaudeskill0.89112,313,775$3.066486.6s70 (2)
2026-10-20T20:39:52.598Z
s2-instance-cred-ssmcursorskill0.80.50.51,052,641~$0.881199.1s65 (3)
2026-10-20T20:46:13.822Z
s2-instance-cred-ssmcursorno-skill0.860.50.5501,725~$0.49168.8s59 (2)
2026-10-20T20:49:24.395Z
s2-instance-cred-ssmcodexskill1111,836,907—257s60 (4)
2026-10-20T20:53:43.500Z
s2-instance-cred-ssmcursorskill0.850.50.5817,875~$0.688104.1s66 (5)
2026-10-20T21:57:51.012Z
s4-persistence-huntclaudeno-skill110.5484,815$0.549196.5s21 (2)
2026-10-20T22:03:11.747Z
s4-persistence-huntclaudeskill1111,073,460$1.070246.1s40 (2)
2026-10-20T22:09:24.214Z
s4-persistence-huntcursorskill0.7811690,230~$0.644124.5s87 (2)
2026-10-20T22:13:35.640Z
s4-persistence-huntcursorno-skill0.830.51224,474~$0.28966.4s48 (1)
2026-10-20T22:16:48.361Z
s4-persistence-huntcursorskill0.960.50.5778,008~$0.681105.3s97 (1)
2026-10-20T22:20:37.889Z
s4-persistence-huntclaudeno-skill111493,864$0.520136.5s17 (2)
2026-10-20T22:25:00.776Z
s4-persistence-huntclaudeskill111899,398$0.889175.7s51
2026-10-20T22:30:02.791Z
s4-persistence-huntcursorno-skill111453,536~$0.46967.9s60 (3)
2026-10-21T00:05:15.163Z
s6-pipeline-oidccursorskill0.8910.5924,553~$0.76281.5s67 (1)
2026-10-21T00:08:38.398Z
s6-pipeline-oidcclaudeskill110.51,285,371$1.069252.9s58 (4)
2026-10-21T00:14:54.773Z
s6-pipeline-oidccodexno-skill111564,179—109.7s43 (1)
2026-10-21T00:18:48.092Z
s6-pipeline-oidcclaudeno-skill0.7910.5597,438$1.349179.3s25
2026-10-21T00:24:49.183Z
s6-pipeline-oidccodexskill1112,200,150—226s60 (3)
2026-10-21T00:30:38.629Z
s6-pipeline-oidccursorno-skill0.7911694,473~$0.61987.3s93 (11)
2026-10-21T00:32:11.811Z
s6-pipeline-oidccursorskill111744,145~$0.72379.3s110 (2)
2026-10-21T00:35:34.765Z
s6-pipeline-oidccodexskill1111,411,337—149.9s49 (1)
2026-10-21T00:40:08.325Z
s6-pipeline-oidcclaudeskill1111,533,356$1.245280.3s66 (1)
2026-10-21T00:44:53.689Z
s6-pipeline-oidccursorno-skill0.8911407,332~$0.45763.9s94 (3)
2026-10-21T00:47:59.407Z
s6-pipeline-oidccodexno-skill0.9511470,266—122.4s19
2026-10-21T01:48:19.184Z
s3-ransomware-blindspotclaudeno-skill0.910.5451,400$0.52597.9s35 (2)
2026-10-21T01:51:59.366Z
s3-ransomware-blindspotclaudeno-skill0.8611444,136$0.516119.1s37 (2)
2026-10-21T01:56:00.826Z
s3-ransomware-blindspotclaudeno-skill111378,311$0.61992.2s30
2026-10-21T02:00:17.024Z
s4-persistence-huntcodexskill1111,279,987—178.5s45 (3)
2026-10-21T02:05:17.839Z
s4-persistence-huntcodexskill1112,045,632—215.5s44 (4)
2026-10-21T18:38:50.609Z
s6-pipeline-oidccursorno-skill0.8911514,666~$0.567105.4s93 (7)
2026-10-21T18:41:22.023Z
s3-ransomware-blindspotcursorno-skill0.65111,059,748~$0.883301.4s84 (3)
2026-10-21T18:48:25.721Z
s3-ransomware-blindspotcursorno-skill0.6711534,413~$0.651119.5s83 (3)
2026-10-21T18:54:02.146Z
s2-instance-cred-ssmcodexskill1113,922,726—267s67 (4)
2026-10-21T19:01:31.008Z
s2-instance-cred-ssmcodexskill0.95116,117,439—436.1s82 (6)
2026-10-21T20:34:16.953Z
s2-instance-cred-ssmcodexno-skill0.9511534,839—123.2s32 (1)
2026-10-21T20:59:12.126Z
s5-snapshot-exfilclaudeno-skill111943,929$0.750341.5s44 (4)
2026-10-21T21:06:55.176Z
s5-snapshot-exfilclaudeskill1112,774,987$4.395435.5s107 (1)
2026-10-21T21:16:11.852Z
s5-snapshot-exfilcursorskill0.95111,304,163~$1.031672s95 (4)
2026-10-21T22:03:40.046Z
s5-snapshot-exfilcursorno-skill0.410.5726,083~$0.692149.3s80 (5)