← Back to benchmark

Raw run data

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

180 of 180 runs

Per-metric comparison

Success

cursor
98%
claude
96%
codex
94%

Adherence

codex
95%
cursor
94%
claude
91%

Cmd accuracy

cursor
95%
claude
93%
codex
90%

Tokens

cursor
183,291
codex
279,038
claude
303,862

Agent time

cursor
59s
codex
110s
claude
121s

Cost

cursor
~$0.204
codex
~$0.463
claude
$0.588
RunTaskAgentArmSuccessAdher.TokensCostAgent timeCmds
claude-eip-cleanup-no-skill-r1eip-cleanupclaudeno-skill11172,582$0.35865.4s5
claude-eip-cleanup-no-skill-r1eip-cleanupclaudeno-skill11144,872$0.32847.6s4
claude-eip-cleanup-no-skill-r1eip-cleanupclaudeno-skill11143,574$0.32647.8s4
cursor-eip-cleanup-no-skill-r1eip-cleanupcursorno-skill1189,773~$0.11016.4s6
cursor-eip-cleanup-no-skill-r1eip-cleanupcursorno-skill1174,934~$0.08615.9s4
cursor-eip-cleanup-no-skill-r1eip-cleanupcursorno-skill1192,388~$0.10117.1s5
claude-eip-cleanup-skill-r1eip-cleanupclaudeskill10.5143,508$0.32947.3s3
claude-eip-cleanup-skill-r1eip-cleanupclaudeskill10.5193,821$0.37775.8s5
claude-eip-cleanup-skill-r1eip-cleanupclaudeskill10.5197,837$0.39064.9s5
cursor-eip-cleanup-skill-r1eip-cleanupcursorskill10.5128,098~$0.17231.3s5
cursor-eip-cleanup-skill-r1eip-cleanupcursorskill11131,203~$0.14322.9s6
cursor-eip-cleanup-skill-r1eip-cleanupcursorskill11131,284~$0.17626.9s6
cursor-tag-compliance-fix-no-skill-r1tag-compliance-fixcursorno-skill11271,953~$0.28151.9s11
claude-vpc-cleanup-review-skill-r1vpc-cleanup-reviewclaudeskill11151,204$0.36691.9s6
claude-vpc-cleanup-review-skill-r1vpc-cleanup-reviewclaudeskill11226,500$0.493135s7
claude-vpc-cleanup-review-skill-r1vpc-cleanup-reviewclaudeskill11177,943$0.451114.3s5 (1)
codex-vpc-cleanup-review-skill-r1vpc-cleanup-reviewcodexskill1184,408~$0.18668.2s13
codex-vpc-cleanup-review-skill-r1vpc-cleanup-reviewcodexskill11148,096~$0.282128.8s6
codex-vpc-cleanup-review-skill-r1vpc-cleanup-reviewcodexskill11127,177~$0.23070.5s14 (1)
cursor-vpc-cleanup-review-skill-r1vpc-cleanup-reviewcursorskill11121,664~$0.19932.5s15
cursor-vpc-cleanup-review-skill-r1vpc-cleanup-reviewcursorskill11125,511~$0.21930.7s15
cursor-vpc-cleanup-review-skill-r1vpc-cleanup-reviewcursorskill11121,261~$0.15831.5s16
claude-vpc-cleanup-review-no-skill-r1vpc-cleanup-reviewclaudeno-skill0.50.5199,861$0.456146.5s7
claude-vpc-cleanup-review-no-skill-r1vpc-cleanup-reviewclaudeno-skill0.50.5209,259$0.511151s7
claude-vpc-cleanup-review-no-skill-r1vpc-cleanup-reviewclaudeno-skill0.50.5207,733$0.490148.2s7
codex-vpc-cleanup-review-no-skill-r1vpc-cleanup-reviewcodexno-skill0.50.5140,374~$0.292116.8s6 (1)
codex-vpc-cleanup-review-no-skill-r1vpc-cleanup-reviewcodexno-skill00.572,859~$0.18660.4s24
codex-vpc-cleanup-review-no-skill-r1vpc-cleanup-reviewcodexno-skill00202,406~$0.372160.8s8 (2)
cursor-vpc-cleanup-review-no-skill-r1vpc-cleanup-reviewcursorno-skill11291,491~$0.35486.6s18 (2)
cursor-vpc-cleanup-review-no-skill-r1vpc-cleanup-reviewcursorno-skill1192,397~$0.18128.8s8
cursor-vpc-cleanup-review-no-skill-r1vpc-cleanup-reviewcursorno-skill00.599,091~$0.26846.6s11 (1)
claude-terraform-drift-fix-skill-r1terraform-drift-fixclaudeskill11264,388$0.50074.2s8 (1)
claude-terraform-drift-fix-skill-r1terraform-drift-fixclaudeskill11242,414$0.50578.7s7
claude-terraform-drift-fix-skill-r1terraform-drift-fixclaudeskill11258,362$0.47770s8 (1)
codex-terraform-drift-fix-skill-r1terraform-drift-fixcodexskill11184,669~$0.295112s4
codex-terraform-drift-fix-skill-r1terraform-drift-fixcodexskill11175,975~$0.282113.8s4
codex-terraform-drift-fix-skill-r1terraform-drift-fixcodexskill11175,351~$0.269114s4
cursor-terraform-drift-fix-skill-r1terraform-drift-fixcursorskill11115,437~$0.13326.7s5
cursor-terraform-drift-fix-skill-r1terraform-drift-fixcursorskill11117,995~$0.12025.1s6
cursor-terraform-drift-fix-skill-r1terraform-drift-fixcursorskill11116,343~$0.12928.4s5
claude-terraform-drift-fix-no-skill-r1terraform-drift-fixclaudeno-skill11230,938$0.45270.9s8 (1)
claude-terraform-drift-fix-no-skill-r1terraform-drift-fixclaudeno-skill11231,240$0.46573.9s8
claude-terraform-drift-fix-no-skill-r1terraform-drift-fixclaudeno-skill11226,161$0.43671.8s7
codex-terraform-drift-fix-no-skill-r1terraform-drift-fixcodexno-skill11141,302~$0.189117.9s2
codex-terraform-drift-fix-no-skill-r1terraform-drift-fixcodexno-skill11141,368~$0.226112.8s2
codex-terraform-drift-fix-no-skill-r1terraform-drift-fixcodexno-skill11141,713~$0.170108.1s2
cursor-terraform-drift-fix-no-skill-r1terraform-drift-fixcursorno-skill1197,048~$0.15323.4s5 (1)
cursor-terraform-drift-fix-no-skill-r1terraform-drift-fixcursorno-skill11111,892~$0.15126.4s5
cursor-terraform-drift-fix-no-skill-r1terraform-drift-fixcursorno-skill11114,289~$0.13232.3s6 (1)
claude-cloudtrail-who-changed-skill-r1cloudtrail-who-changedclaudeskill11147,529$0.288189.1s4
claude-cloudtrail-who-changed-skill-r1cloudtrail-who-changedclaudeskill11199,598$0.337175.9s6 (1)
codex-cloudtrail-who-changed-skill-r1cloudtrail-who-changedcodexskill11298,678~$0.445159.9s7
codex-cloudtrail-who-changed-skill-r1cloudtrail-who-changedcodexskill11105,691~$0.189134.4s4
codex-cloudtrail-who-changed-skill-r1cloudtrail-who-changedcodexskill11102,497~$0.18790.2s4
cursor-cloudtrail-who-changed-skill-r1cloudtrail-who-changedcursorskill1165,313~$0.10650.6s4
cursor-cloudtrail-who-changed-skill-r1cloudtrail-who-changedcursorskill1165,425~$0.107111.6s4
cursor-cloudtrail-who-changed-skill-r1cloudtrail-who-changedcursorskill1166,079~$0.11090.8s4
claude-cloudtrail-who-changed-no-skill-r1cloudtrail-who-changedclaudeno-skill11115,528$0.234139.5s5
claude-cloudtrail-who-changed-no-skill-r1cloudtrail-who-changedclaudeno-skill11300,140$0.685182.2s10
claude-cloudtrail-who-changed-no-skill-r1cloudtrail-who-changedclaudeno-skill11139,217$0.25982s5
codex-cloudtrail-who-changed-no-skill-r1cloudtrail-who-changedcodexno-skill1192,351~$0.164129.8s4 (1)
codex-cloudtrail-who-changed-no-skill-r1cloudtrail-who-changedcodexno-skill1148,151~$0.10076.9s2
codex-cloudtrail-who-changed-no-skill-r1cloudtrail-who-changedcodexno-skill11114,547~$0.167162.5s5 (1)
cursor-cloudtrail-who-changed-no-skill-r1cloudtrail-who-changedcursorno-skill1180,276~$0.101116.2s4
cursor-cloudtrail-who-changed-no-skill-r1cloudtrail-who-changedcursorno-skill1150,560~$0.080108.1s3
cursor-cloudtrail-who-changed-no-skill-r1cloudtrail-who-changedcursorno-skill1169,657~$0.10893.5s4
cursor-assess-backup-jobs-skill-r1assess-backup-jobscursorskill11186,556~$0.21865s10
cursor-assess-backup-jobs-skill-r1assess-backup-jobscursorskill11186,254~$0.29844.9s12
cursor-assess-backup-jobs-skill-r1assess-backup-jobscursorskill11224,548~$0.23541.1s14 (2)
claude-assess-backup-jobs-no-skill-r1assess-backup-jobsclaudeno-skill11501,382$0.832214.6s14 (1)
claude-assess-backup-jobs-no-skill-r1assess-backup-jobsclaudeno-skill11234,169$0.476122.3s8 (1)
claude-assess-backup-jobs-no-skill-r1assess-backup-jobsclaudeno-skill11261,508$0.552129s8
codex-assess-backup-jobs-no-skill-r1assess-backup-jobscodexno-skill11157,109~$0.26781.5s7 (1)
codex-assess-backup-jobs-no-skill-r1assess-backup-jobscodexno-skill0.5158,741~$0.11046.9s3 (2)
codex-assess-backup-jobs-no-skill-r1assess-backup-jobscodexno-skill0.5143,603~$0.07830.5s2
cursor-assess-backup-jobs-no-skill-r1assess-backup-jobscursorno-skill11158,464~$0.21063.7s18 (3)
cursor-assess-backup-jobs-no-skill-r1assess-backup-jobscursorno-skill1198,099~$0.12945.4s8
cursor-assess-backup-jobs-no-skill-r1assess-backup-jobscursorno-skill1182,686~$0.14533.3s6
claude-assess-backup-jobs-skill-r1assess-backup-jobsclaudeskill0.51124,182$0.26552.1s3
codex-assess-backup-jobs-skill-r1assess-backup-jobscodexskill1194,605~$0.20556.6s4 (1)
codex-assess-backup-jobs-skill-r1assess-backup-jobscodexskill11155,905~$0.258100.7s6
codex-assess-backup-jobs-skill-r1assess-backup-jobscodexskill11114,900~$0.19177.1s5 (1)
claude-assess-backup-jobs-skill-r1assess-backup-jobsclaudeskill11289,079$0.48587.8s8
claude-assess-backup-jobs-skill-r1assess-backup-jobsclaudeskill11325,949$0.568117.4s9 (2)
claude-cloudtrail-who-changed-skill-r1cloudtrail-who-changedclaudeskill11155,207$0.295188.7s4
codex-eip-cleanup-skill-r1eip-cleanupcodexskill11211,035~$0.40364.2s3
codex-eip-cleanup-skill-r1eip-cleanupcodexskill10.5210,964~$0.39153.4s3
codex-eip-cleanup-skill-r1eip-cleanupcodexskill10.5212,096~$0.40456.3s3
codex-eip-cleanup-no-skill-r1eip-cleanupcodexno-skill11108,143~$0.27047.5s1
codex-eip-cleanup-no-skill-r1eip-cleanupcodexno-skill11106,312~$0.27641.4s1
codex-eip-cleanup-no-skill-r1eip-cleanupcodexno-skill11108,155~$0.27240.5s1
claude-lambda-invocation-errors-fix-skill-r1lambda-invocation-errors-fixclaudeskill11447,224$0.770132.6s9
claude-lambda-invocation-errors-fix-skill-r1lambda-invocation-errors-fixclaudeskill11506,703$0.910164.9s13 (1)
claude-lambda-invocation-errors-fix-skill-r1lambda-invocation-errors-fixclaudeskill11410,367$0.834153.9s11
codex-lambda-invocation-errors-fix-skill-r1lambda-invocation-errors-fixcodexskill11465,902~$0.690118.7s7
codex-lambda-invocation-errors-fix-skill-r1lambda-invocation-errors-fixcodexskill11552,515~$0.822130.3s7
codex-lambda-invocation-errors-fix-skill-r1lambda-invocation-errors-fixcodexskill11545,412~$0.981121.2s6
cursor-lambda-invocation-errors-fix-skill-r1lambda-invocation-errors-fixcursorskill11415,115~$0.35680.7s17 (1)
cursor-lambda-invocation-errors-fix-skill-r1lambda-invocation-errors-fixcursorskill11494,016~$0.40965.2s12 (2)
cursor-lambda-invocation-errors-fix-skill-r1lambda-invocation-errors-fixcursorskill11441,354~$0.38367.6s18 (1)
claude-lambda-invocation-errors-fix-no-skill-r1lambda-invocation-errors-fixclaudeno-skill11420,439$0.791133.7s11 (1)
claude-lambda-invocation-errors-fix-no-skill-r1lambda-invocation-errors-fixclaudeno-skill11450,081$0.765123.6s13 (1)
claude-lambda-invocation-errors-fix-no-skill-r1lambda-invocation-errors-fixclaudeno-skill11370,953$0.761127.6s11 (1)
codex-lambda-invocation-errors-fix-no-skill-r1lambda-invocation-errors-fixcodexno-skill11444,418~$0.677123.4s6
codex-lambda-invocation-errors-fix-no-skill-r1lambda-invocation-errors-fixcodexno-skill11580,140~$0.797119s8
codex-lambda-invocation-errors-fix-no-skill-r1lambda-invocation-errors-fixcodexno-skill11492,745~$0.73499.6s6
cursor-lambda-invocation-errors-fix-no-skill-r1lambda-invocation-errors-fixcursorno-skill11424,398~$0.42059.7s13
cursor-lambda-invocation-errors-fix-no-skill-r1lambda-invocation-errors-fixcursorno-skill11426,136~$0.35455.7s14
cursor-lambda-invocation-errors-fix-no-skill-r1lambda-invocation-errors-fixcursorno-skill11273,778~$0.27548.3s15
claude-s3-block-public-access-fix-skill-r1s3-block-public-access-fixclaudeskill11322,731$0.667114.9s7
claude-s3-block-public-access-fix-skill-r1s3-block-public-access-fixclaudeskill11380,762$0.710119.6s10
claude-s3-block-public-access-fix-skill-r1s3-block-public-access-fixclaudeskill11350,201$0.680108.8s7
codex-s3-block-public-access-fix-skill-r1s3-block-public-access-fixcodexskill11295,813~$0.47892.3s6
codex-s3-block-public-access-fix-skill-r1s3-block-public-access-fixcodexskill11348,656~$0.616111s6
codex-s3-block-public-access-fix-skill-r1s3-block-public-access-fixcodexskill11424,193~$0.594100s8 (1)
cursor-s3-block-public-access-fix-skill-r1s3-block-public-access-fixcursorskill10.5176,616~$0.16831.3s4
cursor-s3-block-public-access-fix-skill-r1s3-block-public-access-fixcursorskill10.5196,215~$0.23536.6s6 (2)
cursor-s3-block-public-access-fix-skill-r1s3-block-public-access-fixcursorskill10.5201,024~$0.21633.7s6 (1)
claude-s3-block-public-access-fix-no-skill-r1s3-block-public-access-fixclaudeno-skill10.5320,597$0.642113.5s9
claude-s3-block-public-access-fix-no-skill-r1s3-block-public-access-fixclaudeno-skill0.50374,968$0.699131.1s10 (1)
claude-s3-block-public-access-fix-no-skill-r1s3-block-public-access-fixclaudeno-skill10.5407,257$0.726135.4s10 (1)
codex-s3-block-public-access-fix-no-skill-r1s3-block-public-access-fixcodexno-skill11260,755~$0.633103s4 (1)
codex-s3-block-public-access-fix-no-skill-r1s3-block-public-access-fixcodexno-skill11281,081~$0.610565.3s4 (1)
codex-s3-block-public-access-fix-no-skill-r1s3-block-public-access-fixcodexno-skill11350,087~$0.577111.6s8 (2)
cursor-s3-block-public-access-fix-no-skill-r1s3-block-public-access-fixcursorno-skill11232,414~$0.23255.2s7 (1)
cursor-s3-block-public-access-fix-no-skill-r1s3-block-public-access-fixcursorno-skill10.5178,582~$0.23442.5s7
cursor-s3-block-public-access-fix-no-skill-r1s3-block-public-access-fixcursorno-skill10.5200,114~$0.23952.8s6 (1)
claude-ssh-open-ingress-fix-skill-r1ssh-open-ingress-fixclaudeskill11343,067$0.725108s8
claude-ssh-open-ingress-fix-skill-r1ssh-open-ingress-fixclaudeskill11306,017$0.66496.2s7
claude-ssh-open-ingress-fix-skill-r1ssh-open-ingress-fixclaudeskill11371,599$0.735109.2s9 (1)
codex-ssh-open-ingress-fix-skill-r1ssh-open-ingress-fixcodexskill11303,916~$0.48983.3s6
codex-ssh-open-ingress-fix-skill-r1ssh-open-ingress-fixcodexskill11375,272~$0.58678.8s7
codex-ssh-open-ingress-fix-skill-r1ssh-open-ingress-fixcodexskill11280,532~$0.45469.1s5
cursor-ssh-open-ingress-fix-skill-r1ssh-open-ingress-fixcursorskill11192,611~$0.21838.5s6
cursor-ssh-open-ingress-fix-skill-r1ssh-open-ingress-fixcursorskill11121,719~$0.125292.5s6
cursor-ssh-open-ingress-fix-skill-r1ssh-open-ingress-fixcursorskill11102,345~$0.117422.7s7
claude-ssh-open-ingress-fix-no-skill-r1ssh-open-ingress-fixclaudeno-skill11368,778$0.685111.4s12
claude-ssh-open-ingress-fix-no-skill-r1ssh-open-ingress-fixclaudeno-skill11291,654$0.61195.6s9
claude-ssh-open-ingress-fix-no-skill-r1ssh-open-ingress-fixclaudeno-skill11266,318$0.60589.8s9
codex-ssh-open-ingress-fix-no-skill-r1ssh-open-ingress-fixcodexno-skill11347,763~$0.630100.3s5 (1)
codex-ssh-open-ingress-fix-no-skill-r1ssh-open-ingress-fixcodexno-skill11331,344~$0.58487.7s6 (2)
codex-ssh-open-ingress-fix-no-skill-r1ssh-open-ingress-fixcodexno-skill11283,077~$0.53784s5
cursor-ssh-open-ingress-fix-no-skill-r1ssh-open-ingress-fixcursorno-skill11166,627~$0.18737s7
cursor-ssh-open-ingress-fix-no-skill-r1ssh-open-ingress-fixcursorno-skill11145,386~$0.16634.7s5
cursor-ssh-open-ingress-fix-no-skill-r1ssh-open-ingress-fixcursorno-skill11144,828~$0.17032.9s5
claude-tag-compliance-fix-skill-r1tag-compliance-fixclaudeskill11374,967$0.746109.1s7 (2)
claude-tag-compliance-fix-skill-r1tag-compliance-fixclaudeskill11391,734$0.803128.1s9 (1)
claude-tag-compliance-fix-skill-r1tag-compliance-fixclaudeskill11410,415$0.771109s9 (2)
codex-tag-compliance-fix-skill-r1tag-compliance-fixcodexskill11575,234~$0.814150.2s7 (1)
codex-tag-compliance-fix-skill-r1tag-compliance-fixcodexskill11439,336~$0.714165.7s7 (1)
codex-tag-compliance-fix-skill-r1tag-compliance-fixcodexskill11638,866~$0.811198.9s7 (2)
cursor-tag-compliance-fix-skill-r1tag-compliance-fixcursorskill11323,285~$0.28362s10 (2)
cursor-tag-compliance-fix-skill-r1tag-compliance-fixcursorskill11262,712~$0.25938.6s6
cursor-tag-compliance-fix-skill-r1tag-compliance-fixcursorskill11237,946~$0.25137.2s9
claude-tag-compliance-fix-no-skill-r1tag-compliance-fixclaudeno-skill11374,613$0.764155.7s11 (1)
claude-tag-compliance-fix-no-skill-r1tag-compliance-fixclaudeno-skill10.5484,830$0.862138s11 (1)
claude-tag-compliance-fix-no-skill-r1tag-compliance-fixclaudeno-skill11438,113$0.821122s12 (2)
codex-tag-compliance-fix-no-skill-r1tag-compliance-fixcodexno-skill11468,000~$0.797141.9s7 (1)
codex-tag-compliance-fix-no-skill-r1tag-compliance-fixcodexno-skill11429,518~$0.780163.2s6 (2)
codex-tag-compliance-fix-no-skill-r1tag-compliance-fixcodexno-skill11316,342~$0.578104.1s7 (2)
cursor-tag-compliance-fix-no-skill-r1tag-compliance-fixcursorno-skill11288,033~$0.26464.1s10 (1)
cursor-tag-compliance-fix-no-skill-r1tag-compliance-fixcursorno-skill11227,158~$0.22144.2s6
claude-webserver-503-fix-skill-r1webserver-503-fixclaudeskill11538,546$0.838481s15 (2)
claude-webserver-503-fix-skill-r1webserver-503-fixclaudeskill11493,275$0.805124.2s10
codex-webserver-503-fix-skill-r1webserver-503-fixcodexskill11554,280~$0.913116s8 (1)
codex-webserver-503-fix-skill-r1webserver-503-fixcodexskill11479,407~$0.682111.9s12
codex-webserver-503-fix-skill-r1webserver-503-fixcodexskill11476,256~$0.893127.2s7 (2)
cursor-webserver-503-fix-skill-r1webserver-503-fixcursorskill11234,047~$0.21745.9s13 (1)
cursor-webserver-503-fix-skill-r1webserver-503-fixcursorskill11234,869~$0.20949.2s13 (1)
cursor-webserver-503-fix-skill-r1webserver-503-fixcursorskill11202,612~$0.22340s10
claude-webserver-503-fix-no-skill-r1webserver-503-fixclaudeno-skill11372,705$0.729107.7s12 (3)
claude-webserver-503-fix-no-skill-r1webserver-503-fixclaudeno-skill11430,690$0.744129.3s13 (3)
claude-webserver-503-fix-no-skill-r1webserver-503-fixclaudeno-skill11353,309$0.649100.3s11 (1)
codex-webserver-503-fix-no-skill-r1webserver-503-fixcodexno-skill11415,471~$0.640115.6s9 (1)
codex-webserver-503-fix-no-skill-r1webserver-503-fixcodexno-skill11349,638~$0.52083.9s5
codex-webserver-503-fix-no-skill-r1webserver-503-fixcodexno-skill11557,108~$0.781111.8s8 (2)
cursor-webserver-503-fix-no-skill-r1webserver-503-fixcursorno-skill11202,857~$0.18144.2s10 (1)
cursor-webserver-503-fix-no-skill-r1webserver-503-fixcursorno-skill11232,357~$0.23243.9s11 (1)
cursor-webserver-503-fix-no-skill-r1webserver-503-fixcursorno-skill11240,324~$0.276114.9s12 (1)
claude-webserver-503-fix-skill-r1webserver-503-fixclaudeskill11443,110$0.773116.9s13 (1)