Codex /goal run detail

GPT 5.5 (xhigh)

A GoalBench scaffold run against ProgramBench tasks. This page shows the run's measured outcomes, task scores, and public evidence links; it is not an official mini-SWE-agent leaderboard submission.

Paper prompt + /goal no internetCodex /goal paper prompt no-internet, mini-SWE-style executionsmaller VM: 16 CPU / 30gversion 20260518T232006Z
Resolved0 / 2000.0%
Almost resolved1 / 2000.5%
Average pass rate53.4%behavioral tests
Total est. cost$142*token logs for 40/200 tasks
Avg. cost$3.54*per costed task
Total calls11,90059.5 / task
Avg /goal session11.4m0.191h
Max /goal session25.6m0.427h
Total wall time38.11hsum across 200 tasks

Goal Session Duration

Wall-clock time is measured per Codex /goal session from launch to packaged submission. ProgramBench's public mini-SWE-agent runs use a much larger timeout, so this block makes latency differences explicit.

Average0.191h11.4 min
Median0.184h11.1 min
P750.218h13.1 min
P900.248h14.9 min
P950.279h16.8 min
Max0.427h25.6 min
Over 6h0 / 2000.0%
<15 min 180 / 200 90.0%
15-30 min 20 / 200 10.0%
>30 min 0 / 200 0.0%

Longest task: wfxr__csview.8ac4de0 at 25.6 min.

Prompt & Config

ProgramBench paper system prompt from arXiv v1, prefixed with /goal and run through the mini-SWE-style task workspace scaffold. The exact prompt is published as a stable artifact and referenced from results.json and results.csv.

Prompt
Paper Prompt + /goal (mini-SWE-style)
Source
prompts/programbench_goal_paper_prompt.md
SHA-256
76451cdc851023e2fe5ef506b48f95efddab5ec16da7298200976c5d9791c29a

Behavioral Test Pass Rate Distribution

These plots mirror ProgramBench's run-detail views: a score histogram and a cumulative count by behavioral test pass-rate bucket.

Histogram

34 0 0% 100% behavioral test pass rate tasks 0-10% pass: 25 task(s)10-20% pass: 11 task(s)20-30% pass: 6 task(s)30-40% pass: 15 task(s)40-50% pass: 23 task(s)50-60% pass: 20 task(s)60-70% pass: 33 task(s)70-80% pass: 34 task(s)80-90% pass: 25 task(s)90-100% pass: 8 task(s)

Cumulative

200 0 0% 100% behavioral test pass rate tasks >= 0% pass: 200 task(s), 100.0%>= 10% pass: 175 task(s), 87.5%>= 20% pass: 164 task(s), 82.0%>= 30% pass: 158 task(s), 79.0%>= 40% pass: 143 task(s), 71.5%>= 50% pass: 120 task(s), 60.0%>= 60% pass: 100 task(s), 50.0%>= 70% pass: 67 task(s), 33.5%>= 80% pass: 33 task(s), 16.5%>= 90% pass: 8 task(s), 4.0%

Score by Task

Each cell is one evaluated task instance. Dark green means fully resolved, amber means almost resolved, and muted cells are partial or open.

Per-Instance Results

InstanceScoreResolvedAlmostEvalTestsEst. costCallsEvidence
abishekvashok__cmatrix.5c082c6 97.4% no yes ok 494/507 $1.81 41 manifest · eval json · eval summary · agent summary · usage audit
mgdm__htmlq.6e31bc8 94.4% no no ok 1374/1455 $3.37 61 manifest · eval json · eval summary · agent summary · usage audit
agourlay__zip-password-finder.704700d 94.1% no no ok 640/680 n/a 48 manifest · eval json · eval summary · agent summary · usage audit
sstadick__hck.b66c751 93.6% no no ok 800/855 n/a 52 not exported
jarun__nnn.cb2c535 93.5% no no ok 446/477 n/a 58 manifest · eval json · eval summary · agent summary · usage audit
riquito__tuc.16fb471 93.3% no no ok 1116/1196 n/a 44 not exported
sheepla__pingu.926d475 91.4% no no ok 350/383 n/a 43 not exported
ismaelgv__rnr.fc0733b 90.8% no no ok 620/683 n/a 85 not exported
lymphatus__caesium-clt.a529b2e 89.9% no no ok 517/575 n/a 72 not exported
miserlou__loop.209927c 89.9% no no ok 638/710 n/a 51 not exported
svenstaro__miniserve.8449e8b 88.8% no no ok 270/304 n/a 71 not exported
sirwart__ripsecrets.34c9e03 88.2% no no ok 539/611 $3.67 74 manifest · eval json · eval summary · agent summary · usage audit
yaa110__nomino.f892499 88.2% no no ok 276/313 n/a 59 not exported
astro__deadnix.d590041 88.0% no no ok 530/602 $2.93 51 manifest · eval json · eval summary · agent summary · usage audit
sharkdp__hexyl.2e26437 87.9% no no ok 796/906 n/a 66 not exported
johanneskaufmann__html-to-markdown.3006818 87.3% no no ok 773/885 $3.76 62 manifest · eval json · eval summary · agent summary · usage audit
chmln__sd.87d1ba5 87.2% no no ok 706/810 n/a 47 not exported
sharkdp__pastel.b60e899 86.9% no no ok 968/1114 n/a 66 not exported
guumaster__hostctl.d6d9699 86.2% no no ok 906/1051 n/a 78 not exported
nikolassv__bartib.6b9b5ce 86.1% no no ok 622/722 n/a 84 not exported
hooklift__gowsdl.2a06cec 85.2% no no ok 333/391 n/a 79 not exported
jonas__tig.8334123 85.1% no no ok 1350/1586 n/a 60 not exported
kyoheiu__felix.95df390 85.1% no no ok 427/502 n/a 37 not exported
rs__curlie.5dfcbb1 85.0% no no ok 596/701 $3.33 52 manifest · eval json · eval summary · agent summary · usage audit
brocode__fblog.3b54330 84.6% no no ok 827/978 n/a 44 not exported
clog-tool__clog-cli.7066cba 84.0% no no ok 483/575 n/a 68 not exported
oppiliappan__eva.41ae245 83.7% no no ok 764/913 n/a 80 not exported
byron__dua-cli.8570c15 81.9% no no ok 581/709 n/a 50 manifest · eval json · eval summary · agent summary · usage audit
burntsushi__xsv.f430466 81.9% no no ok 968/1182 $2.55 48 manifest · eval json · eval summary · agent summary · usage audit
zevv__duc.a58fa4e 81.5% no no ok 712/874 n/a 53 not exported
mibk__dupl.1bf052b 81.2% no no ok 303/373 n/a 60 not exported
junegunn__fzf.b56d614 80.4% no no ok 1494/1858 $4.31 50 manifest · eval json · eval summary · agent summary · usage audit
esubaalew__run.0fb9dec 80.3% no no ok 973/1212 $3.44 62 manifest · eval json · eval summary · agent summary · usage audit
burntsushi__ripgrep.3b7fd44 79.7% no no ok 1589/1994 n/a 89 not exported
rust-ethereum__ethabi.b1710ad 79.0% no no ok 788/997 n/a 49 not exported
ksxgithub__parallel-disk-usage.96978ed 78.9% no no ok 419/531 n/a 49 not exported
segmentio__chamber.5f93f5f 78.9% no no ok 1379/1748 n/a 61 not exported
eradman__entr.8e2e8b4 78.7% no no ok 461/586 n/a 28 not exported
eudoxia0__hashcards.48aa136 78.2% no no ok 797/1019 n/a 107 manifest · eval json · eval summary · agent summary · usage audit
chmln__handlr.90e78ba 77.8% no no ok 562/722 n/a 61 manifest · eval json · eval summary · agent summary · usage audit
alexpovel__srgn.89f943b 76.6% no no ok 1419/1852 n/a 71 not exported
codesnap-rs__codesnap.f81e4f3 76.4% no no ok 436/571 $5.10 59 manifest · eval json · eval summary · agent summary · usage audit
tomnomnom__gron.88a6234 76.3% no no ok 171/224 n/a 80 not exported
blacknon__hwatch.edfcb62 76.3% no no ok 775/1016 n/a 79 not exported
rhysd__kiro-editor.4157485 75.6% no no ok 450/595 n/a 35 not exported
raviqqe__muffet.a882908 75.1% no no ok 220/293 n/a 46 not exported
ggreer__the_silver_searcher.a61f178 75.0% no no ok 753/1004 n/a 81 not exported
git-bahn__git-graph.87b4473 75.0% no no ok 426/568 n/a 64 not exported
rust-embedded__svd2rust.1760b5e 74.9% no no ok 689/920 n/a 53 not exported
o2sh__onefetch.e5958ce 74.7% no no ok 871/1166 n/a 48 not exported
nachoparker__dutree.44e877d 74.3% no no ok 476/641 n/a 73 not exported
mookid__diffr.2152742 73.9% no no ok 448/606 n/a 44 not exported
mfridman__tparse.2416b4b 73.9% no no ok 314/425 n/a 47 not exported
astaxie__bat.17d1080 73.9% no no ok 806/1091 n/a 44 not exported
lua__lua.c6b4848 73.4% no no ok 982/1338 n/a 46 not exported
konradsz__igrep.aa75630 72.7% no no ok 280/385 n/a 32 not exported
lz4__lz4.1519f46 72.3% no no ok 1081/1496 n/a 33 not exported
dalance__amber.69a0f52 72.2% no no ok 408/565 $1.96 38 manifest · eval json · eval summary · agent summary · usage audit
wintermute-cell__ngrrram.8ea13c3 71.9% no no ok 218/303 $1.98 37 manifest · eval json · eval summary · agent summary · usage audit
rbakbashev__elfcat.52f8cc7 71.5% no no ok 403/564 n/a 57 not exported
ajeetdsouza__zoxide.67ca1bc 71.4% no no ok 379/531 n/a 87 not exported
wfxr__csview.8ac4de0 71.0% no no ok 238/335 n/a 82 not exported
incu6us__goimports-reviser.81bd549 71.0% no no ok 364/513 n/a 32 manifest · eval json · eval summary · agent summary · usage audit
nuta__nsh.bdd0702 70.8% no no ok 1389/1963 n/a 107 not exported
noborus__trdsql.d8c5ff6 70.7% no no ok 928/1312 n/a 54 not exported
xampprocky__tokei.505d648 70.4% no no ok 515/732 n/a 41 not exported
psampaz__go-mod-outdated.bb79367 70.2% no no ok 200/285 n/a 26 not exported
direnv__direnv.02040c7 69.8% no no ok 593/849 n/a 59 not exported
jrnxf__thokr.09375ef 69.7% no no ok 310/445 n/a 46 not exported
facebookresearch__fasttext.1142dc4 69.2% no no ok 216/312 n/a 55 not exported
ninja-build__ninja.cc60300 69.2% no no ok 995/1438 n/a 62 not exported
dundee__gdu.ede21d2 69.1% no no ok 802/1161 n/a 54 not exported
peco__peco.4e58dad 69.0% no no ok 845/1224 n/a 46 not exported
hatoo__oha.8dc6349 69.0% no no ok 620/899 n/a 51 manifest · eval json · eval summary · agent summary · usage audit
bootandy__dust.62bf1e1 68.5% no no ok 400/584 n/a 62 manifest · eval json · eval summary · agent summary · usage audit
rs__jplot.2a54bcc 68.4% no no ok 399/583 n/a 32 not exported
orf__gping.26eb5b9 68.4% no no ok 232/339 n/a 56 not exported
pls-rs__pls.4e1ae50 67.8% no no ok 225/332 $4.68 87 manifest · eval json · eval summary · agent summary · usage audit
tinycc__tinycc.9b8765d 67.4% no no ok 1334/1978 n/a 50 not exported
cordx56__rustowl.655bc5c 67.2% no no ok 396/589 n/a 39 manifest · eval json · eval summary · agent summary · usage audit
rust-lang__mdbook.37273ba 67.1% no no ok 748/1114 n/a 60 not exported
ammarabouzor__tui-journal.2b4540d 66.9% no no ok 938/1402 n/a 53 manifest · eval json · eval summary · agent summary · usage audit
ariga__atlas.6d81150 66.8% no no ok 881/1318 $5.36 94 manifest · eval json · eval summary · agent summary · usage audit
wfxr__code-minimap.0ddeea5 66.5% no no ok 208/313 n/a 76 not exported
halitechallenge__halite.822cfb6 65.8% no no ok 181/275 $2.64 45 manifest · eval json · eval summary · agent summary · usage audit
blake3-team__blake3.15e83a5 65.4% no no ok 423/647 $3.43 58 manifest · eval json · eval summary · agent summary · usage audit
lfos__calcurse.49180d5 65.3% no no ok 435/666 n/a 98 not exported
skeema__skeema.6a76243 64.8% no no ok 1107/1708 n/a 77 not exported
madler__pigz.fe4894f 64.7% no no ok 538/831 n/a 85 not exported
ecumene__rust-sloth.051c559 64.7% no no ok 246/380 n/a 55 not exported
ogham__dog.721440b 64.6% no no ok 840/1300 n/a 63 not exported
multiprocessio__dsq.c3ae0ba 64.4% no no ok 349/542 n/a 96 not exported
naggie__dstask.ff57396 63.5% no no ok 812/1278 n/a 63 not exported
quinn-rs__quinn.bb359cc 63.2% no no ok 330/522 n/a 67 not exported
rochacbruno__marmite.7d4bc2d 62.4% no no ok 417/668 n/a 66 not exported
altdesktop__i3-style.f93821b 62.3% no no ok 336/539 $2.17 39 manifest · eval json · eval summary · agent summary · usage audit
lh3__seqtk.94e7070 62.2% no no ok 267/429 n/a 44 not exported
facebook__zstd.1168da0 61.3% no no ok 1250/2038 n/a 45 not exported
axodotdev__oranda.27d60c7 61.1% no no ok 469/767 n/a 81 manifest · eval json · eval summary · agent summary · usage audit
pemistahl__grex.fa3e8ed 60.7% no no ok 796/1312 n/a 77 not exported
jesseduffield__lazygit.1d0db51 59.9% no no ok 512/855 n/a 47 not exported
sharkdp__fd.40d8eb3 59.4% no no ok 734/1235 n/a 44 not exported
yassinebridi__serpl.c48a9d7 58.7% no no ok 262/446 $1.68 38 manifest · eval json · eval summary · agent summary · usage audit
xorg62__tty-clock.f2f847c 58.0% no no ok 163/281 n/a 44 not exported
thezoraiz__ascii-image-converter.d05a757 57.6% no no ok 268/465 n/a 64 not exported
luajit__luajit.a553b3d 57.2% no no ok 1698/2967 $3.72 47 manifest · eval json · eval summary · agent summary · usage audit
wgunderwood__tex-fmt.3f1aef6 56.9% no no ok 259/455 n/a 75 not exported
rcoh__angle-grinder.9c2fc88 55.8% no no ok 630/1130 $5.22 90 manifest · eval json · eval summary · agent summary · usage audit
kaushiksrini__parqeye.8072121 55.5% no no ok 266/479 n/a 61 not exported
cweill__gotests.2a672c5 55.4% no no ok 334/603 n/a 78 not exported
crowdagger__crowbook.ea214d7 55.1% no no ok 445/807 n/a 37 not exported
canop__rhit.ae90bcb 55.0% no no ok 449/817 n/a 43 not exported
sayanarijit__xplr.1751065 54.2% no no ok 227/419 n/a 56 not exported
robertdavidgraham__masscan.b99d433 53.6% no no ok 1367/2549 n/a 56 not exported
oppiliappan__statix.e9df54c 52.9% no no ok 431/815 $3.05 59 manifest · eval json · eval summary · agent summary · usage audit
shashwatah__jot.a92aad8 52.3% no no ok 393/752 $3.27 70 manifest · eval json · eval summary · agent summary · usage audit
stacked-git__stgit.430027d 52.2% no no warn 1 802/1537 $3.84 58 manifest · eval json · eval summary · agent summary · usage audit
ducaale__xh.4a6e44f 52.2% no no ok 611/1171 n/a 54 manifest · eval json · eval summary · agent summary · usage audit
isona__dirble.e2dea9f 51.7% no no ok 371/718 n/a 76 not exported
elkowar__pipr.fae0b17 51.4% no no ok 270/525 n/a 45 not exported
anordal__shellharden.6a6ffd4 49.4% no no ok 541/1095 n/a 69 not exported
chirlu__sox.42b3557 49.3% no no ok 592/1202 $3.82 44 manifest · eval json · eval summary · agent summary · usage audit
trasta298__keifu.3331426 49.2% no no ok 129/262 $1.91 37 manifest · eval json · eval summary · agent summary · usage audit
y2z__monolith.8702e66 48.9% no no ok 349/713 n/a 69 not exported
mkj__dropbear.75f699b 48.5% no no ok 329/678 $2.44 53 manifest · eval json · eval summary · agent summary · usage audit
arthursonzogni__json-tui.17a22b6 47.7% no no ok 360/755 n/a 88 not exported
sitkevij__hex.61ae69b 46.2% no no ok 380/823 n/a 62 not exported
ip7z__7zip.839151e 45.8% no no ok 478/1043 n/a 30 not exported
epistates__treemd.825c6dd 45.1% no no ok 708/1569 n/a 54 not exported
sharkdp__bat.f822bd0 45.1% no no ok 360/799 $4.62 71 manifest · eval json · eval summary · agent summary · usage audit
sibprogrammer__xq.b89f681 44.6% no no ok 353/792 n/a 42 not exported
tukaani-project__xz.1007bf0 43.8% no no ok 618/1410 n/a 72 not exported
go-critic__go-critic.9aea378 43.8% no no ok 216/493 $5.76 91 manifest · eval json · eval summary · agent summary · usage audit
boyter__scc.515f91c 43.3% no no ok 201/464 n/a 65 not exported
cslarsen__jp2a.61d205f 43.3% no no ok 273/631 n/a 83 not exported
gabotechs__dep-tree.60a95a2 43.2% no no ok 374/865 n/a 63 not exported
arq5x__bedtools2.dd57059 43.2% no no ok 455/1053 n/a 41 manifest · eval json · eval summary · agent summary · usage audit
noborus__ov.b96c2ba 42.3% no no ok 785/1854 n/a 44 not exported
hpjansson__chafa.dd4d4c1 42.0% no no ok 811/1931 n/a 49 not exported
cmatsuoka__figlet.202a0a8 41.1% no no ok 358/872 n/a 118 not exported
cheat__cheat.b8098dc 40.7% no no ok 121/297 n/a 44 not exported
typst__typst.88356d0 40.7% no no ok 701/1724 n/a 45 not exported
nikoladucak__caps-log.2cf2d1e 40.5% no no ok 223/551 $4.51 68 manifest · eval json · eval summary · agent summary · usage audit
canop__broot.d6c798e 39.1% no no ok 211/539 n/a 26 not exported
foriequal0__git-trim.07c2f50 37.7% no no ok 192/509 n/a 79 manifest · eval json · eval summary · agent summary · usage audit
mgechev__revive.201451e 37.1% no no ok 270/727 n/a 88 not exported
paradigmxyz__solar.5190d0e 36.9% no no ok 729/1978 n/a 84 not exported
drew-alleman__datasurgeon.d257cee 36.3% no no ok 182/502 $4.01 71 manifest · eval json · eval summary · agent summary · usage audit
antonmedv__walk.bf802ef 36.0% no no ok 169/470 n/a 40 not exported
svenstaro__genact.16f96e3 35.8% no no ok 83/232 n/a 41 not exported
stranger6667__jsonschema.d52e881 35.0% no no ok 1027/2933 n/a 104 not exported
simeg__eureka.df3796c 34.9% no no ok 120/344 n/a 54 not exported
kisielk__errcheck.dacab89 34.6% no no ok 118/341 n/a 38 not exported
tomarrell__wrapcheck.c058da1 33.8% no no ok 162/480 n/a 49 not exported
bensadeh__tailspin.6278437 33.2% no no ok 204/615 n/a 48 not exported
tree-sitter__tree-sitter.5e23cca 32.7% no no ok 403/1232 n/a 45 not exported
eliukblau__pixterm.1a93fd5 32.1% no no ok 138/430 n/a 62 manifest · eval json · eval summary · agent summary · usage audit
ekzhang__bore.8e059cd 30.5% no no ok 120/394 $3.44 75 manifest · eval json · eval summary · agent summary · usage audit
stathissideris__ditaa.f2286c4 29.4% no no ok 179/609 n/a 57 not exported
johnkerl__miller.8d85b46 28.3% no no ok 4147/14637 n/a 41 not exported
zk-org__zk.10d93d5 26.8% no no ok 297/1108 n/a 44 not exported
ys-l__flamelens.0b4dc33 25.4% no no ok 57/224 n/a 46 not exported
ivanceras__svgbob.6d00ad9 25.4% no no ok 120/472 $4.53 71 manifest · eval json · eval summary · agent summary · usage audit
ast-grep__ast-grep.dde0fe0 20.5% no no ok 181/882 n/a 55 not exported
yoav-lavi__melody.f4af9b4 19.9% no no ok 240/1205 n/a 155 not exported
jhspetersson__fselect.c3559ca 19.4% no no ok 603/3115 n/a 68 not exported
tarka__xcp.5e5b448 18.9% no no ok 224/1184 $3.24 54 manifest · eval json · eval summary · agent summary · usage audit
kyoh86__richgo.313114f 17.8% no no ok 97/546 $2.38 43 manifest · eval json · eval summary · agent summary · usage audit
danmar__cppcheck.0a5b103 16.3% no no ok 347/2126 n/a 28 not exported
jgm__pandoc.5caad90 15.7% no no ok 819/5228 n/a 41 not exported
nukesor__pueue.8b9d6fe 14.9% no no ok 95/638 $2.50 44 manifest · eval json · eval summary · agent summary · usage audit
tstack__lnav.ee34494 14.0% no no ok 139/990 n/a 51 not exported
osgeo__gdal.0847f12 14.0% no no ok 92/657 n/a 56 not exported
samtools__samtools.aa823b5 13.5% no no ok 192/1425 n/a 45 not exported
parcel-bundler__lightningcss.aa2ed1e 12.0% no no ok 339/2828 $3.96 74 manifest · eval json · eval summary · agent summary · usage audit
pier-cli__pier.5e1bde9 10.0% no no ok 69/692 n/a 82 not exported
htop-dev__htop.523600b 9.7% no no ok 67/693 n/a 57 not exported
ffmpeg__ffmpeg.360a402 8.8% no no ok 269/3050 n/a 54 not exported
php__php-src.c891263 8.8% no no ok 1254/14288 n/a 64 not exported
antonmedv__fx.86d0d34 8.6% no no ok 176/2047 n/a 47 not exported
duckdb__duckdb.bdb65ec 8.2% no no ok 466/5650 n/a 40 not exported
hush-shell__hush.560c33a 7.2% no no ok 87/1201 $4.04 56 manifest · eval json · eval summary · agent summary · usage audit
jqlang__jq.b33a763 5.5% no no ok 333/6072 n/a 115 not exported
gromacs__gromacs.665ea4c 3.9% no no ok 49/1245 n/a 49 not exported
unhappychoice__gittype.34b72d0 3.6% no no warn 1 27/742 $3.00 59 manifest · eval json · eval summary · agent summary · usage audit
rvben__rumdl.2d75c4d 2.7% no no warn 1 91/3323 $4.96 56 manifest · eval json · eval summary · agent summary · usage audit
sclevine__yj.8016400 2.1% no no ok 16/767 n/a 34 not exported
hairyhenderson__gomplate.05eb3aa 2.1% no no ok 60/2926 n/a 58 not exported
google__brotli.b3dc9cc 1.4% no no ok 6/441 n/a 72 manifest · eval json · eval summary · agent summary · usage audit
doxygen__doxygen.966d98e 1.3% no no warn 1 3/230 n/a 61 not exported
mikefarah__yq.602586d 1.1% no no ok 23/2000 n/a 43 not exported
osgeo__proj.75d455c 1.0% no no ok 52/5319 n/a 46 not exported
dandavison__delta.acd758f 0.7% no no ok 7/950 n/a 81 manifest · eval json · eval summary · agent summary · usage audit
sqlite__sqlite.839433d 0.5% no no ok 62/13514 n/a 75 not exported
sigoden__argc.04a08f1 0.4% no no ok 4/995 n/a 76 not exported
universal-ctags__ctags.243595e 0.1% no no ok 3/2258 n/a 62 not exported
filosottile__age.706dfc1 0.0% no no error 0/676 $5.20 80 manifest · eval json · eval summary · agent summary · usage audit
bellard__quickjs.d7ae12a 0.0% no no ok 0/3034 n/a 76 not exported
alecthomas__chroma.8d04def 0.0% no no ok 0/503 n/a 57 not exported
sharkdp__hyperfine.327d5f4 0.0% no no ok 0/291 n/a 42 not exported