: GitBench

204 test cases. Filter by tag, difficulty, or benchmark. Click any fixture card to see the full prompt and all model responses.

f001 blame_forensics medium
securitysql-injectionregression +2
f002 blame_forensics easy
error-handlingregressiongit-log +2
f003 blame_forensics easy
securityhardcoded-secretgit-log +2
f004 blame_forensics easy
concurrencyrace-conditionregression +2
f005 blame_forensics medium
refactorvariable-namingregression +2
f006 blame_forensics medium
off-by-oneloop-boundaryregression +2
f007 blame_forensics easy
integer-overflowtruncationregression +2
f008 blame_forensics easy
securitypath-traversalregression +3
f009 blame_forensics easy
resource-leakmemory-leakregression +2
f010 blame_forensics medium
import-errorrefactorregression +3
f011 blame_forensics easy
comparison-operatoraccess-controlregression +2
f012 blame_forensics easy
null-pointernull-checkregression +2
f001 branch_cleanup easy
branch-managementmerged-branchescleanup +1
f002 branch_cleanup easy
branch-managementmerged-branchescleanup +1
f003 branch_cleanup easy
branch-managementedge-caseempty-result +1
f004 branch_cleanup medium
branch-managementfeature-branchesmerged-vs-unmerged +1
f005 branch_cleanup easy
branch-managementhotfixmerged-branches +1
f006 branch_cleanup medium
branch-managementnaming-conventionsmerged-branches +1
f007 branch_cleanup medium
branch-managementnested-branchesbranch-topology +1
f008 branch_cleanup easy
branch-managementall-mergedfull-cleanup
f009 branch_cleanup easy
branch-managementunmergededge-case +1
f010 branch_cleanup medium
branch-managementrelease-branchesmerged-branches +1
f011 branch_cleanup trivial
branch-managementsingle-branchedge-case +1
f012 branch_cleanup hard
branch-managementmany-branchesscalability +2
f001 cherry_pick easy
cherry-pickconflict-resolutionsingle-line +1
f002 cherry_pick easy
cherry-pickconflict-resolutionversion-number +1
f003 cherry_pick easy
cherry-pickconflict-resolutionstatus-message +1
f004 cherry_pick medium
cherry-pickconflict-resolutionmulti-line +1
f005 cherry_pick medium
cherry-pickconflict-resolutionfunction-body +1
f006 cherry_pick medium
cherry-pickconflict-resolutionconfig +1
f007 cherry_pick hard
cherry-pickconflict-resolutionthree-way +2
f008 cherry_pick hard
cherry-pickconflict-resolutionmulti-file +1
f009 cherry_pick medium
cherry-pickconflict-resolutionthree-way +1
f010 cherry_pick hard
cherry-pickconflict-resolutionmulti-file +1
f011 cherry_pick medium
cherry-pickconflict-resolutionjson +1
f012 cherry_pick hard
cherry-pickconflict-resolutionmulti-file +1
f001 commit_messages trivial
commit-messagesingle-fileadd +1
f002 commit_messages easy
commit-messagemulti-fileadd +1
f003 commit_messages easy
commit-messagerenamefile-operations
f004 commit_messages easy
commit-messagedeletionremove
f005 commit_messages easy
commit-messagemodificationupdate
f006 commit_messages medium
commit-messagereplaceadd-and-delete +1
f007 commit_messages easy
commit-messagesubdirectoryadd +1
f008 commit_messages medium
commit-messagepermissionsexecutable +1
f009 commit_messages medium
commit-messagebug-fixfix +1
f010 commit_messages medium
commit-messagerefactormulti-file +1
f011 commit_messages easy
commit-messageconfiginfrastructure
f012 commit_messages easy
commit-messagedocumentationdocs +1
f001 commit_squash easy
commit-squashwipsquash +1
f002 commit_squash easy
commit-squashfixuptypo +1
f003 commit_squash medium
commit-squashrelated-changesatomic-commits +1
f004 commit_squash medium
commit-squashintermediaterebase +1
f005 commit_squash medium
commit-squashexperimentalexploration +1
f006 commit_squash easy
commit-squashdocumentationfixup +1
f007 commit_squash medium
commit-squashtddtest-first +1
f008 commit_squash medium
commit-squashconfigscattered-changes +1
f009 commit_squash medium
commit-squashstyle-fixcosmetic +1
f010 commit_squash medium
commit-squashdebugremoval +1
f011 commit_squash hard
commit-squashfeature-developmentgrouping +1
f012 commit_squash hard
commit-squashlong-runningmany-commits +2
f001 git_bisect easy
git-bisectlinear-historyrecent-bug +1
f002 git_bisect medium
git-bisectlinear-historymiddle-commit
f003 git_bisect easy
git-bisectlinear-historynear-end
f004 git_bisect medium
git-bisectlinear-historyearly-commit
f005 git_bisect easy
git-bisectlinear-historysecond-commit
f006 git_bisect medium
git-bisectlinear-historythird-commit
f007 git_bisect medium
git-bisectbranching-historymerge +1
f008 git_bisect medium
git-bisectvalidationregression +1
f009 git_bisect medium
git-bisectimport-errorregression +1
f010 git_bisect hard
git-bisectmulti-filebranching +1
f011 git_bisect hard
git-bisectmulti-filefrontend +1
f012 git_bisect hard
git-bisectmulti-filebackend +1
f001 git_clean trivial
git-cleanuntrackedbasic
f002 git_clean easy
git-cleandry-runpreview +1
f003 git_clean easy
git-cleandirectoriesrecursive
f004 git_clean medium
git-cleanignoredgitignore
f005 git_clean medium
git-cleanuntrackedignored +1
f006 git_clean easy
git-cleandirectory-scopedpath
f007 git_clean medium
git-cleanexclusionpattern
f008 git_clean medium
git-cleaninteractiveconfirmation
f009 git_clean easy
git-cleansubdirectoryscoped
f010 git_clean easy
git-cleandry-rundirectories +1
f011 git_clean medium
git-cleanbuild-artifactsnested +1
f012 git_clean hard
git-cleancombinedadvanced +1
f001 git_grep trivial
git-grepkeyword-searchbasic
f002 git_grep medium
git-grepcommit-messageslog-grep
f003 git_grep medium
git-grepregexextended
f004 git_grep easy
git-grepline-numbersformat
f005 git_grep easy
git-grepcombined-flagscase-insensitive
f006 git_grep easy
git-grepno-resultsedge-case
f007 git_grep medium
git-grepcontext-linessurrounding
f008 git_grep easy
git-greppath-limitedsubdirectory
f009 git_grep medium
git-grepbranch-searchref +1
f010 git_grep medium
git-grepword-boundaryprecise
f011 git_grep medium
git-grepmultiple-patternsor-search
f012 git_grep medium
git-grepcountaggregation
f001 git_log_format easy
git-loggrepcount +1
f002 git_log_format easy
git-loggreplist +1
f003 git_log_format easy
git-logauthorfilter
f004 git_log_format easy
git-logauthorcount +1
f005 git_log_format medium
git-logdate-rangefilter +1
f006 git_log_format medium
git-logdate-rangecount +1
f007 git_log_format easy
git-logonelineparsing
f008 git_log_format easy
git-logonelinecount
f009 git_log_format medium
git-logmerge-commitidentification
f010 git_log_format medium
git-logmerge-commitcount +1
f011 git_log_format medium
git-logstatchanged-files +1
f012 git_log_format medium
git-logstatlines-changed +1
f001 git_show trivial
git-showauthoremail +1
f002 git_show easy
git-showfiles-changedfile-list
f003 git_show easy
git-showlightweight-tagtag
f004 git_show medium
git-showannotated-tagtagger +1
f005 git_show medium
git-showfile-contentrevision +1
f006 git_show medium
git-showdiffcompare +1
f007 git_show easy
git-showauthor-datemetadata
f008 git_show easy
git-showfull-hashsha +1
f009 git_show medium
git-showmerge-commitparents
f010 git_show medium
git-showrenamedetection
f011 git_show medium
git-showbinaryfile-change
f012 git_show medium
git-showmulti-filecomprehensive
f001 merge_conflicts easy
merge-conflictsingle-linebasic +1
f002 merge_conflicts easy
merge-conflictversion-numbersemver +1
f003 merge_conflicts easy
merge-conflictstatus-messageresolution
f004 merge_conflicts medium
merge-conflictmulti-linehunk +1
f005 merge_conflicts medium
merge-conflictfunction-bodycode-merge +1
f006 merge_conflicts medium
merge-conflictconfiginfrastructure +1
f007 merge_conflicts hard
merge-conflictthree-wayport +2
f008 merge_conflicts hard
merge-conflictmulti-filepartial +1
f009 merge_conflicts medium
merge-conflictthree-wayauthor +1
f010 merge_conflicts hard
merge-conflictmulti-filesimultaneous +1
f011 merge_conflicts medium
merge-conflictjsonstructured-data +1
f012 merge_conflicts hard
merge-conflictmulti-filedependency-aware +1
f001 rebase easy
rebasesingle-lineconflict-resolution +1
f002 rebase easy
rebaseversion-numberconflict-resolution
f003 rebase easy
rebasestatus-messageconflict-resolution
f004 rebase medium
rebasemulti-linehunk +1
f005 rebase medium
rebasefunction-bodycode-merge +1
f006 rebase medium
rebaseconfiginfrastructure +1
f007 rebase hard
rebasethree-wayport +2
f008 rebase hard
rebasemulti-filepartial +1
f009 rebase medium
rebasethree-wayauthor +1
f010 rebase hard
rebasemulti-filesimultaneous +1
f011 rebase medium
rebasejsonstructured-data +1
f012 rebase hard
rebasemulti-filedependency-aware +1
f001 reflog easy
reflogsoft-resetrecovery +1
f002 reflog medium
refloghard-resetrecovery +1
f003 reflog medium
reflogamendhistory +1
f004 reflog medium
reflogdeleted-branchrecovery +1
f005 reflog hard
reflogrebasesquash +1
f006 reflog medium
reflogdetached-headdiagnosis +1
f007 reflog hard
reflogmultiple-resetsfiltering +1
f008 reflog hard
reflogrebaseconflict +1
f009 reflog medium
reflogcherry-pickreset +1
f010 reflog hard
reflogmixed-resetorphaned +1
f011 reflog expert
reflogmulti-branchrebase +1
f012 reflog hard
refloghard-resetdetached-head +1
f001 stash_recovery trivial
stashlistbasic +1
f002 stash_recovery easy
stashmultiplefiltering +1
f003 stash_recovery medium
stashbranch-referenceidentification +1
f004 stash_recovery medium
stashbefore-mergetiming +1
f005 stash_recovery hard
stashpop-failurereapply +1
f006 stash_recovery easy
stashmultiple-filescontent +1
f007 stash_recovery medium
stashdroppedindex +1
f008 stash_recovery medium
stashuntrackedinclude-untracked +1
f009 stash_recovery medium
stashapply-vs-popsemantics +1
f010 stash_recovery medium
stashsubdirectorypath-aware +1
f011 stash_recovery hard
stashafter-rebaserecovery
f012 stash_recovery medium
stashbranch-namemessage +1
f001 submodule_usage easy
submoduleaddbasic
f002 submodule_usage medium
submoduleinitclone +1
f003 submodule_usage medium
submoduleremovedeinit +1
f004 submodule_usage easy
submodulestatusinspection
f005 submodule_usage easy
submoduleaddcommit +1
f006 submodule_usage easy
submodulelistenumeration
f007 submodule_usage medium
submodulemultipleadd +1
f008 submodule_usage medium
submoduledeinitdeactivate
f009 submodule_usage medium
submodulesyncurl +1
f010 submodule_usage medium
submoduleupdatelatest +1
f011 submodule_usage easy
submodulegitmodulesconfig +1
f012 submodule_usage hard
submodulebranchtracking +1
f001 tag_management trivial
taglightweightcreate +1
f002 tag_management easy
tagannotatedcreate +1
f003 tag_management easy
tagdeleteremove
f004 tag_management easy
taglistenumeration
f005 tag_management medium
taglistpattern +1
f006 tag_management medium
tagolder-commitretroactive
f007 tag_management easy
tagshowdetails +1
f008 tag_management medium
tagrenamedelete-and-create +1
f009 tag_management medium
tagsignedgpg +1
f010 tag_management medium
tagpushremote +1
f011 tag_management medium
tagfetchremote +1
f012 tag_management medium
taglistsort +1
f001 worktree_usage easy
worktreecreatebranch +1
f002 worktree_usage medium
worktreecommitchanges +1
f003 worktree_usage easy
worktreedeletecleanup +1
f004 worktree_usage easy
worktreelistenumeration
f005 worktree_usage medium
worktreecreatenew-branch +1
f006 worktree_usage medium
worktreedetachedcreate +1
f007 worktree_usage hard
worktreemultiplecreate +1
f008 worktree_usage medium
worktreecommitworkflow +1
f009 worktree_usage hard
worktreerepairbroken +1
f010 worktree_usage medium
worktreelockprotection
f011 worktree_usage medium
worktreeunlocklifecycle
f012 worktree_usage medium
worktreetagcreate +1