Current theme: dark
← Back to Leaderboard
Task
Detailed breakdown of individual task performance across different models.
Status
All
Models
All
Task Name (52 tasks)
claude-4-6-sonnet
claude-4-7-opus
gemini-3-flash
gemini-3.1-pro
glm-4.7
gpt-5.2-codex
gpt-5.4
kimi-k2.5
abandon_commits
68.1s
57.3s
353.2s
230.1s
162.9s
49.0s
40.6s
35.2s
absorb_changes
99.1s
50.7s
424.8s
107.0s
123.3s
116.1s
33.5s
52.4s
bookmark_create_and_move
50.1s
43.0s
215.4s
213.3s
62.5s
99.6s
42.2s
32.7s
bookmark_delete
36.6s
23.0s
117.7s
75.5s
37.6s
23.7s
16.8s
17.7s
bookmark_push
64.1s
26.4s
82.1s
96.9s
60.2s
95.6s
41.1s
32.7s
bookmark_rename
22.0s
22.0s
153.0s
90.2s
43.9s
30.3s
41.5s
17.4s
commit_splitting
75.4s
81.2s
89.2s
74.9s
112.6s
59.6s
56.7s
84.6s
concurrent_operations
101.2s
60.5s
308.7s
68.1s
110.5s
84.3s
44.3s
112.5s
conflict_resolution
80.2s
76.1s
64.3s
108.8s
119.6s
41.8s
43.0s
51.4s
describe_commit
39.3s
25.1s
86.0s
56.4s
34.8s
19.6s
29.2s
18.4s
diff_revisions
47.3s
30.2s
106.5s
123.3s
44.8s
30.5s
39.9s
24.2s
diffedit_interactive
93.9s
77.1s
235.6s
299.1s
113.4s
149.2s
44.7s
38.4s
duplicate_commit
48.6s
28.9s
141.6s
185.5s
53.6s
26.4s
19.3s
36.0s
edit_commit_message
60.7s
45.8s
110.6s
274.3s
116.2s
58.7s
31.4s
25.9s
git_export
29.5s
32.3s
40.2s
84.7s
50.8s
36.4s
22.8s
19.6s
git_fetch_remote
83.6s
33.9s
136.0s
171.1s
36.1s
73.7s
46.1s
28.2s
git_import
22.0s
33.1s
111.6s
58.9s
29.5s
24.9s
17.3s
27.4s
git_integration
85.3s
62.6s
261.8s
188.9s
217.3s
74.3s
47.4s
59.1s
git_remote_add
115.9s
37.0s
74.5s
26.6s
152.9s
51.5s
34.0s
114.0s
history_rewriting
103.0s
59.5s
328.0s
369.3s
137.5s
67.5s
46.1s
41.5s
ignore_patterns
55.6s
50.2s
334.7s
272.2s
270.4s
105.3s
33.2s
31.5s
log_template_author
41.3s
45.3s
383.0s
226.5s
115.3s
47.7s
26.4s
31.6s
new_commit
58.3s
24.3s
231.0s
122.7s
412.1s
54.4s
27.2s
29.3s
new_insert
76.5s
85.6s
190.9s
530.0s
476.1s
85.1s
52.3s
54.9s
next_prev_navigation
64.7s
64.5s
178.0s
253.5s
241.0s
35.8s
30.5s
36.7s
obslog_view
39.2s
23.0s
115.0s
70.3s
198.4s
32.4s
22.1s
24.8s
operation_recovery
52.9s
36.2s
396.9s
127.9s
49.5s
48.4s
38.3s
37.9s
rebase_branch
113.7s
82.5s
600.2s
595.5s
302.4s
376.9s
42.6s
86.7s
rebase_destination
21.2s
29.5s
87.9s
109.3s
39.1s
21.4s
29.5s
44.5s
resolve_conflict_marker
48.1s
44.6s
51.9s
139.7s
70.4s
34.0s
29.3s
23.6s
resolve_tool
41.2s
42.4s
459.2s
111.0s
74.6s
46.9s
41.1s
38.4s
restore_file_from_parent
29.6s
42.8s
483.0s
94.0s
77.7s
28.3s
20.1s
26.4s
restore_interactive
45.1s
65.6s
49.9s
152.8s
73.7s
47.6s
31.8s
29.1s
restore_specific_revision
43.3s
35.2s
219.5s
63.2s
106.7s
35.0s
25.7s
49.4s
revert_file
77.8s
29.8s
75.6s
37.8s
115.3s
37.3s
40.2s
65.4s
root_commit
37.1s
27.4s
161.3s
31.3s
46.9s
25.7s
23.9s
30.6s
show_commit
57.5s
45.5s
257.1s
43.6s
92.7s
56.7s
46.1s
57.6s
split_commit_interactive
79.5s
49.9s
600.1s
97.3s
217.8s
55.7s
35.6s
92.3s
squash_commits
39.0s
40.2s
390.3s
53.7s
86.0s
96.7s
33.3s
37.1s
squash_range
79.5s
45.1s
600.1s
135.7s
146.0s
78.1s
48.9s
57.0s
stacking_changes
56.6s
58.1s
600.1s
485.0s
118.3s
69.6s
34.2s
34.5s
status_ignored
52.5s
41.2s
535.2s
83.2s
61.9s
58.6s
42.3s
44.7s
template_customize_log_output
54.9s
47.2s
600.1s
71.8s
87.3s
46.9s
29.1s
88.8s
template_formatting
173.2s
140.9s
115.3s
263.7s
238.0s
85.6s
78.4s
96.4s
track_untracked_file
34.8s
32.3s
165.0s
29.9s
64.9s
36.6s
26.2s
21.7s
undo_mistaken_rebase
98.6s
59.6s
198.1s
46.0s
88.1s
46.0s
36.7s
60.8s
untrack_file
43.0s
34.3s
600.1s
36.0s
92.1s
52.6s
31.2s
34.9s
working_copy_as_commit
60.2s
47.5s
60.1s
50.9s
60.1s
60.1s
33.3s
60.2s
workspace_add
21.8s
29.4s
114.7s
31.5s
48.0s
24.0s
20.2s
22.0s
workspace_forget
40.0s
30.4s
126.5s
31.5s
98.7s
41.2s
33.6s
35.5s
workspace_root
20.6s
24.9s
100.3s
35.3s
53.5s
29.9s
19.7s
24.9s
workspace_update_stale
57.2s
41.8s
175.7s
43.8s
52.0s
59.3s
30.2s
33.0s