Thinkingmachines / inkling
low
96.1%
196 / 204 fixtures · 1 run(s)
36,128 input / 12,121 total output / 8,322 reasoning within output tokens $0.08193653
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-53.9%
Text: 96.1% →
JSON: 42.2%
+2
Gained
JSON pass / text fail
−112
Lost
Text pass / JSON fail
84
Unchanged Pass
Both pass
6
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| submodule_usage | 100% | 25% | -75% |
| git_show | 100% | 33.3% | -66.7% |
| reflog | 100% | 33.3% | -66.7% |
| rebase | 91.7% | 25% | -66.7% |
| git_clean | 91.7% | 33.3% | -58.3% |
| cherry_pick | 75% | 16.7% | -58.3% |
| blame_forensics | 100% | 41.7% | -58.3% |
| branch_cleanup | 100% | 41.7% | -58.3% |
| git_grep | 100% | 41.7% | -58.3% |
| git_log_format | 100% | 41.7% | -58.3% |
| commit_squash | 100% | 50% | -50% |
| merge_conflicts | 83.3% | 33.3% | -50% |
| worktree_usage | 100% | 50% | -50% |
| commit_messages | 100% | 58.3% | -41.7% |
| stash_recovery | 100% | 58.3% | -41.7% |
| git_bisect | 100% | 66.7% | -33.3% |
| tag_management | 91.7% | 66.7% | -25% |
Changed Fixtures (114)
f001 -loss f002 -loss f005 -loss f008 -loss f009 -loss f011 -loss f012 -loss f001 -loss f003 -loss f004 -loss f008 -loss f009 -loss f010 -loss f012 -loss f001 -loss f002 -loss f003 -loss f005 -loss f007 -loss f008 -loss f009 -loss f001 -loss f002 -loss f005 -loss f008 -loss f012 -loss f001 -loss f002 -loss f007 -loss f009 -loss f010 -loss f011 -loss f001 -loss f003 -loss f010 -loss f011 -loss f002 -loss f003 -loss f004 -loss f005 -loss f007 -loss f010 -loss f011 -loss f002 -loss f005 -loss f006 -loss f007 -loss f010 -loss f011 -loss f012 -loss f001 -loss f003 -loss f004 -loss f005 -loss f006 -loss f007 -loss f012 -loss f001 -loss f004 -loss f005 -loss f006 -loss f007 -loss f009 -loss f011 -loss f012 -loss f001 +gain f002 -loss f005 -loss f006 -loss f007 -loss f009 -loss f010 -loss f011 -loss f001 -loss f004 -loss f006 -loss f007 -loss f008 -loss f009 -loss f010 -loss f011 -loss f001 -loss f002 -loss f004 -loss f005 -loss f006 -loss f007 -loss f010 -loss f012 -loss f001 -loss f004 -loss f006 -loss f010 -loss f012 -loss f001 -loss f002 -loss f004 -loss f005 -loss f006 -loss f007 -loss f008 -loss f010 -loss f012 -loss f001 -loss f007 +gain f008 -loss f009 -loss f010 -loss f002 -loss f004 -loss f006 -loss f007 -loss f011 -loss f012 -loss
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
224
Input
51
Total output
40
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
209
Input
98
Total output
88
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
230
Input
33
Total output
20
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
181
Input
39
Total output
34
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
229
Input
39
Total output
30
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
211
Input
61
Total output
51
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
195
Input
41
Total output
31
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
221
Input
57
Total output
47
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
187
Input
77
Total output
64
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
369
Input
46
Total output
45
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
215
Input
55
Total output
46
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
142
Input
85
Total output
66
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
106
Input
105
Total output
104
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
122
Input
56
Total output
52
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
96
Input
38
Total output
39
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
132
Input
30
Total output
18
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
109
Input
37
Total output
34
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
125
Input
42
Total output
34
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
104
Input
27
Total output
15
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
126
Input
82
Total output
71
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
84
Input
54
Total output
47
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
119
Input
44
Total output
32
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
74
Input
53
Total output
46
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
158
Input
36
Total output
19
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
97
Input
95
Total output
84
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
121
Input
89
Total output
76
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
92
Input
182
Total output
172
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
146
Input
46
Total output
21
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
152
Input
47
Total output
28
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
138
Input
50
Total output
24
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
128
Input
30
Total output
15
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
127
Input
23
Total output
11
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
111
Input
30
Total output
18
Reasoning within output
cherry_pick f010
50%
Failed
Tokens
209
Input
193
Total output
186
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
167
Input
50
Total output
22
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
259
Input
261
Total output
249
Reasoning within output
commit_messages f001
85.3%
Passed
Tokens
110
Input
76
Total output
67
Reasoning within output
commit_messages f002
93.3%
Passed
Tokens
204
Input
61
Total output
46
Reasoning within output
commit_messages f003
96.3%
Passed
Tokens
89
Input
48
Total output
34
Reasoning within output
commit_messages f004
94.3%
Passed
Tokens
117
Input
38
Total output
28
Reasoning within output
commit_messages f005
92.7%
Passed
Tokens
105
Input
38
Total output
28
Reasoning within output
commit_messages f006
92.7%
Passed
Tokens
140
Input
45
Total output
33
Reasoning within output
commit_messages f007
88.3%
Passed
Tokens
182
Input
39
Total output
26
Reasoning within output
commit_messages f008
90.7%
Passed
Tokens
77
Input
50
Total output
39
Reasoning within output
commit_messages f009
84.3%
Passed
Tokens
129
Input
45
Total output
32
Reasoning within output
commit_messages f010
92.7%
Passed
Tokens
265
Input
49
Total output
44
Reasoning within output
commit_messages f011
87.7%
Passed
Tokens
147
Input
76
Total output
63
Reasoning within output
commit_messages f012
90%
Passed
Tokens
130
Input
90
Total output
79
Reasoning within output
commit_squash f001
100%
Passed
Tokens
141
Input
55
Total output
36
Reasoning within output
commit_squash f002
100%
Passed
Tokens
122
Input
47
Total output
33
Reasoning within output
commit_squash f003
100%
Passed
Tokens
132
Input
59
Total output
41
Reasoning within output
commit_squash f004
100%
Passed
Tokens
119
Input
38
Total output
21
Reasoning within output
commit_squash f005
100%
Passed
Tokens
116
Input
48
Total output
43
Reasoning within output
commit_squash f006
100%
Passed
Tokens
99
Input
45
Total output
28
Reasoning within output
commit_squash f007
100%
Passed
Tokens
108
Input
42
Total output
24
Reasoning within output
commit_squash f008
100%
Passed
Tokens
120
Input
49
Total output
31
Reasoning within output
commit_squash f009
100%
Passed
Tokens
112
Input
49
Total output
25
Reasoning within output
commit_squash f010
100%
Passed
Tokens
127
Input
107
Total output
86
Reasoning within output
commit_squash f011
100%
Passed
Tokens
135
Input
51
Total output
30
Reasoning within output
commit_squash f012
100%
Passed
Tokens
135
Input
64
Total output
38
Reasoning within output
git_bisect f001
100%
Passed
Tokens
183
Input
28
Total output
14
Reasoning within output
git_bisect f002
100%
Passed
Tokens
196
Input
20
Total output
10
Reasoning within output
git_bisect f003
100%
Passed
Tokens
200
Input
29
Total output
18
Reasoning within output
git_bisect f004
100%
Passed
Tokens
204
Input
38
Total output
19
Reasoning within output
git_bisect f005
100%
Passed
Tokens
198
Input
27
Total output
15
Reasoning within output
git_bisect f006
100%
Passed
Tokens
221
Input
24
Total output
13
Reasoning within output
git_bisect f007
100%
Passed
Tokens
200
Input
26
Total output
14
Reasoning within output
git_bisect f008
100%
Passed
Tokens
198
Input
26
Total output
15
Reasoning within output
git_bisect f009
100%
Passed
Tokens
204
Input
23
Total output
10
Reasoning within output
git_bisect f010
100%
Passed
Tokens
198
Input
21
Total output
10
Reasoning within output
git_bisect f011
100%
Passed
Tokens
198
Input
23
Total output
12
Reasoning within output
git_bisect f012
100%
Passed
Tokens
225
Input
28
Total output
15
Reasoning within output
git_clean f001
100%
Passed
Tokens
55
Input
66
Total output
53
Reasoning within output
git_clean f002
100%
Passed
Tokens
66
Input
27
Total output
17
Reasoning within output
git_clean f003
100%
Passed
Tokens
63
Input
20
Total output
9
Reasoning within output
git_clean f004
100%
Passed
Tokens
63
Input
46
Total output
32
Reasoning within output
git_clean f005
100%
Passed
Tokens
55
Input
80
Total output
69
Reasoning within output
git_clean f006
100%
Passed
Tokens
78
Input
42
Total output
30
Reasoning within output
git_clean f007
100%
Passed
Tokens
70
Input
78
Total output
61
Reasoning within output
git_clean f008
100%
Passed
Tokens
77
Input
21
Total output
10
Reasoning within output
git_clean f009
100%
Passed
Tokens
71
Input
32
Total output
20
Reasoning within output
git_clean f010
100%
Passed
Tokens
68
Input
58
Total output
47
Reasoning within output
git_clean f011
100%
Passed
Tokens
67
Input
64
Total output
52
Reasoning within output
git_clean f012
66.7%
Failed
Tokens
69
Input
23
Total output
10
Reasoning within output
git_grep f001
100%
Passed
Tokens
58
Input
23
Total output
19
Reasoning within output
git_grep f002
100%
Passed
Tokens
71
Input
22
Total output
16
Reasoning within output
git_grep f003
100%
Passed
Tokens
91
Input
22
Total output
14
Reasoning within output
git_grep f004
100%
Passed
Tokens
83
Input
24
Total output
12
Reasoning within output
git_grep f005
100%
Passed
Tokens
118
Input
45
Total output
38
Reasoning within output
git_grep f006
100%
Passed
Tokens
48
Input
38
Total output
31
Reasoning within output
git_grep f007
100%
Passed
Tokens
163
Input
251
Total output
244
Reasoning within output
git_grep f008
100%
Passed
Tokens
65
Input
28
Total output
21
Reasoning within output
git_grep f009
100%
Passed
Tokens
61
Input
21
Total output
11
Reasoning within output
git_grep f010
100%
Passed
Tokens
70
Input
59
Total output
53
Reasoning within output
git_grep f011
100%
Passed
Tokens
115
Input
16
Total output
9
Reasoning within output
git_grep f012
100%
Passed
Tokens
72
Input
36
Total output
22
Reasoning within output
git_log_format f001
100%
Passed
Tokens
717
Input
36
Total output
29
Reasoning within output
git_log_format f002
100%
Passed
Tokens
692
Input
39
Total output
35
Reasoning within output
git_log_format f003
100%
Passed
Tokens
564
Input
37
Total output
22
Reasoning within output
git_log_format f004
100%
Passed
Tokens
711
Input
38
Total output
30
Reasoning within output
git_log_format f005
100%
Passed
Tokens
572
Input
69
Total output
58
Reasoning within output
git_log_format f006
100%
Passed
Tokens
702
Input
64
Total output
56
Reasoning within output
git_log_format f007
100%
Passed
Tokens
716
Input
30
Total output
18
Reasoning within output
git_log_format f008
100%
Passed
Tokens
945
Input
21
Total output
14
Reasoning within output
git_log_format f009
100%
Passed
Tokens
572
Input
35
Total output
27
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,055
Input
37
Total output
19
Reasoning within output
git_log_format f011
100%
Passed
Tokens
361
Input
34
Total output
25
Reasoning within output
git_log_format f012
100%
Passed
Tokens
333
Input
12
Total output
4
Reasoning within output
git_show f001
100%
Passed
Tokens
180
Input
38
Total output
28
Reasoning within output
git_show f002
100%
Passed
Tokens
174
Input
14
Total output
6
Reasoning within output
git_show f003
100%
Passed
Tokens
582
Input
42
Total output
28
Reasoning within output
git_show f004
100%
Passed
Tokens
406
Input
39
Total output
26
Reasoning within output
git_show f005
100%
Passed
Tokens
178
Input
28
Total output
20
Reasoning within output
git_show f006
100%
Passed
Tokens
192
Input
15
Total output
8
Reasoning within output
git_show f007
100%
Passed
Tokens
172
Input
20
Total output
10
Reasoning within output
git_show f008
100%
Passed
Tokens
188
Input
65
Total output
35
Reasoning within output
git_show f009
100%
Passed
Tokens
262
Input
53
Total output
45
Reasoning within output
git_show f010
100%
Passed
Tokens
181
Input
13
Total output
5
Reasoning within output
git_show f011
100%
Passed
Tokens
204
Input
32
Total output
24
Reasoning within output
git_show f012
100%
Passed
Tokens
299
Input
34
Total output
26
Reasoning within output
merge_conflicts f001
0%
Failed
Tokens
89
Input
162
Total output
149
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
109
Input
54
Total output
42
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
84
Input
121
Total output
129
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
135
Input
242
Total output
214
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
140
Input
30
Total output
7
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
124
Input
49
Total output
24
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
129
Input
68
Total output
57
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
111
Input
26
Total output
13
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
108
Input
32
Total output
20
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
178
Input
181
Total output
178
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
147
Input
50
Total output
22
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
228
Input
320
Total output
276
Reasoning within output
rebase f001
100%
Passed
Tokens
98
Input
99
Total output
104
Reasoning within output
rebase f002
100%
Passed
Tokens
129
Input
28
Total output
14
Reasoning within output
rebase f003
100%
Passed
Tokens
109
Input
29
Total output
20
Reasoning within output
rebase f004
100%
Passed
Tokens
147
Input
57
Total output
29
Reasoning within output
rebase f005
100%
Passed
Tokens
143
Input
61
Total output
41
Reasoning within output
rebase f006
100%
Passed
Tokens
135
Input
50
Total output
25
Reasoning within output
rebase f007
100%
Passed
Tokens
131
Input
28
Total output
14
Reasoning within output
rebase f008
100%
Passed
Tokens
124
Input
27
Total output
17
Reasoning within output
rebase f009
100%
Passed
Tokens
107
Input
30
Total output
18
Reasoning within output
rebase f010
100%
Passed
Tokens
205
Input
72
Total output
46
Reasoning within output
rebase f011
100%
Passed
Tokens
157
Input
88
Total output
60
Reasoning within output
rebase f012
0%
Failed
Tokens
259
Input
96
Total output
51
Reasoning within output
reflog f001
100%
Passed
Tokens
204
Input
67
Total output
42
Reasoning within output
reflog f002
100%
Passed
Tokens
203
Input
128
Total output
45
Reasoning within output
reflog f003
100%
Passed
Tokens
184
Input
104
Total output
46
Reasoning within output
reflog f004
100%
Passed
Tokens
289
Input
202
Total output
65
Reasoning within output
reflog f005
100%
Passed
Tokens
321
Input
211
Total output
130
Reasoning within output
reflog f006
100%
Passed
Tokens
224
Input
69
Total output
30
Reasoning within output
reflog f007
100%
Passed
Tokens
251
Input
76
Total output
11
Reasoning within output
reflog f008
100%
Passed
Tokens
322
Input
93
Total output
39
Reasoning within output
reflog f009
100%
Passed
Tokens
290
Input
155
Total output
68
Reasoning within output
reflog f010
100%
Passed
Tokens
236
Input
86
Total output
31
Reasoning within output
reflog f011
100%
Passed
Tokens
293
Input
208
Total output
104
Reasoning within output
reflog f012
100%
Passed
Tokens
289
Input
212
Total output
90
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
135
Input
28
Total output
9
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
273
Input
79
Total output
9
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
121
Input
45
Total output
24
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
119
Input
110
Total output
47
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
128
Input
41
Total output
26
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
176
Input
35
Total output
12
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
204
Input
41
Total output
18
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
170
Input
99
Total output
52
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
202
Input
93
Total output
46
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
128
Input
30
Total output
12
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
116
Input
54
Total output
34
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
133
Input
57
Total output
11
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
51
Input
29
Total output
13
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
100
Input
35
Total output
19
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
99
Input
149
Total output
131
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
87
Input
23
Total output
12
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
58
Input
63
Total output
33
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
82
Input
23
Total output
14
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
59
Input
47
Total output
22
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
97
Input
67
Total output
54
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
88
Input
30
Total output
20
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
101
Input
26
Total output
15
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
103
Input
26
Total output
16
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
57
Input
33
Total output
14
Reasoning within output
tag_management f001
100%
Passed
Tokens
65
Input
24
Total output
11
Reasoning within output
tag_management f002
100%
Passed
Tokens
63
Input
45
Total output
17
Reasoning within output
tag_management f003
100%
Passed
Tokens
68
Input
39
Total output
20
Reasoning within output
tag_management f004
100%
Passed
Tokens
71
Input
32
Total output
24
Reasoning within output
tag_management f005
100%
Passed
Tokens
83
Input
49
Total output
34
Reasoning within output
tag_management f006
100%
Passed
Tokens
69
Input
43
Total output
27
Reasoning within output
tag_management f007
66.7%
Failed
Tokens
71
Input
180
Total output
159
Reasoning within output
tag_management f008
100%
Passed
Tokens
74
Input
52
Total output
15
Reasoning within output
tag_management f009
100%
Passed
Tokens
76
Input
43
Total output
16
Reasoning within output
tag_management f010
100%
Passed
Tokens
55
Input
25
Total output
11
Reasoning within output
tag_management f011
100%
Passed
Tokens
53
Input
41
Total output
29
Reasoning within output
tag_management f012
100%
Passed
Tokens
88
Input
151
Total output
136
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
131
Input
31
Total output
15
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
131
Input
54
Total output
27
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
186
Input
48
Total output
35
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
185
Input
27
Total output
19
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
121
Input
34
Total output
19
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
127
Input
35
Total output
16
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
133
Input
49
Total output
24
Reasoning within output
worktree_usage f008
100%
Passed
Tokens
153
Input
111
Total output
56
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
225
Input
20
Total output
12
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
193
Input
39
Total output
18
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
188
Input
46
Total output
32
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
124
Input
38
Total output
19
Reasoning within output