Thinkingmachines / inkling-small
medium
97.1%
198 / 204 fixtures · 1 run(s)
36,021 input / 42,443 total output / 37,249 reasoning within output tokens $0.06593300
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-2%
Text: 97.1% →
JSON: 95.1%
+2
Gained
JSON pass / text fail
−6
Lost
Text pass / JSON fail
192
Unchanged Pass
Both pass
4
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| branch_cleanup | 100% | 83.3% | -16.7% |
| merge_conflicts | 91.7% | 83.3% | -8.3% |
| git_grep | 100% | 91.7% | -8.3% |
| git_log_format | 100% | 91.7% | -8.3% |
| reflog | 100% | 91.7% | -8.3% |
| submodule_usage | 91.7% | 100% | + 8.3% |
| tag_management | 91.7% | 100% | + 8.3% |
| blame_forensics | 100% | 100% | + 0% |
| cherry_pick | 83.3% | 83.3% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| commit_squash | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_clean | 100% | 100% | + 0% |
| git_show | 100% | 100% | + 0% |
| rebase | 91.7% | 91.7% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| worktree_usage | 100% | 100% | + 0% |
Changed Fixtures (8)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
224
Input
114
Total output
103
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
212
Input
110
Total output
100
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
234
Input
52
Total output
40
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
173
Input
38
Total output
33
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
227
Input
343
Total output
319
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
220
Input
179
Total output
170
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
194
Input
53
Total output
43
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
214
Input
129
Total output
119
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
182
Input
37
Total output
27
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
358
Input
554
Total output
545
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
213
Input
127
Total output
118
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
141
Input
77
Total output
66
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
108
Input
164
Total output
154
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
122
Input
85
Total output
78
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
98
Input
140
Total output
133
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
128
Input
99
Total output
96
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
104
Input
89
Total output
79
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
127
Input
84
Total output
71
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
104
Input
84
Total output
73
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
124
Input
122
Total output
106
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
86
Input
129
Total output
132
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
120
Input
90
Total output
54
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
75
Input
195
Total output
188
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
155
Input
174
Total output
126
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
99
Input
135
Total output
125
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
121
Input
366
Total output
341
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
92
Input
209
Total output
239
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
148
Input
805
Total output
893
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
150
Input
261
Total output
289
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
136
Input
207
Total output
170
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
126
Input
119
Total output
113
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
125
Input
72
Total output
69
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
110
Input
90
Total output
79
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
209
Input
400
Total output
425
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
168
Input
129
Total output
99
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
259
Input
469
Total output
481
Reasoning within output
commit_messages f001
84.3%
Passed
Tokens
110
Input
341
Total output
327
Reasoning within output
commit_messages f002
91.3%
Passed
Tokens
204
Input
171
Total output
98
Reasoning within output
commit_messages f003
94%
Passed
Tokens
89
Input
151
Total output
142
Reasoning within output
commit_messages f004
93.3%
Passed
Tokens
117
Input
111
Total output
107
Reasoning within output
commit_messages f005
88.3%
Passed
Tokens
105
Input
136
Total output
125
Reasoning within output
commit_messages f006
89.3%
Passed
Tokens
140
Input
902
Total output
890
Reasoning within output
commit_messages f007
90%
Passed
Tokens
182
Input
368
Total output
356
Reasoning within output
commit_messages f008
91.3%
Passed
Tokens
77
Input
53
Total output
43
Reasoning within output
commit_messages f009
90%
Passed
Tokens
129
Input
154
Total output
145
Reasoning within output
commit_messages f010
90%
Passed
Tokens
265
Input
257
Total output
170
Reasoning within output
commit_messages f011
78.7%
Passed
Tokens
147
Input
813
Total output
795
Reasoning within output
commit_messages f012
95%
Passed
Tokens
130
Input
107
Total output
114
Reasoning within output
commit_squash f001
100%
Passed
Tokens
142
Input
1,294
Total output
1,276
Reasoning within output
commit_squash f002
100%
Passed
Tokens
122
Input
145
Total output
131
Reasoning within output
commit_squash f003
100%
Passed
Tokens
131
Input
366
Total output
349
Reasoning within output
commit_squash f004
100%
Passed
Tokens
119
Input
178
Total output
161
Reasoning within output
commit_squash f005
100%
Passed
Tokens
119
Input
306
Total output
293
Reasoning within output
commit_squash f006
100%
Passed
Tokens
108
Input
191
Total output
174
Reasoning within output
commit_squash f007
100%
Passed
Tokens
108
Input
89
Total output
72
Reasoning within output
commit_squash f008
100%
Passed
Tokens
121
Input
310
Total output
292
Reasoning within output
commit_squash f009
100%
Passed
Tokens
109
Input
295
Total output
276
Reasoning within output
commit_squash f010
100%
Passed
Tokens
126
Input
203
Total output
182
Reasoning within output
commit_squash f011
100%
Passed
Tokens
134
Input
408
Total output
367
Reasoning within output
commit_squash f012
100%
Passed
Tokens
129
Input
103
Total output
59
Reasoning within output
git_bisect f001
100%
Passed
Tokens
181
Input
35
Total output
21
Reasoning within output
git_bisect f002
100%
Passed
Tokens
198
Input
114
Total output
80
Reasoning within output
git_bisect f003
100%
Passed
Tokens
190
Input
30
Total output
20
Reasoning within output
git_bisect f004
100%
Passed
Tokens
204
Input
82
Total output
60
Reasoning within output
git_bisect f005
100%
Passed
Tokens
202
Input
143
Total output
130
Reasoning within output
git_bisect f006
100%
Passed
Tokens
217
Input
27
Total output
18
Reasoning within output
git_bisect f007
100%
Passed
Tokens
200
Input
31
Total output
21
Reasoning within output
git_bisect f008
100%
Passed
Tokens
198
Input
117
Total output
91
Reasoning within output
git_bisect f009
100%
Passed
Tokens
198
Input
104
Total output
89
Reasoning within output
git_bisect f010
100%
Passed
Tokens
202
Input
31
Total output
21
Reasoning within output
git_bisect f011
100%
Passed
Tokens
194
Input
64
Total output
36
Reasoning within output
git_bisect f012
100%
Passed
Tokens
227
Input
46
Total output
35
Reasoning within output
git_clean f001
100%
Passed
Tokens
55
Input
109
Total output
107
Reasoning within output
git_clean f002
100%
Passed
Tokens
66
Input
29
Total output
19
Reasoning within output
git_clean f003
100%
Passed
Tokens
63
Input
81
Total output
71
Reasoning within output
git_clean f004
100%
Passed
Tokens
63
Input
263
Total output
272
Reasoning within output
git_clean f005
100%
Passed
Tokens
55
Input
194
Total output
185
Reasoning within output
git_clean f006
100%
Passed
Tokens
78
Input
156
Total output
154
Reasoning within output
git_clean f007
100%
Passed
Tokens
70
Input
114
Total output
100
Reasoning within output
git_clean f008
100%
Passed
Tokens
77
Input
185
Total output
173
Reasoning within output
git_clean f009
100%
Passed
Tokens
71
Input
358
Total output
401
Reasoning within output
git_clean f010
100%
Passed
Tokens
68
Input
92
Total output
80
Reasoning within output
git_clean f011
100%
Passed
Tokens
67
Input
131
Total output
134
Reasoning within output
git_clean f012
100%
Passed
Tokens
69
Input
210
Total output
196
Reasoning within output
git_grep f001
100%
Passed
Tokens
58
Input
35
Total output
29
Reasoning within output
git_grep f002
100%
Passed
Tokens
73
Input
42
Total output
35
Reasoning within output
git_grep f003
100%
Passed
Tokens
91
Input
47
Total output
40
Reasoning within output
git_grep f004
100%
Passed
Tokens
83
Input
34
Total output
23
Reasoning within output
git_grep f005
100%
Passed
Tokens
118
Input
123
Total output
104
Reasoning within output
git_grep f006
100%
Passed
Tokens
48
Input
118
Total output
111
Reasoning within output
git_grep f007
100%
Passed
Tokens
163
Input
1,747
Total output
1,696
Reasoning within output
git_grep f008
100%
Passed
Tokens
65
Input
43
Total output
39
Reasoning within output
git_grep f009
100%
Passed
Tokens
61
Input
48
Total output
35
Reasoning within output
git_grep f010
100%
Passed
Tokens
70
Input
22
Total output
14
Reasoning within output
git_grep f011
100%
Passed
Tokens
115
Input
113
Total output
100
Reasoning within output
git_grep f012
100%
Passed
Tokens
72
Input
46
Total output
32
Reasoning within output
git_log_format f001
100%
Passed
Tokens
715
Input
58
Total output
57
Reasoning within output
git_log_format f002
100%
Passed
Tokens
681
Input
165
Total output
152
Reasoning within output
git_log_format f003
100%
Passed
Tokens
586
Input
224
Total output
222
Reasoning within output
git_log_format f004
100%
Passed
Tokens
708
Input
38
Total output
31
Reasoning within output
git_log_format f005
100%
Passed
Tokens
572
Input
324
Total output
341
Reasoning within output
git_log_format f006
100%
Passed
Tokens
702
Input
51
Total output
32
Reasoning within output
git_log_format f007
100%
Passed
Tokens
717
Input
21
Total output
9
Reasoning within output
git_log_format f008
100%
Passed
Tokens
934
Input
22
Total output
15
Reasoning within output
git_log_format f009
100%
Passed
Tokens
569
Input
27
Total output
20
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,050
Input
26
Total output
18
Reasoning within output
git_log_format f011
100%
Passed
Tokens
357
Input
75
Total output
70
Reasoning within output
git_log_format f012
100%
Passed
Tokens
329
Input
72
Total output
62
Reasoning within output
git_show f001
100%
Passed
Tokens
173
Input
69
Total output
60
Reasoning within output
git_show f002
100%
Passed
Tokens
178
Input
235
Total output
227
Reasoning within output
git_show f003
100%
Passed
Tokens
564
Input
27
Total output
15
Reasoning within output
git_show f004
100%
Passed
Tokens
398
Input
22
Total output
10
Reasoning within output
git_show f005
100%
Passed
Tokens
182
Input
105
Total output
104
Reasoning within output
git_show f006
100%
Passed
Tokens
186
Input
14
Total output
7
Reasoning within output
git_show f007
100%
Passed
Tokens
172
Input
61
Total output
51
Reasoning within output
git_show f008
100%
Passed
Tokens
189
Input
136
Total output
81
Reasoning within output
git_show f009
100%
Passed
Tokens
267
Input
86
Total output
58
Reasoning within output
git_show f010
100%
Passed
Tokens
172
Input
86
Total output
81
Reasoning within output
git_show f011
100%
Passed
Tokens
207
Input
62
Total output
62
Reasoning within output
git_show f012
100%
Passed
Tokens
297
Input
14
Total output
7
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
89
Input
270
Total output
260
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
109
Input
392
Total output
379
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
84
Input
439
Total output
429
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
135
Input
596
Total output
583
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
140
Input
92
Total output
82
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
124
Input
149
Total output
115
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
129
Input
239
Total output
241
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
111
Input
185
Total output
173
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
108
Input
133
Total output
122
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
178
Input
256
Total output
256
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
147
Input
155
Total output
116
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
228
Input
565
Total output
538
Reasoning within output
rebase f001
100%
Passed
Tokens
100
Input
287
Total output
330
Reasoning within output
rebase f002
100%
Passed
Tokens
127
Input
204
Total output
191
Reasoning within output
rebase f003
100%
Passed
Tokens
110
Input
221
Total output
233
Reasoning within output
rebase f004
100%
Passed
Tokens
147
Input
715
Total output
688
Reasoning within output
rebase f005
100%
Passed
Tokens
143
Input
199
Total output
213
Reasoning within output
rebase f006
100%
Passed
Tokens
137
Input
243
Total output
194
Reasoning within output
rebase f007
100%
Passed
Tokens
131
Input
203
Total output
189
Reasoning within output
rebase f008
100%
Passed
Tokens
124
Input
53
Total output
41
Reasoning within output
rebase f009
100%
Passed
Tokens
106
Input
432
Total output
470
Reasoning within output
rebase f010
100%
Passed
Tokens
199
Input
378
Total output
348
Reasoning within output
rebase f011
100%
Passed
Tokens
155
Input
124
Total output
82
Reasoning within output
rebase f012
0%
Failed
Tokens
253
Input
787
Total output
743
Reasoning within output
reflog f001
100%
Passed
Tokens
214
Input
73
Total output
45
Reasoning within output
reflog f002
100%
Passed
Tokens
199
Input
164
Total output
48
Reasoning within output
reflog f003
100%
Passed
Tokens
188
Input
295
Total output
154
Reasoning within output
reflog f004
100%
Passed
Tokens
281
Input
751
Total output
464
Reasoning within output
reflog f005
100%
Passed
Tokens
316
Input
812
Total output
709
Reasoning within output
reflog f006
100%
Passed
Tokens
223
Input
230
Total output
98
Reasoning within output
reflog f007
100%
Passed
Tokens
253
Input
251
Total output
85
Reasoning within output
reflog f008
100%
Passed
Tokens
319
Input
425
Total output
268
Reasoning within output
reflog f009
100%
Passed
Tokens
288
Input
1,284
Total output
960
Reasoning within output
reflog f010
100%
Passed
Tokens
242
Input
158
Total output
58
Reasoning within output
reflog f011
100%
Passed
Tokens
295
Input
550
Total output
305
Reasoning within output
reflog f012
100%
Passed
Tokens
276
Input
812
Total output
462
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
132
Input
130
Total output
74
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
273
Input
220
Total output
127
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
121
Input
86
Total output
40
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
119
Input
170
Total output
127
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
128
Input
83
Total output
36
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
176
Input
107
Total output
47
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
204
Input
203
Total output
127
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
170
Input
173
Total output
99
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
202
Input
128
Total output
80
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
128
Input
48
Total output
12
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
119
Input
413
Total output
362
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
133
Input
192
Total output
127
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
51
Input
62
Total output
47
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
98
Input
480
Total output
510
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
100
Input
645
Total output
611
Reasoning within output
submodule_usage f004
0%
Failed
Tokens
87
Input
7
Total output
0
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
58
Input
155
Total output
122
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
90
Input
348
Total output
338
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
59
Input
154
Total output
130
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
93
Input
495
Total output
522
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
88
Input
68
Total output
58
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
97
Input
99
Total output
87
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
101
Input
62
Total output
52
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
57
Input
103
Total output
91
Reasoning within output
tag_management f001
100%
Passed
Tokens
62
Input
56
Total output
42
Reasoning within output
tag_management f002
100%
Passed
Tokens
62
Input
128
Total output
95
Reasoning within output
tag_management f003
100%
Passed
Tokens
70
Input
74
Total output
56
Reasoning within output
tag_management f004
100%
Passed
Tokens
73
Input
103
Total output
76
Reasoning within output
tag_management f005
100%
Passed
Tokens
90
Input
26
Total output
12
Reasoning within output
tag_management f006
100%
Passed
Tokens
70
Input
97
Total output
80
Reasoning within output
tag_management f007
66.7%
Failed
Tokens
69
Input
315
Total output
227
Reasoning within output
tag_management f008
100%
Passed
Tokens
74
Input
245
Total output
216
Reasoning within output
tag_management f009
100%
Passed
Tokens
78
Input
79
Total output
55
Reasoning within output
tag_management f010
100%
Passed
Tokens
54
Input
95
Total output
75
Reasoning within output
tag_management f011
100%
Passed
Tokens
54
Input
73
Total output
62
Reasoning within output
tag_management f012
100%
Passed
Tokens
87
Input
234
Total output
218
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
134
Input
204
Total output
160
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
140
Input
220
Total output
200
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
184
Input
145
Total output
138
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
187
Input
43
Total output
33
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
120
Input
74
Total output
60
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
127
Input
138
Total output
118
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
127
Input
341
Total output
316
Reasoning within output
worktree_usage f008
100%
Passed
Tokens
148
Input
476
Total output
409
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
228
Input
80
Total output
76
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
191
Input
152
Total output
133
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
189
Input
46
Total output
32
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
127
Input
80
Total output
58
Reasoning within output