Thinkingmachines / inkling
xhigh
97.1%
198 / 204 fixtures · 1 run(s)
36,010 input / 85,403 total output / 80,805 reasoning within output tokens $0.37861079
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-27.9%
Text: 97.1% →
JSON: 69.1%
+1
Gained
JSON pass / text fail
−59
Lost
Text pass / JSON fail
139
Unchanged Pass
Both pass
5
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| commit_messages | 100% | 33.3% | -66.7% |
| git_bisect | 100% | 50% | -50% |
| git_log_format | 100% | 50% | -50% |
| stash_recovery | 100% | 50% | -50% |
| commit_squash | 100% | 58.3% | -41.7% |
| git_clean | 100% | 58.3% | -41.7% |
| merge_conflicts | 91.7% | 50% | -41.7% |
| cherry_pick | 83.3% | 50% | -33.3% |
| branch_cleanup | 100% | 75% | -25% |
| git_show | 100% | 75% | -25% |
| reflog | 100% | 83.3% | -16.7% |
| submodule_usage | 100% | 83.3% | -16.7% |
| git_grep | 100% | 91.7% | -8.3% |
| rebase | 83.3% | 75% | -8.3% |
| blame_forensics | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
| worktree_usage | 91.7% | 91.7% | + 0% |
Changed Fixtures (60)
f002 -loss f005 -loss f011 -loss f003 -loss f007 -loss f008 -loss f009 -loss f001 -loss f002 -loss f004 -loss f005 -loss f006 -loss f008 -loss f009 -loss f012 -loss f001 -loss f002 -loss f004 -loss f009 -loss f012 -loss f001 -loss f002 -loss f006 -loss f010 -loss f011 -loss f012 -loss f001 -loss f004 -loss f007 -loss f010 -loss f011 -loss f004 -loss f001 -loss f002 -loss f003 -loss f004 -loss f007 -loss f012 -loss f002 -loss f006 -loss f008 -loss f002 -loss f005 -loss f007 -loss f008 -loss f010 -loss f001 -loss f011 -loss f007 -loss f008 -loss f002 -loss f005 -loss f008 -loss f009 -loss f010 -loss f011 -loss f009 -loss f011 -loss f007 -loss f008 +gain
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
230
Input
244
Total output
233
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
207
Input
130
Total output
119
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
234
Input
58
Total output
50
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
176
Input
180
Total output
168
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
227
Input
2,634
Total output
2,624
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
214
Input
396
Total output
386
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
188
Input
99
Total output
88
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
214
Input
328
Total output
291
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
182
Input
161
Total output
161
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
368
Input
273
Total output
274
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
216
Input
168
Total output
135
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
140
Input
133
Total output
118
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
108
Input
429
Total output
418
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
122
Input
216
Total output
201
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
100
Input
175
Total output
168
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
130
Input
172
Total output
161
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
105
Input
168
Total output
159
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
128
Input
184
Total output
171
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
107
Input
166
Total output
155
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
121
Input
212
Total output
184
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
85
Input
372
Total output
365
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
121
Input
306
Total output
266
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
73
Input
229
Total output
268
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
160
Input
208
Total output
191
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
99
Input
378
Total output
367
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
120
Input
2,102
Total output
2,088
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
95
Input
2,504
Total output
2,495
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
147
Input
2,149
Total output
2,127
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
154
Input
206
Total output
225
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
136
Input
720
Total output
711
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
129
Input
328
Total output
314
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
125
Input
113
Total output
101
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
111
Input
112
Total output
100
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
209
Input
570
Total output
539
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
167
Input
177
Total output
144
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
263
Input
975
Total output
931
Reasoning within output
commit_messages f001
84.3%
Passed
Tokens
110
Input
197
Total output
191
Reasoning within output
commit_messages f002
90.3%
Passed
Tokens
204
Input
187
Total output
187
Reasoning within output
commit_messages f003
89.3%
Passed
Tokens
89
Input
195
Total output
180
Reasoning within output
commit_messages f004
93.3%
Passed
Tokens
117
Input
127
Total output
117
Reasoning within output
commit_messages f005
80%
Passed
Tokens
105
Input
188
Total output
180
Reasoning within output
commit_messages f006
93.3%
Passed
Tokens
140
Input
182
Total output
170
Reasoning within output
commit_messages f007
89.3%
Passed
Tokens
182
Input
157
Total output
145
Reasoning within output
commit_messages f008
91%
Passed
Tokens
77
Input
178
Total output
167
Reasoning within output
commit_messages f009
72.7%
Passed
Tokens
129
Input
154
Total output
143
Reasoning within output
commit_messages f010
90%
Passed
Tokens
265
Input
395
Total output
383
Reasoning within output
commit_messages f011
81.7%
Passed
Tokens
147
Input
534
Total output
517
Reasoning within output
commit_messages f012
91.7%
Passed
Tokens
130
Input
113
Total output
128
Reasoning within output
commit_squash f001
100%
Passed
Tokens
139
Input
441
Total output
423
Reasoning within output
commit_squash f002
100%
Passed
Tokens
120
Input
152
Total output
138
Reasoning within output
commit_squash f003
100%
Passed
Tokens
131
Input
279
Total output
261
Reasoning within output
commit_squash f004
100%
Passed
Tokens
117
Input
312
Total output
294
Reasoning within output
commit_squash f005
100%
Passed
Tokens
121
Input
228
Total output
214
Reasoning within output
commit_squash f006
100%
Passed
Tokens
106
Input
196
Total output
190
Reasoning within output
commit_squash f007
100%
Passed
Tokens
106
Input
76
Total output
58
Reasoning within output
commit_squash f008
100%
Passed
Tokens
119
Input
192
Total output
173
Reasoning within output
commit_squash f009
100%
Passed
Tokens
110
Input
222
Total output
205
Reasoning within output
commit_squash f010
100%
Passed
Tokens
126
Input
177
Total output
156
Reasoning within output
commit_squash f011
100%
Passed
Tokens
139
Input
192
Total output
170
Reasoning within output
commit_squash f012
100%
Passed
Tokens
132
Input
230
Total output
203
Reasoning within output
git_bisect f001
100%
Passed
Tokens
179
Input
37
Total output
28
Reasoning within output
git_bisect f002
100%
Passed
Tokens
202
Input
223
Total output
184
Reasoning within output
git_bisect f003
100%
Passed
Tokens
196
Input
163
Total output
104
Reasoning within output
git_bisect f004
100%
Passed
Tokens
194
Input
159
Total output
98
Reasoning within output
git_bisect f005
100%
Passed
Tokens
200
Input
143
Total output
106
Reasoning within output
git_bisect f006
100%
Passed
Tokens
227
Input
134
Total output
94
Reasoning within output
git_bisect f007
100%
Passed
Tokens
200
Input
194
Total output
114
Reasoning within output
git_bisect f008
100%
Passed
Tokens
198
Input
179
Total output
169
Reasoning within output
git_bisect f009
100%
Passed
Tokens
202
Input
235
Total output
146
Reasoning within output
git_bisect f010
100%
Passed
Tokens
198
Input
120
Total output
109
Reasoning within output
git_bisect f011
100%
Passed
Tokens
194
Input
110
Total output
99
Reasoning within output
git_bisect f012
100%
Passed
Tokens
229
Input
139
Total output
129
Reasoning within output
git_clean f001
100%
Passed
Tokens
55
Input
117
Total output
103
Reasoning within output
git_clean f002
100%
Passed
Tokens
66
Input
130
Total output
120
Reasoning within output
git_clean f003
100%
Passed
Tokens
63
Input
123
Total output
112
Reasoning within output
git_clean f004
100%
Passed
Tokens
63
Input
452
Total output
442
Reasoning within output
git_clean f005
100%
Passed
Tokens
55
Input
249
Total output
238
Reasoning within output
git_clean f006
100%
Passed
Tokens
78
Input
417
Total output
404
Reasoning within output
git_clean f007
100%
Passed
Tokens
70
Input
249
Total output
235
Reasoning within output
git_clean f008
100%
Passed
Tokens
77
Input
302
Total output
292
Reasoning within output
git_clean f009
100%
Passed
Tokens
71
Input
85
Total output
84
Reasoning within output
git_clean f010
100%
Passed
Tokens
68
Input
184
Total output
173
Reasoning within output
git_clean f011
100%
Passed
Tokens
67
Input
192
Total output
181
Reasoning within output
git_clean f012
100%
Passed
Tokens
69
Input
300
Total output
312
Reasoning within output
git_grep f001
100%
Passed
Tokens
58
Input
76
Total output
66
Reasoning within output
git_grep f002
100%
Passed
Tokens
71
Input
55
Total output
47
Reasoning within output
git_grep f003
100%
Passed
Tokens
91
Input
33
Total output
26
Reasoning within output
git_grep f004
100%
Passed
Tokens
83
Input
118
Total output
106
Reasoning within output
git_grep f005
100%
Passed
Tokens
118
Input
125
Total output
118
Reasoning within output
git_grep f006
100%
Passed
Tokens
48
Input
151
Total output
144
Reasoning within output
git_grep f007
100%
Passed
Tokens
163
Input
796
Total output
747
Reasoning within output
git_grep f008
100%
Passed
Tokens
65
Input
97
Total output
95
Reasoning within output
git_grep f009
100%
Passed
Tokens
61
Input
53
Total output
43
Reasoning within output
git_grep f010
100%
Passed
Tokens
70
Input
173
Total output
165
Reasoning within output
git_grep f011
100%
Passed
Tokens
115
Input
128
Total output
120
Reasoning within output
git_grep f012
100%
Passed
Tokens
72
Input
81
Total output
66
Reasoning within output
git_log_format f001
100%
Passed
Tokens
689
Input
59
Total output
58
Reasoning within output
git_log_format f002
100%
Passed
Tokens
701
Input
149
Total output
160
Reasoning within output
git_log_format f003
100%
Passed
Tokens
574
Input
222
Total output
208
Reasoning within output
git_log_format f004
100%
Passed
Tokens
696
Input
40
Total output
32
Reasoning within output
git_log_format f005
100%
Passed
Tokens
572
Input
230
Total output
210
Reasoning within output
git_log_format f006
100%
Passed
Tokens
702
Input
109
Total output
59
Reasoning within output
git_log_format f007
100%
Passed
Tokens
704
Input
104
Total output
94
Reasoning within output
git_log_format f008
100%
Passed
Tokens
960
Input
29
Total output
22
Reasoning within output
git_log_format f009
100%
Passed
Tokens
569
Input
64
Total output
56
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,067
Input
62
Total output
50
Reasoning within output
git_log_format f011
100%
Passed
Tokens
360
Input
103
Total output
94
Reasoning within output
git_log_format f012
100%
Passed
Tokens
321
Input
37
Total output
29
Reasoning within output
git_show f001
100%
Passed
Tokens
179
Input
71
Total output
70
Reasoning within output
git_show f002
100%
Passed
Tokens
175
Input
159
Total output
150
Reasoning within output
git_show f003
100%
Passed
Tokens
570
Input
304
Total output
292
Reasoning within output
git_show f004
100%
Passed
Tokens
398
Input
63
Total output
49
Reasoning within output
git_show f005
100%
Passed
Tokens
180
Input
164
Total output
174
Reasoning within output
git_show f006
100%
Passed
Tokens
184
Input
83
Total output
76
Reasoning within output
git_show f007
100%
Passed
Tokens
172
Input
80
Total output
73
Reasoning within output
git_show f008
100%
Passed
Tokens
185
Input
111
Total output
78
Reasoning within output
git_show f009
100%
Passed
Tokens
272
Input
90
Total output
83
Reasoning within output
git_show f010
100%
Passed
Tokens
173
Input
154
Total output
146
Reasoning within output
git_show f011
100%
Passed
Tokens
205
Input
35
Total output
32
Reasoning within output
git_show f012
100%
Passed
Tokens
296
Input
122
Total output
114
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
89
Input
355
Total output
345
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
109
Input
2,092
Total output
2,078
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
84
Input
5,527
Total output
5,517
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
135
Input
4,092
Total output
4,481
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
140
Input
281
Total output
259
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
124
Input
696
Total output
666
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
129
Input
290
Total output
276
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
111
Input
179
Total output
168
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
108
Input
198
Total output
187
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
178
Input
422
Total output
392
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
147
Input
254
Total output
226
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
228
Input
640
Total output
613
Reasoning within output
rebase f001
100%
Passed
Tokens
99
Input
1,041
Total output
1,031
Reasoning within output
rebase f002
100%
Passed
Tokens
128
Input
107
Total output
93
Reasoning within output
rebase f003
100%
Passed
Tokens
107
Input
95
Total output
101
Reasoning within output
rebase f004
0%
Failed
Tokens
145
Input
7,821
Total output
7,807
Reasoning within output
rebase f005
100%
Passed
Tokens
145
Input
326
Total output
369
Reasoning within output
rebase f006
100%
Passed
Tokens
135
Input
2,195
Total output
2,170
Reasoning within output
rebase f007
100%
Passed
Tokens
130
Input
94
Total output
80
Reasoning within output
rebase f008
100%
Passed
Tokens
121
Input
178
Total output
167
Reasoning within output
rebase f009
100%
Passed
Tokens
105
Input
147
Total output
147
Reasoning within output
rebase f010
100%
Passed
Tokens
201
Input
421
Total output
390
Reasoning within output
rebase f011
100%
Passed
Tokens
154
Input
264
Total output
237
Reasoning within output
rebase f012
0%
Failed
Tokens
257
Input
3,187
Total output
3,142
Reasoning within output
reflog f001
100%
Passed
Tokens
217
Input
292
Total output
259
Reasoning within output
reflog f002
100%
Passed
Tokens
204
Input
497
Total output
376
Reasoning within output
reflog f003
100%
Passed
Tokens
184
Input
325
Total output
178
Reasoning within output
reflog f004
100%
Passed
Tokens
286
Input
1,833
Total output
1,640
Reasoning within output
reflog f005
100%
Passed
Tokens
323
Input
831
Total output
731
Reasoning within output
reflog f006
100%
Passed
Tokens
213
Input
429
Total output
263
Reasoning within output
reflog f007
100%
Passed
Tokens
242
Input
965
Total output
848
Reasoning within output
reflog f008
100%
Passed
Tokens
319
Input
556
Total output
436
Reasoning within output
reflog f009
100%
Passed
Tokens
274
Input
496
Total output
333
Reasoning within output
reflog f010
100%
Passed
Tokens
242
Input
324
Total output
242
Reasoning within output
reflog f011
100%
Passed
Tokens
279
Input
3,692
Total output
3,509
Reasoning within output
reflog f012
100%
Passed
Tokens
290
Input
1,183
Total output
908
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
133
Input
139
Total output
85
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
273
Input
214
Total output
135
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
121
Input
104
Total output
61
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
119
Input
564
Total output
506
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
129
Input
293
Total output
201
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
176
Input
106
Total output
72
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
198
Input
160
Total output
105
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
170
Input
150
Total output
97
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
202
Input
178
Total output
127
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
128
Input
132
Total output
115
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
120
Input
525
Total output
421
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
133
Input
170
Total output
126
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
51
Input
90
Total output
77
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
100
Input
385
Total output
370
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
101
Input
304
Total output
288
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
84
Input
44
Total output
34
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
58
Input
264
Total output
234
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
84
Input
1,014
Total output
1,147
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
59
Input
123
Total output
97
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
92
Input
207
Total output
194
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
90
Input
106
Total output
106
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
96
Input
298
Total output
285
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
95
Input
97
Total output
94
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
57
Input
120
Total output
102
Reasoning within output
tag_management f001
100%
Passed
Tokens
64
Input
72
Total output
65
Reasoning within output
tag_management f002
100%
Passed
Tokens
62
Input
284
Total output
260
Reasoning within output
tag_management f003
100%
Passed
Tokens
70
Input
95
Total output
80
Reasoning within output
tag_management f004
100%
Passed
Tokens
72
Input
105
Total output
97
Reasoning within output
tag_management f005
100%
Passed
Tokens
83
Input
140
Total output
102
Reasoning within output
tag_management f006
100%
Passed
Tokens
67
Input
288
Total output
219
Reasoning within output
tag_management f007
100%
Passed
Tokens
70
Input
391
Total output
319
Reasoning within output
tag_management f008
100%
Passed
Tokens
76
Input
360
Total output
330
Reasoning within output
tag_management f009
100%
Passed
Tokens
78
Input
232
Total output
207
Reasoning within output
tag_management f010
100%
Passed
Tokens
55
Input
39
Total output
26
Reasoning within output
tag_management f011
100%
Passed
Tokens
54
Input
147
Total output
136
Reasoning within output
tag_management f012
100%
Passed
Tokens
89
Input
204
Total output
189
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
130
Input
154
Total output
139
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
138
Input
336
Total output
306
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
195
Input
122
Total output
117
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
191
Input
216
Total output
241
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
123
Input
82
Total output
65
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
125
Input
259
Total output
238
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
131
Input
150
Total output
125
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
151
Input
648
Total output
590
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
219
Input
174
Total output
193
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
191
Input
86
Total output
65
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
188
Input
114
Total output
106
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
125
Input
148
Total output
129
Reasoning within output