Thinkingmachines / inkling
high
96.6%
197 / 204 fixtures · 1 run(s)
36,142 input / 100,568 total output / 96,605 reasoning within output tokens $0.43943280
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-47.1%
Text: 96.6% →
JSON: 49.5%
+1
Gained
JSON pass / text fail
−97
Lost
Text pass / JSON fail
100
Unchanged Pass
Both pass
6
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| branch_cleanup | 100% | 33.3% | -66.7% |
| submodule_usage | 100% | 33.3% | -66.7% |
| cherry_pick | 83.3% | 16.7% | -66.7% |
| git_show | 100% | 41.7% | -58.3% |
| stash_recovery | 100% | 41.7% | -58.3% |
| commit_messages | 100% | 50% | -50% |
| git_grep | 100% | 50% | -50% |
| worktree_usage | 100% | 50% | -50% |
| commit_squash | 100% | 58.3% | -41.7% |
| git_bisect | 100% | 58.3% | -41.7% |
| reflog | 100% | 58.3% | -41.7% |
| merge_conflicts | 83.3% | 41.7% | -41.7% |
| rebase | 83.3% | 41.7% | -41.7% |
| tag_management | 91.7% | 58.3% | -33.3% |
| blame_forensics | 100% | 66.7% | -33.3% |
| git_clean | 100% | 66.7% | -33.3% |
| git_log_format | 100% | 75% | -25% |
Changed Fixtures (98)
f002 -loss f003 -loss f011 -loss f012 -loss f001 -loss f002 -loss f003 -loss f006 -loss f008 -loss f010 -loss f011 -loss f012 -loss f001 -loss f002 -loss f003 -loss f006 -loss f008 -loss f009 -loss f010 -loss f011 -loss f001 -loss f004 -loss f005 -loss f006 -loss f007 -loss f012 -loss f001 -loss f004 -loss f007 -loss f011 -loss f012 -loss f002 -loss f003 -loss f004 -loss f005 -loss f006 -loss f001 -loss f005 -loss f008 -loss f012 -loss f002 -loss f003 -loss f007 -loss f008 -loss f010 -loss f011 -loss f002 -loss f005 -loss f008 -loss f003 -loss f005 -loss f006 -loss f007 -loss f009 -loss f011 -loss f012 -loss f005 -loss f007 -loss f008 -loss f010 -loss f011 -loss f002 -loss f007 -loss f009 -loss f010 -loss f011 -loss f005 -loss f006 -loss f008 -loss f009 -loss f010 -loss f001 -loss f005 -loss f008 -loss f009 -loss f010 -loss f011 -loss f012 -loss f001 -loss f002 -loss f004 -loss f005 -loss f007 -loss f008 -loss f009 -loss f012 -loss f001 -loss f002 -loss f007 +gain f008 -loss f009 -loss f012 -loss f003 -loss f005 -loss f008 -loss f009 -loss f010 -loss f012 -loss
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
224
Input
246
Total output
234
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
206
Input
133
Total output
118
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
237
Input
98
Total output
85
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
172
Input
42
Total output
31
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
231
Input
583
Total output
553
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
218
Input
302
Total output
269
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
191
Input
215
Total output
178
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
217
Input
180
Total output
169
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
180
Input
97
Total output
86
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
378
Input
223
Total output
213
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
215
Input
221
Total output
211
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
135
Input
96
Total output
87
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
104
Input
196
Total output
185
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
117
Input
211
Total output
200
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
99
Input
450
Total output
443
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
125
Input
137
Total output
126
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
110
Input
243
Total output
233
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
125
Input
138
Total output
124
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
107
Input
180
Total output
188
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
128
Input
230
Total output
197
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
84
Input
366
Total output
444
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
120
Input
221
Total output
210
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
75
Input
122
Total output
114
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
156
Input
225
Total output
208
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
97
Input
420
Total output
410
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
120
Input
1,044
Total output
1,032
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
92
Input
2,331
Total output
2,737
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
148
Input
1,960
Total output
1,935
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
152
Input
122
Total output
128
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
137
Input
1,009
Total output
983
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
128
Input
443
Total output
428
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
127
Input
128
Total output
115
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
111
Input
158
Total output
159
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
215
Input
677
Total output
647
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
166
Input
248
Total output
221
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
263
Input
999
Total output
1,059
Reasoning within output
commit_messages f001
93%
Passed
Tokens
110
Input
299
Total output
298
Reasoning within output
commit_messages f002
85%
Passed
Tokens
204
Input
291
Total output
269
Reasoning within output
commit_messages f003
94.3%
Passed
Tokens
89
Input
374
Total output
259
Reasoning within output
commit_messages f004
92.7%
Passed
Tokens
117
Input
130
Total output
121
Reasoning within output
commit_messages f005
88.3%
Passed
Tokens
105
Input
173
Total output
163
Reasoning within output
commit_messages f006
91%
Passed
Tokens
140
Input
309
Total output
297
Reasoning within output
commit_messages f007
91.7%
Passed
Tokens
182
Input
129
Total output
130
Reasoning within output
commit_messages f008
93.3%
Passed
Tokens
77
Input
127
Total output
117
Reasoning within output
commit_messages f009
86.7%
Passed
Tokens
129
Input
234
Total output
233
Reasoning within output
commit_messages f010
91.7%
Passed
Tokens
265
Input
344
Total output
332
Reasoning within output
commit_messages f011
84%
Passed
Tokens
147
Input
403
Total output
391
Reasoning within output
commit_messages f012
90%
Passed
Tokens
130
Input
148
Total output
137
Reasoning within output
commit_squash f001
100%
Passed
Tokens
139
Input
694
Total output
767
Reasoning within output
commit_squash f002
100%
Passed
Tokens
123
Input
156
Total output
144
Reasoning within output
commit_squash f003
100%
Passed
Tokens
131
Input
303
Total output
284
Reasoning within output
commit_squash f004
100%
Passed
Tokens
125
Input
274
Total output
261
Reasoning within output
commit_squash f005
100%
Passed
Tokens
116
Input
286
Total output
272
Reasoning within output
commit_squash f006
100%
Passed
Tokens
102
Input
226
Total output
232
Reasoning within output
commit_squash f007
100%
Passed
Tokens
103
Input
267
Total output
249
Reasoning within output
commit_squash f008
100%
Passed
Tokens
117
Input
213
Total output
194
Reasoning within output
commit_squash f009
100%
Passed
Tokens
110
Input
302
Total output
288
Reasoning within output
commit_squash f010
100%
Passed
Tokens
124
Input
233
Total output
211
Reasoning within output
commit_squash f011
100%
Passed
Tokens
134
Input
247
Total output
220
Reasoning within output
commit_squash f012
100%
Passed
Tokens
133
Input
234
Total output
207
Reasoning within output
git_bisect f001
100%
Passed
Tokens
173
Input
100
Total output
88
Reasoning within output
git_bisect f002
100%
Passed
Tokens
206
Input
121
Total output
88
Reasoning within output
git_bisect f003
100%
Passed
Tokens
194
Input
141
Total output
101
Reasoning within output
git_bisect f004
100%
Passed
Tokens
198
Input
168
Total output
157
Reasoning within output
git_bisect f005
100%
Passed
Tokens
196
Input
167
Total output
124
Reasoning within output
git_bisect f006
100%
Passed
Tokens
223
Input
129
Total output
94
Reasoning within output
git_bisect f007
100%
Passed
Tokens
200
Input
131
Total output
104
Reasoning within output
git_bisect f008
100%
Passed
Tokens
196
Input
218
Total output
139
Reasoning within output
git_bisect f009
100%
Passed
Tokens
196
Input
169
Total output
159
Reasoning within output
git_bisect f010
100%
Passed
Tokens
204
Input
172
Total output
121
Reasoning within output
git_bisect f011
100%
Passed
Tokens
206
Input
198
Total output
94
Reasoning within output
git_bisect f012
100%
Passed
Tokens
227
Input
222
Total output
110
Reasoning within output
git_clean f001
100%
Passed
Tokens
55
Input
97
Total output
84
Reasoning within output
git_clean f002
100%
Passed
Tokens
66
Input
76
Total output
65
Reasoning within output
git_clean f003
100%
Passed
Tokens
63
Input
78
Total output
78
Reasoning within output
git_clean f004
100%
Passed
Tokens
63
Input
335
Total output
322
Reasoning within output
git_clean f005
100%
Passed
Tokens
55
Input
232
Total output
238
Reasoning within output
git_clean f006
100%
Passed
Tokens
78
Input
105
Total output
93
Reasoning within output
git_clean f007
100%
Passed
Tokens
70
Input
415
Total output
401
Reasoning within output
git_clean f008
100%
Passed
Tokens
77
Input
274
Total output
258
Reasoning within output
git_clean f009
100%
Passed
Tokens
71
Input
150
Total output
137
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
404
Total output
456
Reasoning within output
git_clean f012
100%
Passed
Tokens
69
Input
297
Total output
284
Reasoning within output
git_grep f001
100%
Passed
Tokens
58
Input
92
Total output
96
Reasoning within output
git_grep f002
100%
Passed
Tokens
73
Input
94
Total output
86
Reasoning within output
git_grep f003
100%
Passed
Tokens
91
Input
99
Total output
104
Reasoning within output
git_grep f004
100%
Passed
Tokens
83
Input
115
Total output
97
Reasoning within output
git_grep f005
100%
Passed
Tokens
118
Input
117
Total output
110
Reasoning within output
git_grep f006
100%
Passed
Tokens
48
Input
210
Total output
241
Reasoning within output
git_grep f007
100%
Passed
Tokens
163
Input
284
Total output
258
Reasoning within output
git_grep f008
100%
Passed
Tokens
65
Input
57
Total output
56
Reasoning within output
git_grep f009
100%
Passed
Tokens
61
Input
71
Total output
62
Reasoning within output
git_grep f010
100%
Passed
Tokens
70
Input
223
Total output
216
Reasoning within output
git_grep f011
100%
Passed
Tokens
115
Input
88
Total output
81
Reasoning within output
git_grep f012
100%
Passed
Tokens
72
Input
108
Total output
93
Reasoning within output
git_log_format f001
100%
Passed
Tokens
717
Input
82
Total output
75
Reasoning within output
git_log_format f002
100%
Passed
Tokens
683
Input
180
Total output
162
Reasoning within output
git_log_format f003
100%
Passed
Tokens
582
Input
211
Total output
195
Reasoning within output
git_log_format f004
100%
Passed
Tokens
713
Input
59
Total output
41
Reasoning within output
git_log_format f005
100%
Passed
Tokens
572
Input
350
Total output
342
Reasoning within output
git_log_format f006
100%
Passed
Tokens
702
Input
93
Total output
86
Reasoning within output
git_log_format f007
100%
Passed
Tokens
707
Input
89
Total output
78
Reasoning within output
git_log_format f008
100%
Passed
Tokens
940
Input
83
Total output
75
Reasoning within output
git_log_format f009
100%
Passed
Tokens
593
Input
48
Total output
37
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,081
Input
58
Total output
36
Reasoning within output
git_log_format f011
100%
Passed
Tokens
357
Input
71
Total output
62
Reasoning within output
git_log_format f012
100%
Passed
Tokens
324
Input
46
Total output
36
Reasoning within output
git_show f001
100%
Passed
Tokens
176
Input
109
Total output
99
Reasoning within output
git_show f002
100%
Passed
Tokens
174
Input
158
Total output
150
Reasoning within output
git_show f003
100%
Passed
Tokens
566
Input
64
Total output
47
Reasoning within output
git_show f004
100%
Passed
Tokens
396
Input
99
Total output
86
Reasoning within output
git_show f005
100%
Passed
Tokens
181
Input
120
Total output
124
Reasoning within output
git_show f006
100%
Passed
Tokens
185
Input
79
Total output
73
Reasoning within output
git_show f007
100%
Passed
Tokens
172
Input
42
Total output
32
Reasoning within output
git_show f008
100%
Passed
Tokens
186
Input
69
Total output
41
Reasoning within output
git_show f009
100%
Passed
Tokens
272
Input
119
Total output
111
Reasoning within output
git_show f010
100%
Passed
Tokens
181
Input
100
Total output
93
Reasoning within output
git_show f011
100%
Passed
Tokens
202
Input
39
Total output
34
Reasoning within output
git_show f012
100%
Passed
Tokens
302
Input
121
Total output
116
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
89
Input
315
Total output
357
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
109
Input
1,023
Total output
1,011
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
84
Input
2,985
Total output
2,975
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
135
Input
11,458
Total output
12,590
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
140
Input
167
Total output
171
Reasoning within output
merge_conflicts f006
0%
Failed
Tokens
124
Input
710
Total output
683
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
129
Input
285
Total output
271
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
111
Input
230
Total output
220
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
108
Input
130
Total output
118
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
178
Input
530
Total output
500
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
147
Input
259
Total output
231
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
228
Input
890
Total output
931
Reasoning within output
rebase f001
100%
Passed
Tokens
98
Input
828
Total output
818
Reasoning within output
rebase f002
100%
Passed
Tokens
128
Input
118
Total output
104
Reasoning within output
rebase f003
100%
Passed
Tokens
107
Input
99
Total output
89
Reasoning within output
rebase f004
0%
Failed
Tokens
145
Input
3,228
Total output
3,203
Reasoning within output
rebase f005
100%
Passed
Tokens
145
Input
3,739
Total output
3,723
Reasoning within output
rebase f006
100%
Passed
Tokens
135
Input
877
Total output
852
Reasoning within output
rebase f007
100%
Passed
Tokens
130
Input
145
Total output
131
Reasoning within output
rebase f008
100%
Passed
Tokens
124
Input
154
Total output
165
Reasoning within output
rebase f009
100%
Passed
Tokens
105
Input
166
Total output
180
Reasoning within output
rebase f010
100%
Passed
Tokens
199
Input
306
Total output
303
Reasoning within output
rebase f011
100%
Passed
Tokens
157
Input
407
Total output
367
Reasoning within output
rebase f012
0%
Failed
Tokens
255
Input
12,551
Total output
12,516
Reasoning within output
reflog f001
100%
Passed
Tokens
210
Input
215
Total output
156
Reasoning within output
reflog f002
100%
Passed
Tokens
207
Input
387
Total output
278
Reasoning within output
reflog f003
100%
Passed
Tokens
191
Input
398
Total output
236
Reasoning within output
reflog f004
100%
Passed
Tokens
278
Input
4,424
Total output
4,212
Reasoning within output
reflog f005
100%
Passed
Tokens
329
Input
1,551
Total output
1,457
Reasoning within output
reflog f006
100%
Passed
Tokens
223
Input
448
Total output
219
Reasoning within output
reflog f007
100%
Passed
Tokens
249
Input
697
Total output
581
Reasoning within output
reflog f008
100%
Passed
Tokens
311
Input
1,357
Total output
1,021
Reasoning within output
reflog f009
100%
Passed
Tokens
288
Input
1,011
Total output
818
Reasoning within output
reflog f010
100%
Passed
Tokens
251
Input
365
Total output
184
Reasoning within output
reflog f011
100%
Passed
Tokens
284
Input
4,381
Total output
4,114
Reasoning within output
reflog f012
100%
Passed
Tokens
284
Input
1,777
Total output
1,609
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
133
Input
88
Total output
55
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
276
Input
191
Total output
119
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
121
Input
134
Total output
93
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
119
Input
1,696
Total output
1,626
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
130
Input
194
Total output
93
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
176
Input
168
Total output
102
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
206
Input
201
Total output
121
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
170
Input
155
Total output
103
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
202
Input
184
Total output
141
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
128
Input
88
Total output
64
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
120
Input
609
Total output
538
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
133
Input
166
Total output
124
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
51
Input
95
Total output
82
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
99
Input
541
Total output
526
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
102
Input
420
Total output
381
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
88
Input
127
Total output
116
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
58
Input
297
Total output
268
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
85
Input
343
Total output
382
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
59
Input
115
Total output
89
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
91
Input
426
Total output
448
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
93
Input
133
Total output
135
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
94
Input
143
Total output
137
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
98
Input
52
Total output
46
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
57
Input
78
Total output
63
Reasoning within output
tag_management f001
100%
Passed
Tokens
65
Input
51
Total output
38
Reasoning within output
tag_management f002
100%
Passed
Tokens
62
Input
118
Total output
94
Reasoning within output
tag_management f003
100%
Passed
Tokens
69
Input
98
Total output
82
Reasoning within output
tag_management f004
100%
Passed
Tokens
75
Input
81
Total output
72
Reasoning within output
tag_management f005
100%
Passed
Tokens
83
Input
138
Total output
124
Reasoning within output
tag_management f006
100%
Passed
Tokens
68
Input
120
Total output
103
Reasoning within output
tag_management f007
66.7%
Failed
Tokens
71
Input
1,396
Total output
1,171
Reasoning within output
tag_management f008
100%
Passed
Tokens
75
Input
257
Total output
175
Reasoning within output
tag_management f009
100%
Passed
Tokens
76
Input
251
Total output
228
Reasoning within output
tag_management f010
100%
Passed
Tokens
55
Input
80
Total output
60
Reasoning within output
tag_management f011
100%
Passed
Tokens
54
Input
92
Total output
86
Reasoning within output
tag_management f012
100%
Passed
Tokens
88
Input
277
Total output
251
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
132
Input
133
Total output
118
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
138
Input
256
Total output
228
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
196
Input
184
Total output
177
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
191
Input
70
Total output
68
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
130
Input
143
Total output
107
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
130
Input
237
Total output
191
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
125
Input
578
Total output
553
Reasoning within output
worktree_usage f008
100%
Passed
Tokens
150
Input
452
Total output
397
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
225
Input
139
Total output
128
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
196
Input
125
Total output
109
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
191
Input
116
Total output
102
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
129
Input
201
Total output
162
Reasoning within output