Openai / gpt-5.4-mini
high
97.6%
199 / 204 fixtures · 1 run(s)
34,256 input / 42,355 total output / 38,228 reasoning within output tokens $0.21628950
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-4.9%
Text: 97.6% →
JSON: 92.7%
+0
Gained
JSON pass / text fail
−10
Lost
Text pass / JSON fail
189
Unchanged Pass
Both pass
5
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| branch_cleanup | 100% | 75% | -25% |
| cherry_pick | 91.7% | 75% | -16.7% |
| tag_management | 100% | 83.3% | -16.7% |
| merge_conflicts | 91.7% | 83.3% | -8.3% |
| rebase | 91.7% | 83.3% | -8.3% |
| submodule_usage | 100% | 91.7% | -8.3% |
| blame_forensics | 100% | 100% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| commit_squash | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_clean | 100% | 100% | + 0% |
| git_grep | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 100% | 100% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| worktree_usage | 83.3% | 83.3% | + 0% |
Changed Fixtures (10)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
214
Input
357
Total output
346
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
201
Input
212
Total output
202
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
225
Input
65
Total output
53
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
166
Input
296
Total output
285
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
227
Input
166
Total output
157
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
205
Input
417
Total output
408
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
180
Input
95
Total output
85
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
213
Input
219
Total output
209
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
172
Input
109
Total output
99
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
355
Input
226
Total output
217
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
201
Input
99
Total output
90
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
128
Input
192
Total output
181
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
94
Input
161
Total output
151
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
111
Input
111
Total output
100
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
91
Input
104
Total output
97
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
122
Input
103
Total output
92
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
101
Input
97
Total output
88
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
120
Input
97
Total output
84
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
101
Input
78
Total output
67
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
115
Input
95
Total output
80
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
77
Input
103
Total output
96
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
112
Input
76
Total output
65
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
68
Input
68
Total output
61
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
152
Input
78
Total output
61
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
88
Input
227
Total output
217
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
111
Input
496
Total output
483
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
83
Input
170
Total output
160
Reasoning within output
cherry_pick f004
100%
Passed
Tokens
138
Input
282
Total output
255
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
144
Input
160
Total output
138
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
126
Input
163
Total output
138
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
119
Input
108
Total output
94
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
116
Input
46
Total output
34
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
102
Input
51
Total output
40
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
200
Input
215
Total output
185
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
157
Input
173
Total output
146
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
254
Input
216
Total output
172
Reasoning within output
commit_messages f001
92.7%
Passed
Tokens
101
Input
73
Total output
64
Reasoning within output
commit_messages f002
91.7%
Passed
Tokens
195
Input
175
Total output
161
Reasoning within output
commit_messages f003
94.3%
Passed
Tokens
80
Input
240
Total output
226
Reasoning within output
commit_messages f004
97%
Passed
Tokens
108
Input
69
Total output
60
Reasoning within output
commit_messages f005
90%
Passed
Tokens
96
Input
82
Total output
72
Reasoning within output
commit_messages f006
89.3%
Passed
Tokens
131
Input
290
Total output
278
Reasoning within output
commit_messages f007
87.7%
Passed
Tokens
173
Input
148
Total output
139
Reasoning within output
commit_messages f008
93.3%
Passed
Tokens
68
Input
83
Total output
73
Reasoning within output
commit_messages f009
85%
Passed
Tokens
120
Input
112
Total output
99
Reasoning within output
commit_messages f010
90.3%
Passed
Tokens
256
Input
208
Total output
196
Reasoning within output
commit_messages f011
77.7%
Passed
Tokens
138
Input
59
Total output
50
Reasoning within output
commit_messages f012
91%
Passed
Tokens
121
Input
87
Total output
78
Reasoning within output
commit_squash f001
100%
Passed
Tokens
131
Input
335
Total output
317
Reasoning within output
commit_squash f002
100%
Passed
Tokens
112
Input
124
Total output
110
Reasoning within output
commit_squash f003
100%
Passed
Tokens
121
Input
202
Total output
184
Reasoning within output
commit_squash f004
100%
Passed
Tokens
112
Input
2,369
Total output
2,352
Reasoning within output
commit_squash f005
100%
Passed
Tokens
109
Input
466
Total output
453
Reasoning within output
commit_squash f006
100%
Passed
Tokens
98
Input
168
Total output
151
Reasoning within output
commit_squash f007
100%
Passed
Tokens
94
Input
161
Total output
143
Reasoning within output
commit_squash f008
100%
Passed
Tokens
111
Input
150
Total output
132
Reasoning within output
commit_squash f009
100%
Passed
Tokens
100
Input
182
Total output
165
Reasoning within output
commit_squash f010
100%
Passed
Tokens
117
Input
83
Total output
62
Reasoning within output
commit_squash f011
100%
Passed
Tokens
128
Input
117
Total output
96
Reasoning within output
commit_squash f012
100%
Passed
Tokens
126
Input
209
Total output
183
Reasoning within output
git_bisect f001
100%
Passed
Tokens
172
Input
73
Total output
63
Reasoning within output
git_bisect f002
100%
Passed
Tokens
189
Input
105
Total output
94
Reasoning within output
git_bisect f003
100%
Passed
Tokens
185
Input
60
Total output
50
Reasoning within output
git_bisect f004
100%
Passed
Tokens
193
Input
86
Total output
75
Reasoning within output
git_bisect f005
100%
Passed
Tokens
189
Input
102
Total output
91
Reasoning within output
git_bisect f006
100%
Passed
Tokens
208
Input
71
Total output
61
Reasoning within output
git_bisect f007
100%
Passed
Tokens
185
Input
83
Total output
74
Reasoning within output
git_bisect f008
100%
Passed
Tokens
195
Input
59
Total output
47
Reasoning within output
git_bisect f009
100%
Passed
Tokens
195
Input
87
Total output
74
Reasoning within output
git_bisect f010
100%
Passed
Tokens
197
Input
85
Total output
75
Reasoning within output
git_bisect f011
100%
Passed
Tokens
193
Input
65
Total output
54
Reasoning within output
git_bisect f012
100%
Passed
Tokens
208
Input
73
Total output
63
Reasoning within output
git_clean f001
100%
Passed
Tokens
46
Input
140
Total output
126
Reasoning within output
git_clean f002
100%
Passed
Tokens
57
Input
131
Total output
121
Reasoning within output
git_clean f003
100%
Passed
Tokens
54
Input
98
Total output
88
Reasoning within output
git_clean f004
100%
Passed
Tokens
54
Input
82
Total output
71
Reasoning within output
git_clean f005
100%
Passed
Tokens
46
Input
207
Total output
195
Reasoning within output
git_clean f006
100%
Passed
Tokens
69
Input
205
Total output
192
Reasoning within output
git_clean f007
100%
Passed
Tokens
61
Input
156
Total output
142
Reasoning within output
git_clean f008
100%
Passed
Tokens
68
Input
83
Total output
73
Reasoning within output
git_clean f009
100%
Passed
Tokens
62
Input
192
Total output
178
Reasoning within output
git_clean f010
100%
Passed
Tokens
59
Input
207
Total output
197
Reasoning within output
git_clean f011
100%
Passed
Tokens
58
Input
71
Total output
60
Reasoning within output
git_clean f012
100%
Passed
Tokens
60
Input
189
Total output
176
Reasoning within output
git_grep f001
100%
Passed
Tokens
49
Input
50
Total output
41
Reasoning within output
git_grep f002
100%
Passed
Tokens
60
Input
36
Total output
29
Reasoning within output
git_grep f003
100%
Passed
Tokens
82
Input
33
Total output
26
Reasoning within output
git_grep f004
100%
Passed
Tokens
74
Input
47
Total output
36
Reasoning within output
git_grep f005
100%
Passed
Tokens
109
Input
38
Total output
31
Reasoning within output
git_grep f006
100%
Passed
Tokens
39
Input
219
Total output
212
Reasoning within output
git_grep f007
100%
Passed
Tokens
154
Input
275
Total output
268
Reasoning within output
git_grep f008
100%
Passed
Tokens
56
Input
31
Total output
24
Reasoning within output
git_grep f009
100%
Passed
Tokens
52
Input
49
Total output
40
Reasoning within output
git_grep f010
100%
Passed
Tokens
61
Input
32
Total output
25
Reasoning within output
git_grep f011
100%
Passed
Tokens
106
Input
34
Total output
27
Reasoning within output
git_grep f012
100%
Passed
Tokens
63
Input
57
Total output
43
Reasoning within output
git_log_format f001
100%
Passed
Tokens
692
Input
55
Total output
48
Reasoning within output
git_log_format f002
100%
Passed
Tokens
703
Input
56
Total output
43
Reasoning within output
git_log_format f003
100%
Passed
Tokens
558
Input
66
Total output
51
Reasoning within output
git_log_format f004
100%
Passed
Tokens
678
Input
45
Total output
38
Reasoning within output
git_log_format f005
100%
Passed
Tokens
563
Input
447
Total output
436
Reasoning within output
git_log_format f006
100%
Passed
Tokens
693
Input
61
Total output
54
Reasoning within output
git_log_format f007
100%
Passed
Tokens
726
Input
48
Total output
38
Reasoning within output
git_log_format f008
100%
Passed
Tokens
929
Input
27
Total output
20
Reasoning within output
git_log_format f009
100%
Passed
Tokens
551
Input
45
Total output
38
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,061
Input
61
Total output
54
Reasoning within output
git_log_format f011
100%
Passed
Tokens
349
Input
59
Total output
51
Reasoning within output
git_log_format f012
100%
Passed
Tokens
317
Input
27
Total output
20
Reasoning within output
git_show f001
100%
Passed
Tokens
162
Input
47
Total output
38
Reasoning within output
git_show f002
100%
Passed
Tokens
160
Input
193
Total output
185
Reasoning within output
git_show f003
100%
Passed
Tokens
577
Input
96
Total output
84
Reasoning within output
git_show f004
100%
Passed
Tokens
389
Input
59
Total output
47
Reasoning within output
git_show f005
100%
Passed
Tokens
173
Input
81
Total output
73
Reasoning within output
git_show f006
100%
Passed
Tokens
175
Input
44
Total output
37
Reasoning within output
git_show f007
100%
Passed
Tokens
163
Input
47
Total output
37
Reasoning within output
git_show f008
100%
Passed
Tokens
181
Input
92
Total output
60
Reasoning within output
git_show f009
100%
Passed
Tokens
257
Input
76
Total output
69
Reasoning within output
git_show f010
100%
Passed
Tokens
168
Input
96
Total output
89
Reasoning within output
git_show f011
100%
Passed
Tokens
194
Input
44
Total output
36
Reasoning within output
git_show f012
100%
Passed
Tokens
288
Input
55
Total output
48
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
80
Input
214
Total output
204
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
100
Input
891
Total output
878
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
75
Input
420
Total output
410
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
126
Input
243
Total output
216
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
131
Input
93
Total output
71
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
115
Input
182
Total output
157
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
120
Input
107
Total output
93
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
102
Input
87
Total output
75
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
99
Input
137
Total output
126
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
169
Input
164
Total output
134
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
138
Input
276
Total output
249
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
219
Input
137
Total output
83
Reasoning within output
rebase f001
100%
Passed
Tokens
89
Input
179
Total output
169
Reasoning within output
rebase f002
100%
Passed
Tokens
118
Input
126
Total output
113
Reasoning within output
rebase f003
100%
Passed
Tokens
98
Input
142
Total output
133
Reasoning within output
rebase f004
100%
Passed
Tokens
139
Input
543
Total output
516
Reasoning within output
rebase f005
100%
Passed
Tokens
134
Input
81
Total output
62
Reasoning within output
rebase f006
100%
Passed
Tokens
127
Input
227
Total output
202
Reasoning within output
rebase f007
100%
Passed
Tokens
122
Input
87
Total output
73
Reasoning within output
rebase f008
100%
Passed
Tokens
116
Input
92
Total output
80
Reasoning within output
rebase f009
100%
Passed
Tokens
98
Input
77
Total output
66
Reasoning within output
rebase f010
100%
Passed
Tokens
192
Input
155
Total output
125
Reasoning within output
rebase f011
100%
Passed
Tokens
148
Input
135
Total output
108
Reasoning within output
rebase f012
0%
Failed
Tokens
250
Input
193
Total output
149
Reasoning within output
reflog f001
100%
Passed
Tokens
206
Input
110
Total output
78
Reasoning within output
reflog f002
100%
Passed
Tokens
195
Input
157
Total output
77
Reasoning within output
reflog f003
100%
Passed
Tokens
178
Input
121
Total output
32
Reasoning within output
reflog f004
100%
Passed
Tokens
269
Input
682
Total output
516
Reasoning within output
reflog f005
100%
Passed
Tokens
314
Input
136
Total output
88
Reasoning within output
reflog f006
100%
Passed
Tokens
217
Input
176
Total output
102
Reasoning within output
reflog f007
100%
Passed
Tokens
225
Input
117
Total output
73
Reasoning within output
reflog f008
100%
Passed
Tokens
327
Input
233
Total output
130
Reasoning within output
reflog f009
100%
Passed
Tokens
275
Input
622
Total output
516
Reasoning within output
reflog f010
100%
Passed
Tokens
240
Input
135
Total output
70
Reasoning within output
reflog f011
100%
Passed
Tokens
269
Input
1,110
Total output
984
Reasoning within output
reflog f012
100%
Passed
Tokens
279
Input
566
Total output
442
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
125
Input
56
Total output
29
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
267
Input
96
Total output
60
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
112
Input
78
Total output
57
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
110
Input
110
Total output
87
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
121
Input
72
Total output
45
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
167
Input
38
Total output
19
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
193
Input
49
Total output
28
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
161
Input
97
Total output
78
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
193
Input
114
Total output
51
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
119
Input
65
Total output
46
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
110
Input
168
Total output
144
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
124
Input
86
Total output
43
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
42
Input
73
Total output
58
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
88
Input
532
Total output
516
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
94
Input
4,451
Total output
4,421
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
78
Input
136
Total output
126
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
49
Input
303
Total output
270
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
74
Input
526
Total output
516
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
50
Input
202
Total output
177
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
85
Input
80
Total output
66
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
81
Input
149
Total output
139
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
92
Input
526
Total output
513
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
92
Input
50
Total output
40
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
48
Input
95
Total output
77
Reasoning within output
tag_management f001
100%
Passed
Tokens
54
Input
55
Total output
43
Reasoning within output
tag_management f002
100%
Passed
Tokens
52
Input
98
Total output
74
Reasoning within output
tag_management f003
100%
Passed
Tokens
57
Input
140
Total output
125
Reasoning within output
tag_management f004
100%
Passed
Tokens
62
Input
103
Total output
95
Reasoning within output
tag_management f005
100%
Passed
Tokens
75
Input
113
Total output
99
Reasoning within output
tag_management f006
100%
Passed
Tokens
61
Input
270
Total output
246
Reasoning within output
tag_management f007
100%
Passed
Tokens
62
Input
1,628
Total output
1,607
Reasoning within output
tag_management f008
100%
Passed
Tokens
65
Input
306
Total output
277
Reasoning within output
tag_management f009
100%
Passed
Tokens
69
Input
110
Total output
87
Reasoning within output
tag_management f010
100%
Passed
Tokens
45
Input
195
Total output
182
Reasoning within output
tag_management f011
100%
Passed
Tokens
45
Input
93
Total output
82
Reasoning within output
tag_management f012
100%
Passed
Tokens
75
Input
515
Total output
500
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
124
Input
134
Total output
119
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
128
Input
336
Total output
308
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
177
Input
152
Total output
138
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
187
Input
59
Total output
49
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
113
Input
148
Total output
131
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
117
Input
159
Total output
139
Reasoning within output
worktree_usage f007
0%
Failed
Tokens
120
Input
1,364
Total output
1,333
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
147
Input
691
Total output
516
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
215
Input
216
Total output
206
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
188
Input
188
Total output
167
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
180
Input
156
Total output
142
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
114
Input
160
Total output
141
Reasoning within output