Openai / gpt-oss-120b
low
92.7%
189 / 204 fixtures · 1 run(s)
46,286 input / 20,477 total output / 13,952 reasoning within output tokens $0.00984320
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-6.4%
Text: 92.7% →
JSON: 86.3%
+7
Gained
JSON pass / text fail
−20
Lost
Text pass / JSON fail
169
Unchanged Pass
Both pass
8
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| git_clean | 100% | 83.3% | -16.7% |
| git_grep | 91.7% | 75% | -16.7% |
| merge_conflicts | 75% | 58.3% | -16.7% |
| tag_management | 100% | 83.3% | -16.7% |
| reflog | 91.7% | 83.3% | -8.3% |
| branch_cleanup | 83.3% | 75% | -8.3% |
| cherry_pick | 83.3% | 75% | -8.3% |
| git_bisect | 100% | 91.7% | -8.3% |
| rebase | 83.3% | 75% | -8.3% |
| stash_recovery | 91.7% | 100% | + 8.3% |
| submodule_usage | 100% | 91.7% | -8.3% |
| blame_forensics | 91.7% | 91.7% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| commit_squash | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 100% | 100% | + 0% |
| worktree_usage | 83.3% | 83.3% | + 0% |
Changed Fixtures (27)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
265
Input
74
Total output
70
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
248
Input
86
Total output
64
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
286
Input
50
Total output
37
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
226
Input
51
Total output
44
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
272
Input
73
Total output
68
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
258
Input
149
Total output
135
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
251
Input
58
Total output
0
Reasoning within output
blame_forensics f008
0%
Failed
Tokens
265
Input
51
Total output
46
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
230
Input
198
Total output
184
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
410
Input
60
Total output
58
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
265
Input
94
Total output
91
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
195
Input
91
Total output
0
Reasoning within output
branch_cleanup f001
0%
Failed
Tokens
161
Input
85
Total output
73
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
171
Input
164
Total output
152
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
150
Input
53
Total output
47
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
182
Input
186
Total output
201
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
161
Input
82
Total output
76
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
174
Input
69
Total output
55
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
157
Input
60
Total output
52
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
181
Input
95
Total output
75
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
125
Input
77
Total output
78
Reasoning within output
branch_cleanup f010
0%
Failed
Tokens
177
Input
60
Total output
41
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
127
Input
96
Total output
86
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
210
Input
54
Total output
32
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
146
Input
62
Total output
61
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
160
Input
72
Total output
45
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
147
Input
172
Total output
188
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
199
Input
86
Total output
55
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
201
Input
48
Total output
28
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
188
Input
85
Total output
44
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
178
Input
42
Total output
27
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
177
Input
46
Total output
34
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
150
Input
45
Total output
32
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
265
Input
370
Total output
384
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
228
Input
76
Total output
0
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
311
Input
229
Total output
187
Reasoning within output
commit_messages f001
89%
Passed
Tokens
160
Input
43
Total output
27
Reasoning within output
commit_messages f002
88.3%
Passed
Tokens
256
Input
64
Total output
43
Reasoning within output
commit_messages f003
92.7%
Passed
Tokens
128
Input
46
Total output
28
Reasoning within output
commit_messages f004
91.7%
Passed
Tokens
167
Input
39
Total output
26
Reasoning within output
commit_messages f005
91.7%
Passed
Tokens
168
Input
30
Total output
0
Reasoning within output
commit_messages f006
93.3%
Passed
Tokens
190
Input
58
Total output
50
Reasoning within output
commit_messages f007
90%
Passed
Tokens
236
Input
142
Total output
115
Reasoning within output
commit_messages f008
91%
Passed
Tokens
129
Input
94
Total output
82
Reasoning within output
commit_messages f009
90%
Passed
Tokens
179
Input
62
Total output
44
Reasoning within output
commit_messages f010
94.3%
Passed
Tokens
321
Input
155
Total output
137
Reasoning within output
commit_messages f011
77.7%
Passed
Tokens
199
Input
251
Total output
238
Reasoning within output
commit_messages f012
86.7%
Passed
Tokens
182
Input
34
Total output
23
Reasoning within output
commit_squash f001
100%
Passed
Tokens
191
Input
142
Total output
126
Reasoning within output
commit_squash f002
100%
Passed
Tokens
171
Input
49
Total output
31
Reasoning within output
commit_squash f003
100%
Passed
Tokens
186
Input
99
Total output
79
Reasoning within output
commit_squash f004
100%
Passed
Tokens
159
Input
115
Total output
96
Reasoning within output
commit_squash f005
100%
Passed
Tokens
172
Input
192
Total output
206
Reasoning within output
commit_squash f006
100%
Passed
Tokens
143
Input
86
Total output
68
Reasoning within output
commit_squash f007
100%
Passed
Tokens
155
Input
83
Total output
67
Reasoning within output
commit_squash f008
100%
Passed
Tokens
171
Input
85
Total output
64
Reasoning within output
commit_squash f009
100%
Passed
Tokens
167
Input
237
Total output
207
Reasoning within output
commit_squash f010
100%
Passed
Tokens
162
Input
62
Total output
34
Reasoning within output
commit_squash f011
100%
Passed
Tokens
183
Input
53
Total output
24
Reasoning within output
commit_squash f012
100%
Passed
Tokens
187
Input
99
Total output
69
Reasoning within output
git_bisect f001
100%
Passed
Tokens
235
Input
37
Total output
18
Reasoning within output
git_bisect f002
100%
Passed
Tokens
243
Input
47
Total output
31
Reasoning within output
git_bisect f003
100%
Passed
Tokens
252
Input
103
Total output
100
Reasoning within output
git_bisect f004
100%
Passed
Tokens
245
Input
65
Total output
46
Reasoning within output
git_bisect f005
100%
Passed
Tokens
252
Input
171
Total output
137
Reasoning within output
git_bisect f006
100%
Passed
Tokens
269
Input
77
Total output
60
Reasoning within output
git_bisect f007
100%
Passed
Tokens
246
Input
55
Total output
38
Reasoning within output
git_bisect f008
100%
Passed
Tokens
250
Input
63
Total output
44
Reasoning within output
git_bisect f009
100%
Passed
Tokens
244
Input
53
Total output
36
Reasoning within output
git_bisect f010
100%
Passed
Tokens
241
Input
49
Total output
26
Reasoning within output
git_bisect f011
100%
Passed
Tokens
256
Input
69
Total output
39
Reasoning within output
git_bisect f012
100%
Passed
Tokens
277
Input
172
Total output
155
Reasoning within output
git_clean f001
100%
Passed
Tokens
94
Input
38
Total output
23
Reasoning within output
git_clean f002
100%
Passed
Tokens
105
Input
75
Total output
51
Reasoning within output
git_clean f003
100%
Passed
Tokens
115
Input
32
Total output
20
Reasoning within output
git_clean f004
100%
Passed
Tokens
115
Input
46
Total output
32
Reasoning within output
git_clean f005
100%
Passed
Tokens
94
Input
134
Total output
118
Reasoning within output
git_clean f006
100%
Passed
Tokens
130
Input
48
Total output
34
Reasoning within output
git_clean f007
100%
Passed
Tokens
124
Input
218
Total output
215
Reasoning within output
git_clean f008
100%
Passed
Tokens
129
Input
70
Total output
55
Reasoning within output
git_clean f009
100%
Passed
Tokens
123
Input
69
Total output
59
Reasoning within output
git_clean f010
100%
Passed
Tokens
118
Input
52
Total output
39
Reasoning within output
git_clean f011
100%
Passed
Tokens
130
Input
41
Total output
0
Reasoning within output
git_clean f012
100%
Passed
Tokens
119
Input
102
Total output
85
Reasoning within output
git_grep f001
100%
Passed
Tokens
97
Input
25
Total output
13
Reasoning within output
git_grep f002
100%
Passed
Tokens
123
Input
38
Total output
25
Reasoning within output
git_grep f003
100%
Passed
Tokens
147
Input
25
Total output
15
Reasoning within output
git_grep f004
100%
Passed
Tokens
137
Input
41
Total output
20
Reasoning within output
git_grep f005
100%
Passed
Tokens
170
Input
34
Total output
25
Reasoning within output
git_grep f006
100%
Passed
Tokens
100
Input
86
Total output
85
Reasoning within output
git_grep f007
100%
Passed
Tokens
213
Input
140
Total output
121
Reasoning within output
git_grep f008
100%
Passed
Tokens
119
Input
62
Total output
62
Reasoning within output
git_grep f009
100%
Passed
Tokens
113
Input
58
Total output
45
Reasoning within output
git_grep f010
0%
Failed
Tokens
124
Input
76
Total output
66
Reasoning within output
git_grep f011
100%
Passed
Tokens
178
Input
82
Total output
0
Reasoning within output
git_grep f012
100%
Passed
Tokens
124
Input
39
Total output
22
Reasoning within output
git_log_format f001
100%
Passed
Tokens
761
Input
38
Total output
37
Reasoning within output
git_log_format f002
100%
Passed
Tokens
738
Input
45
Total output
36
Reasoning within output
git_log_format f003
100%
Passed
Tokens
638
Input
45
Total output
27
Reasoning within output
git_log_format f004
100%
Passed
Tokens
759
Input
66
Total output
42
Reasoning within output
git_log_format f005
100%
Passed
Tokens
622
Input
110
Total output
111
Reasoning within output
git_log_format f006
100%
Passed
Tokens
754
Input
36
Total output
19
Reasoning within output
git_log_format f007
100%
Passed
Tokens
778
Input
32
Total output
20
Reasoning within output
git_log_format f008
100%
Passed
Tokens
989
Input
29
Total output
17
Reasoning within output
git_log_format f009
100%
Passed
Tokens
621
Input
32
Total output
21
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,085
Input
27
Total output
17
Reasoning within output
git_log_format f011
100%
Passed
Tokens
402
Input
54
Total output
38
Reasoning within output
git_log_format f012
100%
Passed
Tokens
390
Input
28
Total output
0
Reasoning within output
git_show f001
100%
Passed
Tokens
226
Input
22
Total output
10
Reasoning within output
git_show f002
100%
Passed
Tokens
229
Input
172
Total output
178
Reasoning within output
git_show f003
100%
Passed
Tokens
622
Input
87
Total output
81
Reasoning within output
git_show f004
100%
Passed
Tokens
448
Input
26
Total output
11
Reasoning within output
git_show f005
100%
Passed
Tokens
231
Input
49
Total output
40
Reasoning within output
git_show f006
100%
Passed
Tokens
230
Input
47
Total output
36
Reasoning within output
git_show f007
100%
Passed
Tokens
226
Input
90
Total output
81
Reasoning within output
git_show f008
100%
Passed
Tokens
224
Input
61
Total output
18
Reasoning within output
git_show f009
100%
Passed
Tokens
310
Input
28
Total output
19
Reasoning within output
git_show f010
100%
Passed
Tokens
217
Input
26
Total output
14
Reasoning within output
git_show f011
100%
Passed
Tokens
257
Input
19
Total output
8
Reasoning within output
git_show f012
100%
Passed
Tokens
348
Input
97
Total output
96
Reasoning within output
merge_conflicts f001
0%
Failed
Tokens
141
Input
314
Total output
310
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
159
Input
82
Total output
62
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
123
Input
68
Total output
61
Reasoning within output
merge_conflicts f004
0%
Failed
Tokens
174
Input
89
Total output
67
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
192
Input
62
Total output
43
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
174
Input
136
Total output
94
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
184
Input
43
Total output
28
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
161
Input
47
Total output
35
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
147
Input
58
Total output
49
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
232
Input
386
Total output
405
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
199
Input
68
Total output
37
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
282
Input
267
Total output
222
Reasoning within output
rebase f001
0%
Failed
Tokens
137
Input
95
Total output
86
Reasoning within output
rebase f002
100%
Passed
Tokens
178
Input
82
Total output
75
Reasoning within output
rebase f003
100%
Passed
Tokens
170
Input
30
Total output
0
Reasoning within output
rebase f004
100%
Passed
Tokens
183
Input
91
Total output
68
Reasoning within output
rebase f005
100%
Passed
Tokens
198
Input
120
Total output
130
Reasoning within output
rebase f006
100%
Passed
Tokens
187
Input
77
Total output
39
Reasoning within output
rebase f007
100%
Passed
Tokens
182
Input
42
Total output
28
Reasoning within output
rebase f008
100%
Passed
Tokens
174
Input
89
Total output
73
Reasoning within output
rebase f009
100%
Passed
Tokens
158
Input
36
Total output
24
Reasoning within output
rebase f010
100%
Passed
Tokens
255
Input
192
Total output
156
Reasoning within output
rebase f011
100%
Passed
Tokens
208
Input
71
Total output
42
Reasoning within output
rebase f012
0%
Failed
Tokens
313
Input
527
Total output
484
Reasoning within output
reflog f001
100%
Passed
Tokens
257
Input
93
Total output
39
Reasoning within output
reflog f002
100%
Passed
Tokens
259
Input
250
Total output
74
Reasoning within output
reflog f003
100%
Passed
Tokens
248
Input
109
Total output
0
Reasoning within output
reflog f004
100%
Passed
Tokens
350
Input
670
Total output
198
Reasoning within output
reflog f005
100%
Passed
Tokens
388
Input
574
Total output
427
Reasoning within output
reflog f006
100%
Passed
Tokens
273
Input
137
Total output
28
Reasoning within output
reflog f007
100%
Passed
Tokens
299
Input
467
Total output
197
Reasoning within output
reflog f008
100%
Passed
Tokens
350
Input
160
Total output
33
Reasoning within output
reflog f009
100%
Passed
Tokens
330
Input
370
Total output
55
Reasoning within output
reflog f010
0%
Failed
Tokens
285
Input
58
Total output
28
Reasoning within output
reflog f011
100%
Passed
Tokens
344
Input
392
Total output
0
Reasoning within output
reflog f012
100%
Passed
Tokens
333
Input
675
Total output
8
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
186
Input
95
Total output
60
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
315
Input
61
Total output
21
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
171
Input
38
Total output
13
Reasoning within output
stash_recovery f004
0%
Failed
Tokens
171
Input
50
Total output
23
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
167
Input
65
Total output
25
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
232
Input
53
Total output
14
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
256
Input
57
Total output
24
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
220
Input
56
Total output
21
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
252
Input
47
Total output
17
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
182
Input
94
Total output
72
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
169
Input
52
Total output
22
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
185
Input
48
Total output
22
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
107
Input
49
Total output
29
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
153
Input
277
Total output
237
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
147
Input
140
Total output
101
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
151
Input
58
Total output
0
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
110
Input
195
Total output
163
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
126
Input
95
Total output
84
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
111
Input
33
Total output
5
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
147
Input
120
Total output
109
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
140
Input
97
Total output
78
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
148
Input
44
Total output
34
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
140
Input
29
Total output
15
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
109
Input
66
Total output
54
Reasoning within output
tag_management f001
100%
Passed
Tokens
116
Input
45
Total output
31
Reasoning within output
tag_management f002
100%
Passed
Tokens
103
Input
59
Total output
29
Reasoning within output
tag_management f003
100%
Passed
Tokens
120
Input
45
Total output
21
Reasoning within output
tag_management f004
100%
Passed
Tokens
115
Input
32
Total output
22
Reasoning within output
tag_management f005
100%
Passed
Tokens
136
Input
87
Total output
76
Reasoning within output
tag_management f006
100%
Passed
Tokens
122
Input
73
Total output
31
Reasoning within output
tag_management f007
100%
Passed
Tokens
121
Input
287
Total output
237
Reasoning within output
tag_management f008
100%
Passed
Tokens
129
Input
132
Total output
94
Reasoning within output
tag_management f009
100%
Passed
Tokens
131
Input
138
Total output
111
Reasoning within output
tag_management f010
100%
Passed
Tokens
94
Input
28
Total output
9
Reasoning within output
tag_management f011
100%
Passed
Tokens
111
Input
90
Total output
85
Reasoning within output
tag_management f012
100%
Passed
Tokens
141
Input
178
Total output
168
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
185
Input
89
Total output
80
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
187
Input
64
Total output
39
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
244
Input
30
Total output
12
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
248
Input
35
Total output
0
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
172
Input
61
Total output
42
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
175
Input
46
Total output
21
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
174
Input
64
Total output
39
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
198
Input
88
Total output
43
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
261
Input
38
Total output
27
Reasoning within output
worktree_usage f010
0%
Failed
Tokens
252
Input
63
Total output
34
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
238
Input
50
Total output
33
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
176
Input
82
Total output
49
Reasoning within output