Openai / gpt-oss-120b
high
96.6%
197 / 204 fixtures · 1 run(s)
46,271 input / 92,554 total output / 88,177 reasoning within output tokens $0.03010587
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-7.4%
Text: 96.6% →
JSON: 89.2%
+2
Gained
JSON pass / text fail
−17
Lost
Text pass / JSON fail
180
Unchanged Pass
Both pass
5
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| reflog | 100% | 75% | -25% |
| branch_cleanup | 100% | 83.3% | -16.7% |
| commit_squash | 100% | 83.3% | -16.7% |
| merge_conflicts | 91.7% | 75% | -16.7% |
| worktree_usage | 91.7% | 83.3% | -8.3% |
| blame_forensics | 100% | 91.7% | -8.3% |
| cherry_pick | 83.3% | 75% | -8.3% |
| git_clean | 100% | 91.7% | -8.3% |
| submodule_usage | 100% | 91.7% | -8.3% |
| tag_management | 100% | 91.7% | -8.3% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 91.7% | 91.7% | + 0% |
| git_grep | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 100% | 100% | + 0% |
| rebase | 83.3% | 83.3% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
Changed Fixtures (19)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
276
Input
386
Total output
445
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
254
Input
506
Total output
553
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
271
Input
353
Total output
303
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
225
Input
110
Total output
95
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
282
Input
315
Total output
288
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
251
Input
438
Total output
440
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
244
Input
286
Total output
319
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
271
Input
427
Total output
493
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
229
Input
271
Total output
290
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
415
Input
748
Total output
737
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
265
Input
323
Total output
312
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
175
Input
650
Total output
730
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
149
Input
367
Total output
400
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
157
Input
485
Total output
496
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
150
Input
339
Total output
380
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
181
Input
345
Total output
365
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
159
Input
212
Total output
228
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
177
Input
320
Total output
335
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
157
Input
278
Total output
315
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
175
Input
220
Total output
201
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
151
Input
328
Total output
0
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
160
Input
292
Total output
260
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
126
Input
179
Total output
197
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
208
Input
265
Total output
246
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
153
Input
462
Total output
542
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
173
Input
173
Total output
157
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
145
Input
151
Total output
147
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
201
Input
1,617
Total output
1,849
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
205
Input
219
Total output
246
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
174
Input
667
Total output
666
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
178
Input
326
Total output
368
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
179
Input
311
Total output
356
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
166
Input
206
Total output
225
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
265
Input
1,027
Total output
1,181
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
219
Input
205
Total output
184
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
317
Input
815
Total output
872
Reasoning within output
commit_messages f001
87.7%
Passed
Tokens
162
Input
118
Total output
108
Reasoning within output
commit_messages f002
85%
Passed
Tokens
256
Input
585
Total output
570
Reasoning within output
commit_messages f003
93.7%
Passed
Tokens
141
Input
148
Total output
133
Reasoning within output
commit_messages f004
93.7%
Passed
Tokens
167
Input
149
Total output
153
Reasoning within output
commit_messages f005
88.7%
Passed
Tokens
155
Input
125
Total output
130
Reasoning within output
commit_messages f006
91.7%
Passed
Tokens
190
Input
454
Total output
413
Reasoning within output
commit_messages f007
88.3%
Passed
Tokens
234
Input
489
Total output
329
Reasoning within output
commit_messages f008
93.3%
Passed
Tokens
116
Input
230
Total output
243
Reasoning within output
commit_messages f009
87.7%
Passed
Tokens
181
Input
274
Total output
267
Reasoning within output
commit_messages f010
83.3%
Passed
Tokens
319
Input
493
Total output
398
Reasoning within output
commit_messages f011
66.3%
Passed
Tokens
186
Input
1,817
Total output
1,085
Reasoning within output
commit_messages f012
89.3%
Passed
Tokens
186
Input
445
Total output
431
Reasoning within output
commit_squash f001
100%
Passed
Tokens
192
Input
418
Total output
398
Reasoning within output
commit_squash f002
100%
Passed
Tokens
175
Input
183
Total output
175
Reasoning within output
commit_squash f003
100%
Passed
Tokens
185
Input
477
Total output
500
Reasoning within output
commit_squash f004
100%
Passed
Tokens
172
Input
470
Total output
490
Reasoning within output
commit_squash f005
100%
Passed
Tokens
155
Input
447
Total output
508
Reasoning within output
commit_squash f006
100%
Passed
Tokens
154
Input
310
Total output
335
Reasoning within output
commit_squash f007
100%
Passed
Tokens
145
Input
273
Total output
264
Reasoning within output
commit_squash f008
100%
Passed
Tokens
170
Input
273
Total output
253
Reasoning within output
commit_squash f009
100%
Passed
Tokens
148
Input
353
Total output
348
Reasoning within output
commit_squash f010
100%
Passed
Tokens
176
Input
261
Total output
237
Reasoning within output
commit_squash f011
100%
Passed
Tokens
187
Input
246
Total output
225
Reasoning within output
commit_squash f012
100%
Passed
Tokens
185
Input
525
Total output
506
Reasoning within output
git_bisect f001
100%
Passed
Tokens
231
Input
241
Total output
228
Reasoning within output
git_bisect f002
100%
Passed
Tokens
252
Input
175
Total output
175
Reasoning within output
git_bisect f003
100%
Passed
Tokens
235
Input
331
Total output
350
Reasoning within output
git_bisect f004
0%
Failed
Tokens
235
Input
260
Total output
285
Reasoning within output
git_bisect f005
100%
Passed
Tokens
254
Input
472
Total output
453
Reasoning within output
git_bisect f006
100%
Passed
Tokens
273
Input
257
Total output
237
Reasoning within output
git_bisect f007
100%
Passed
Tokens
254
Input
244
Total output
233
Reasoning within output
git_bisect f008
100%
Passed
Tokens
248
Input
489
Total output
471
Reasoning within output
git_bisect f009
100%
Passed
Tokens
250
Input
110
Total output
92
Reasoning within output
git_bisect f010
100%
Passed
Tokens
256
Input
487
Total output
468
Reasoning within output
git_bisect f011
100%
Passed
Tokens
252
Input
549
Total output
504
Reasoning within output
git_bisect f012
100%
Passed
Tokens
275
Input
988
Total output
982
Reasoning within output
git_clean f001
100%
Passed
Tokens
105
Input
324
Total output
326
Reasoning within output
git_clean f002
100%
Passed
Tokens
118
Input
372
Total output
408
Reasoning within output
git_clean f003
100%
Passed
Tokens
102
Input
275
Total output
311
Reasoning within output
git_clean f004
100%
Passed
Tokens
115
Input
120
Total output
115
Reasoning within output
git_clean f005
100%
Passed
Tokens
105
Input
765
Total output
783
Reasoning within output
git_clean f006
100%
Passed
Tokens
117
Input
676
Total output
722
Reasoning within output
git_clean f007
100%
Passed
Tokens
109
Input
483
Total output
518
Reasoning within output
git_clean f008
100%
Passed
Tokens
127
Input
549
Total output
559
Reasoning within output
git_clean f009
100%
Passed
Tokens
121
Input
2,001
Total output
2,244
Reasoning within output
git_clean f010
100%
Passed
Tokens
107
Input
450
Total output
455
Reasoning within output
git_clean f011
100%
Passed
Tokens
119
Input
329
Total output
365
Reasoning within output
git_clean f012
100%
Passed
Tokens
121
Input
147
Total output
130
Reasoning within output
git_grep f001
100%
Passed
Tokens
108
Input
197
Total output
218
Reasoning within output
git_grep f002
100%
Passed
Tokens
123
Input
116
Total output
106
Reasoning within output
git_grep f003
100%
Passed
Tokens
130
Input
142
Total output
149
Reasoning within output
git_grep f004
100%
Passed
Tokens
135
Input
121
Total output
102
Reasoning within output
git_grep f005
100%
Passed
Tokens
157
Input
182
Total output
180
Reasoning within output
git_grep f006
100%
Passed
Tokens
100
Input
654
Total output
734
Reasoning within output
git_grep f007
100%
Passed
Tokens
217
Input
537
Total output
545
Reasoning within output
git_grep f008
100%
Passed
Tokens
117
Input
210
Total output
199
Reasoning within output
git_grep f009
100%
Passed
Tokens
115
Input
164
Total output
156
Reasoning within output
git_grep f010
100%
Passed
Tokens
122
Input
76
Total output
64
Reasoning within output
git_grep f011
100%
Passed
Tokens
167
Input
271
Total output
261
Reasoning within output
git_grep f012
100%
Passed
Tokens
128
Input
144
Total output
127
Reasoning within output
git_log_format f001
100%
Passed
Tokens
730
Input
177
Total output
169
Reasoning within output
git_log_format f002
100%
Passed
Tokens
758
Input
210
Total output
248
Reasoning within output
git_log_format f003
100%
Passed
Tokens
613
Input
225
Total output
232
Reasoning within output
git_log_format f004
100%
Passed
Tokens
750
Input
213
Total output
206
Reasoning within output
git_log_format f005
100%
Passed
Tokens
622
Input
347
Total output
348
Reasoning within output
git_log_format f006
100%
Passed
Tokens
754
Input
130
Total output
119
Reasoning within output
git_log_format f007
100%
Passed
Tokens
763
Input
62
Total output
48
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,014
Input
137
Total output
119
Reasoning within output
git_log_format f009
100%
Passed
Tokens
636
Input
214
Total output
216
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,138
Input
255
Total output
206
Reasoning within output
git_log_format f011
100%
Passed
Tokens
411
Input
212
Total output
220
Reasoning within output
git_log_format f012
100%
Passed
Tokens
364
Input
115
Total output
102
Reasoning within output
git_show f001
100%
Passed
Tokens
225
Input
96
Total output
83
Reasoning within output
git_show f002
100%
Passed
Tokens
226
Input
2,744
Total output
2,732
Reasoning within output
git_show f003
100%
Passed
Tokens
612
Input
302
Total output
286
Reasoning within output
git_show f004
100%
Passed
Tokens
448
Input
123
Total output
106
Reasoning within output
git_show f005
100%
Passed
Tokens
230
Input
333
Total output
361
Reasoning within output
git_show f006
100%
Passed
Tokens
240
Input
231
Total output
208
Reasoning within output
git_show f007
100%
Passed
Tokens
235
Input
203
Total output
0
Reasoning within output
git_show f008
100%
Passed
Tokens
225
Input
174
Total output
115
Reasoning within output
git_show f009
100%
Passed
Tokens
322
Input
247
Total output
248
Reasoning within output
git_show f010
100%
Passed
Tokens
232
Input
148
Total output
143
Reasoning within output
git_show f011
100%
Passed
Tokens
255
Input
169
Total output
148
Reasoning within output
git_show f012
100%
Passed
Tokens
346
Input
129
Total output
118
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
141
Input
335
Total output
371
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
161
Input
155
Total output
148
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
136
Input
1,649
Total output
2,011
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
185
Input
1,424
Total output
1,576
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
190
Input
260
Total output
291
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
176
Input
733
Total output
677
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
180
Input
409
Total output
460
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
165
Input
179
Total output
201
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
160
Input
159
Total output
145
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
230
Input
660
Total output
730
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
186
Input
566
Total output
567
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
284
Input
543
Total output
496
Reasoning within output
rebase f001
100%
Passed
Tokens
151
Input
173
Total output
169
Reasoning within output
rebase f002
100%
Passed
Tokens
178
Input
118
Total output
90
Reasoning within output
rebase f003
100%
Passed
Tokens
158
Input
127
Total output
131
Reasoning within output
rebase f004
0%
Failed
Tokens
195
Input
3,175
Total output
3,727
Reasoning within output
rebase f005
100%
Passed
Tokens
193
Input
229
Total output
268
Reasoning within output
rebase f006
100%
Passed
Tokens
185
Input
582
Total output
573
Reasoning within output
rebase f007
100%
Passed
Tokens
181
Input
244
Total output
255
Reasoning within output
rebase f008
100%
Passed
Tokens
175
Input
74
Total output
68
Reasoning within output
rebase f009
100%
Passed
Tokens
154
Input
216
Total output
225
Reasoning within output
rebase f010
100%
Passed
Tokens
255
Input
1,468
Total output
1,693
Reasoning within output
rebase f011
100%
Passed
Tokens
211
Input
501
Total output
484
Reasoning within output
rebase f012
0%
Failed
Tokens
307
Input
469
Total output
417
Reasoning within output
reflog f001
100%
Passed
Tokens
243
Input
518
Total output
435
Reasoning within output
reflog f002
100%
Passed
Tokens
259
Input
694
Total output
472
Reasoning within output
reflog f003
100%
Passed
Tokens
238
Input
850
Total output
406
Reasoning within output
reflog f004
100%
Passed
Tokens
350
Input
1,354
Total output
919
Reasoning within output
reflog f005
100%
Passed
Tokens
390
Input
769
Total output
638
Reasoning within output
reflog f006
100%
Passed
Tokens
268
Input
535
Total output
309
Reasoning within output
reflog f007
100%
Passed
Tokens
298
Input
849
Total output
512
Reasoning within output
reflog f008
100%
Passed
Tokens
372
Input
313
Total output
176
Reasoning within output
reflog f009
100%
Passed
Tokens
342
Input
1,527
Total output
1,076
Reasoning within output
reflog f010
100%
Passed
Tokens
292
Input
1,048
Total output
749
Reasoning within output
reflog f011
100%
Passed
Tokens
355
Input
1,364
Total output
0
Reasoning within output
reflog f012
100%
Passed
Tokens
339
Input
3,325
Total output
2,437
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
185
Input
175
Total output
155
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
330
Input
299
Total output
252
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
173
Input
185
Total output
159
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
174
Input
225
Total output
201
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
170
Input
362
Total output
333
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
226
Input
195
Total output
197
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
241
Input
419
Total output
384
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
220
Input
393
Total output
415
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
252
Input
226
Total output
193
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
182
Input
229
Total output
212
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
170
Input
120
Total output
98
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
183
Input
188
Total output
171
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
105
Input
199
Total output
190
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
139
Input
826
Total output
882
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
161
Input
971
Total output
929
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
137
Input
363
Total output
413
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
97
Input
1,166
Total output
1,230
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
124
Input
525
Total output
575
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
109
Input
657
Total output
705
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
148
Input
176
Total output
168
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
140
Input
281
Total output
290
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
140
Input
819
Total output
916
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
140
Input
124
Total output
120
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
109
Input
214
Total output
184
Reasoning within output
tag_management f001
100%
Passed
Tokens
118
Input
162
Total output
154
Reasoning within output
tag_management f002
100%
Passed
Tokens
117
Input
375
Total output
340
Reasoning within output
tag_management f003
100%
Passed
Tokens
120
Input
545
Total output
581
Reasoning within output
tag_management f004
100%
Passed
Tokens
127
Input
194
Total output
190
Reasoning within output
tag_management f005
100%
Passed
Tokens
135
Input
358
Total output
339
Reasoning within output
tag_management f006
100%
Passed
Tokens
120
Input
564
Total output
503
Reasoning within output
tag_management f007
100%
Passed
Tokens
122
Input
214
Total output
178
Reasoning within output
tag_management f008
100%
Passed
Tokens
125
Input
904
Total output
873
Reasoning within output
tag_management f009
100%
Passed
Tokens
133
Input
120
Total output
104
Reasoning within output
tag_management f010
100%
Passed
Tokens
97
Input
422
Total output
357
Reasoning within output
tag_management f011
100%
Passed
Tokens
108
Input
121
Total output
106
Reasoning within output
tag_management f012
100%
Passed
Tokens
144
Input
355
Total output
336
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
183
Input
349
Total output
370
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
187
Input
626
Total output
630
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
227
Input
190
Total output
182
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
240
Input
123
Total output
128
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
167
Input
906
Total output
929
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
180
Input
81
Total output
67
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
184
Input
962
Total output
1,007
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
200
Input
1,523
Total output
1,565
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
280
Input
224
Total output
257
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
236
Input
627
Total output
609
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
239
Input
100
Total output
92
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
175
Input
289
Total output
250
Reasoning within output