Openai / gpt-oss-120b
xhigh
94.6%
193 / 204 fixtures · 1 run(s)
46,146 input / 100,957 total output / 93,793 reasoning within output tokens $0.03184461
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-4.4%
Text: 94.6% →
JSON: 90.2%
+4
Gained
JSON pass / text fail
−13
Lost
Text pass / JSON fail
180
Unchanged Pass
Both pass
7
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| reflog | 100% | 75% | -25% |
| commit_messages | 100% | 83.3% | -16.7% |
| git_grep | 100% | 83.3% | -16.7% |
| rebase | 75% | 91.7% | + 16.7% |
| tag_management | 100% | 83.3% | -16.7% |
| commit_squash | 91.7% | 83.3% | -8.3% |
| cherry_pick | 83.3% | 75% | -8.3% |
| blame_forensics | 100% | 100% | + 0% |
| branch_cleanup | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_clean | 91.7% | 91.7% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 100% | 100% | + 0% |
| merge_conflicts | 83.3% | 83.3% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 100% | 100% | + 0% |
| worktree_usage | 83.3% | 83.3% | + 0% |
Changed Fixtures (17)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
275
Input
996
Total output
1,196
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
259
Input
304
Total output
308
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
284
Input
94
Total output
76
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
228
Input
245
Total output
271
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
271
Input
708
Total output
761
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
252
Input
909
Total output
962
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
244
Input
248
Total output
222
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
279
Input
400
Total output
0
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
236
Input
270
Total output
284
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
428
Input
445
Total output
432
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
262
Input
303
Total output
305
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
188
Input
305
Total output
290
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
144
Input
277
Total output
274
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
176
Input
311
Total output
324
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
150
Input
85
Total output
84
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
182
Input
450
Total output
506
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
161
Input
130
Total output
127
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
175
Input
246
Total output
256
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
160
Input
196
Total output
209
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
177
Input
223
Total output
195
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
124
Input
244
Total output
280
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
177
Input
127
Total output
122
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
125
Input
166
Total output
188
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
207
Input
268
Total output
248
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
153
Input
559
Total output
546
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
173
Input
1,684
Total output
1,780
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
147
Input
377
Total output
433
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
198
Input
1,050
Total output
1,226
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
201
Input
243
Total output
265
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
186
Input
729
Total output
742
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
183
Input
449
Total output
512
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
179
Input
136
Total output
130
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
164
Input
180
Total output
166
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
261
Input
731
Total output
844
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
219
Input
433
Total output
377
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
315
Input
633
Total output
634
Reasoning within output
commit_messages f001
90%
Passed
Tokens
162
Input
166
Total output
161
Reasoning within output
commit_messages f002
82.3%
Passed
Tokens
256
Input
283
Total output
275
Reasoning within output
commit_messages f003
93.3%
Passed
Tokens
128
Input
189
Total output
189
Reasoning within output
commit_messages f004
94%
Passed
Tokens
167
Input
132
Total output
145
Reasoning within output
commit_messages f005
91.7%
Passed
Tokens
159
Input
400
Total output
309
Reasoning within output
commit_messages f006
91%
Passed
Tokens
192
Input
496
Total output
486
Reasoning within output
commit_messages f007
88%
Passed
Tokens
232
Input
475
Total output
325
Reasoning within output
commit_messages f008
91.7%
Passed
Tokens
131
Input
315
Total output
278
Reasoning within output
commit_messages f009
85.7%
Passed
Tokens
181
Input
687
Total output
670
Reasoning within output
commit_messages f010
90%
Passed
Tokens
315
Input
548
Total output
455
Reasoning within output
commit_messages f011
51.7%
Passed
Tokens
199
Input
1,210
Total output
939
Reasoning within output
commit_messages f012
89.3%
Passed
Tokens
180
Input
427
Total output
292
Reasoning within output
commit_squash f001
100%
Passed
Tokens
176
Input
467
Total output
503
Reasoning within output
commit_squash f002
100%
Passed
Tokens
173
Input
242
Total output
226
Reasoning within output
commit_squash f003
50%
Failed
Tokens
182
Input
2,784
Total output
2,981
Reasoning within output
commit_squash f004
100%
Passed
Tokens
171
Input
769
Total output
819
Reasoning within output
commit_squash f005
100%
Passed
Tokens
171
Input
219
Total output
203
Reasoning within output
commit_squash f006
100%
Passed
Tokens
141
Input
213
Total output
230
Reasoning within output
commit_squash f007
100%
Passed
Tokens
154
Input
703
Total output
720
Reasoning within output
commit_squash f008
100%
Passed
Tokens
158
Input
776
Total output
815
Reasoning within output
commit_squash f009
100%
Passed
Tokens
173
Input
299
Total output
0
Reasoning within output
commit_squash f010
100%
Passed
Tokens
182
Input
84
Total output
59
Reasoning within output
commit_squash f011
100%
Passed
Tokens
185
Input
354
Total output
343
Reasoning within output
commit_squash f012
100%
Passed
Tokens
180
Input
557
Total output
536
Reasoning within output
git_bisect f001
100%
Passed
Tokens
229
Input
193
Total output
179
Reasoning within output
git_bisect f002
100%
Passed
Tokens
256
Input
232
Total output
222
Reasoning within output
git_bisect f003
100%
Passed
Tokens
237
Input
401
Total output
373
Reasoning within output
git_bisect f004
100%
Passed
Tokens
250
Input
467
Total output
447
Reasoning within output
git_bisect f005
100%
Passed
Tokens
244
Input
301
Total output
295
Reasoning within output
git_bisect f006
100%
Passed
Tokens
271
Input
266
Total output
247
Reasoning within output
git_bisect f007
100%
Passed
Tokens
250
Input
270
Total output
254
Reasoning within output
git_bisect f008
100%
Passed
Tokens
248
Input
665
Total output
686
Reasoning within output
git_bisect f009
100%
Passed
Tokens
239
Input
295
Total output
265
Reasoning within output
git_bisect f010
100%
Passed
Tokens
252
Input
454
Total output
436
Reasoning within output
git_bisect f011
100%
Passed
Tokens
245
Input
210
Total output
174
Reasoning within output
git_bisect f012
100%
Passed
Tokens
268
Input
318
Total output
305
Reasoning within output
git_clean f001
100%
Passed
Tokens
107
Input
331
Total output
317
Reasoning within output
git_clean f002
100%
Passed
Tokens
118
Input
477
Total output
459
Reasoning within output
git_clean f003
100%
Passed
Tokens
115
Input
149
Total output
140
Reasoning within output
git_clean f004
100%
Passed
Tokens
115
Input
84
Total output
79
Reasoning within output
git_clean f005
100%
Passed
Tokens
94
Input
775
Total output
834
Reasoning within output
git_clean f006
100%
Passed
Tokens
128
Input
430
Total output
451
Reasoning within output
git_clean f007
100%
Passed
Tokens
120
Input
676
Total output
710
Reasoning within output
git_clean f008
100%
Passed
Tokens
127
Input
450
Total output
473
Reasoning within output
git_clean f009
75%
Failed
Tokens
123
Input
611
Total output
594
Reasoning within output
git_clean f010
100%
Passed
Tokens
107
Input
336
Total output
345
Reasoning within output
git_clean f011
100%
Passed
Tokens
106
Input
435
Total output
484
Reasoning within output
git_clean f012
100%
Passed
Tokens
119
Input
599
Total output
636
Reasoning within output
git_grep f001
100%
Passed
Tokens
110
Input
64
Total output
61
Reasoning within output
git_grep f002
100%
Passed
Tokens
123
Input
217
Total output
218
Reasoning within output
git_grep f003
100%
Passed
Tokens
141
Input
126
Total output
129
Reasoning within output
git_grep f004
100%
Passed
Tokens
135
Input
80
Total output
65
Reasoning within output
git_grep f005
100%
Passed
Tokens
170
Input
203
Total output
191
Reasoning within output
git_grep f006
100%
Passed
Tokens
87
Input
441
Total output
492
Reasoning within output
git_grep f007
100%
Passed
Tokens
215
Input
760
Total output
775
Reasoning within output
git_grep f008
100%
Passed
Tokens
104
Input
178
Total output
195
Reasoning within output
git_grep f009
100%
Passed
Tokens
113
Input
71
Total output
68
Reasoning within output
git_grep f010
100%
Passed
Tokens
120
Input
356
Total output
383
Reasoning within output
git_grep f011
100%
Passed
Tokens
167
Input
217
Total output
236
Reasoning within output
git_grep f012
100%
Passed
Tokens
122
Input
121
Total output
113
Reasoning within output
git_log_format f001
100%
Passed
Tokens
748
Input
178
Total output
182
Reasoning within output
git_log_format f002
100%
Passed
Tokens
734
Input
301
Total output
371
Reasoning within output
git_log_format f003
100%
Passed
Tokens
616
Input
188
Total output
181
Reasoning within output
git_log_format f004
100%
Passed
Tokens
752
Input
144
Total output
106
Reasoning within output
git_log_format f005
100%
Passed
Tokens
611
Input
956
Total output
1,044
Reasoning within output
git_log_format f006
100%
Passed
Tokens
752
Input
183
Total output
162
Reasoning within output
git_log_format f007
100%
Passed
Tokens
768
Input
193
Total output
180
Reasoning within output
git_log_format f008
100%
Passed
Tokens
994
Input
124
Total output
111
Reasoning within output
git_log_format f009
100%
Passed
Tokens
625
Input
156
Total output
143
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,135
Input
53
Total output
52
Reasoning within output
git_log_format f011
100%
Passed
Tokens
389
Input
166
Total output
166
Reasoning within output
git_log_format f012
100%
Passed
Tokens
392
Input
181
Total output
170
Reasoning within output
git_show f001
100%
Passed
Tokens
227
Input
113
Total output
115
Reasoning within output
git_show f002
100%
Passed
Tokens
211
Input
497
Total output
584
Reasoning within output
git_show f003
100%
Passed
Tokens
633
Input
211
Total output
0
Reasoning within output
git_show f004
100%
Passed
Tokens
450
Input
361
Total output
291
Reasoning within output
git_show f005
100%
Passed
Tokens
229
Input
346
Total output
366
Reasoning within output
git_show f006
100%
Passed
Tokens
237
Input
65
Total output
64
Reasoning within output
git_show f007
100%
Passed
Tokens
211
Input
204
Total output
187
Reasoning within output
git_show f008
100%
Passed
Tokens
244
Input
169
Total output
141
Reasoning within output
git_show f009
100%
Passed
Tokens
307
Input
226
Total output
214
Reasoning within output
git_show f010
100%
Passed
Tokens
214
Input
267
Total output
248
Reasoning within output
git_show f011
100%
Passed
Tokens
260
Input
68
Total output
56
Reasoning within output
git_show f012
100%
Passed
Tokens
351
Input
284
Total output
275
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
143
Input
983
Total output
1,165
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
159
Input
1,130
Total output
1,103
Reasoning within output
merge_conflicts f003
0%
Failed
Tokens
139
Input
872
Total output
1,035
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
174
Input
2,307
Total output
2,564
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
194
Input
253
Total output
283
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
174
Input
862
Total output
881
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
168
Input
384
Total output
414
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
163
Input
308
Total output
354
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
147
Input
638
Total output
711
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
217
Input
644
Total output
716
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
186
Input
532
Total output
495
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
280
Input
1,042
Total output
1,093
Reasoning within output
rebase f001
0%
Failed
Tokens
150
Input
478
Total output
470
Reasoning within output
rebase f002
100%
Passed
Tokens
180
Input
166
Total output
149
Reasoning within output
rebase f003
100%
Passed
Tokens
159
Input
395
Total output
465
Reasoning within output
rebase f004
0%
Failed
Tokens
200
Input
1,398
Total output
1,544
Reasoning within output
rebase f005
100%
Passed
Tokens
199
Input
516
Total output
620
Reasoning within output
rebase f006
100%
Passed
Tokens
174
Input
985
Total output
1,009
Reasoning within output
rebase f007
100%
Passed
Tokens
182
Input
115
Total output
107
Reasoning within output
rebase f008
100%
Passed
Tokens
175
Input
49
Total output
43
Reasoning within output
rebase f009
100%
Passed
Tokens
156
Input
186
Total output
194
Reasoning within output
rebase f010
100%
Passed
Tokens
242
Input
517
Total output
577
Reasoning within output
rebase f011
100%
Passed
Tokens
206
Input
506
Total output
493
Reasoning within output
rebase f012
0%
Failed
Tokens
311
Input
2,960
Total output
3,355
Reasoning within output
reflog f001
100%
Passed
Tokens
261
Input
212
Total output
189
Reasoning within output
reflog f002
100%
Passed
Tokens
248
Input
625
Total output
407
Reasoning within output
reflog f003
100%
Passed
Tokens
243
Input
534
Total output
88
Reasoning within output
reflog f004
100%
Passed
Tokens
363
Input
1,099
Total output
840
Reasoning within output
reflog f005
100%
Passed
Tokens
359
Input
1,924
Total output
1,251
Reasoning within output
reflog f006
100%
Passed
Tokens
278
Input
328
Total output
110
Reasoning within output
reflog f007
100%
Passed
Tokens
319
Input
1,413
Total output
0
Reasoning within output
reflog f008
100%
Passed
Tokens
366
Input
764
Total output
508
Reasoning within output
reflog f009
100%
Passed
Tokens
332
Input
921
Total output
694
Reasoning within output
reflog f010
100%
Passed
Tokens
296
Input
1,656
Total output
713
Reasoning within output
reflog f011
100%
Passed
Tokens
333
Input
2,164
Total output
1,796
Reasoning within output
reflog f012
100%
Passed
Tokens
354
Input
2,688
Total output
0
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
189
Input
191
Total output
177
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
325
Input
320
Total output
278
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
173
Input
142
Total output
125
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
171
Input
360
Total output
338
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
167
Input
183
Total output
164
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
228
Input
158
Total output
150
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
256
Input
292
Total output
259
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
220
Input
220
Total output
178
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
252
Input
268
Total output
223
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
180
Input
122
Total output
91
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
171
Input
509
Total output
488
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
185
Input
249
Total output
192
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
103
Input
135
Total output
112
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
139
Input
766
Total output
895
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
152
Input
1,432
Total output
1,347
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
126
Input
344
Total output
385
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
110
Input
1,240
Total output
1,173
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
134
Input
2,076
Total output
2,328
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
111
Input
171
Total output
134
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
145
Input
593
Total output
632
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
139
Input
309
Total output
330
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
153
Input
132
Total output
109
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
137
Input
176
Total output
186
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
96
Input
215
Total output
209
Reasoning within output
tag_management f001
100%
Passed
Tokens
121
Input
140
Total output
125
Reasoning within output
tag_management f002
100%
Passed
Tokens
104
Input
216
Total output
185
Reasoning within output
tag_management f003
100%
Passed
Tokens
118
Input
150
Total output
128
Reasoning within output
tag_management f004
100%
Passed
Tokens
113
Input
205
Total output
190
Reasoning within output
tag_management f005
100%
Passed
Tokens
135
Input
389
Total output
370
Reasoning within output
tag_management f006
100%
Passed
Tokens
121
Input
367
Total output
325
Reasoning within output
tag_management f007
100%
Passed
Tokens
122
Input
2,574
Total output
2,555
Reasoning within output
tag_management f008
100%
Passed
Tokens
124
Input
1,748
Total output
1,573
Reasoning within output
tag_management f009
100%
Passed
Tokens
129
Input
196
Total output
165
Reasoning within output
tag_management f010
100%
Passed
Tokens
107
Input
44
Total output
37
Reasoning within output
tag_management f011
100%
Passed
Tokens
105
Input
99
Total output
86
Reasoning within output
tag_management f012
100%
Passed
Tokens
128
Input
443
Total output
369
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
188
Input
260
Total output
290
Reasoning within output
worktree_usage f002
0%
Failed
Tokens
191
Input
395
Total output
428
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
232
Input
253
Total output
266
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
244
Input
109
Total output
119
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
178
Input
441
Total output
479
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
168
Input
571
Total output
542
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
163
Input
449
Total output
454
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
185
Input
1,230
Total output
1,276
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
279
Input
206
Total output
192
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
237
Input
537
Total output
555
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
228
Input
245
Total output
250
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
178
Input
691
Total output
621
Reasoning within output