Openai / gpt-oss-20b
xhigh
96.1%
196 / 204 fixtures · 1 run(s)
46,158 input / 129,978 total output / 129,754 reasoning within output tokens $0.02223179
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-8.8%
Text: 96.1% →
JSON: 87.3%
+2
Gained
JSON pass / text fail
−20
Lost
Text pass / JSON fail
176
Unchanged Pass
Both pass
6
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| merge_conflicts | 91.7% | 66.7% | -25% |
| reflog | 100% | 75% | -25% |
| blame_forensics | 100% | 83.3% | -16.7% |
| commit_squash | 100% | 83.3% | -16.7% |
| git_log_format | 100% | 83.3% | -16.7% |
| branch_cleanup | 100% | 91.7% | -8.3% |
| cherry_pick | 83.3% | 75% | -8.3% |
| git_bisect | 100% | 91.7% | -8.3% |
| git_clean | 100% | 91.7% | -8.3% |
| git_grep | 100% | 91.7% | -8.3% |
| stash_recovery | 100% | 91.7% | -8.3% |
| submodule_usage | 91.7% | 100% | + 8.3% |
| tag_management | 100% | 91.7% | -8.3% |
| commit_messages | 100% | 100% | + 0% |
| git_show | 100% | 100% | + 0% |
| rebase | 83.3% | 83.3% | + 0% |
| worktree_usage | 83.3% | 83.3% | + 0% |
Changed Fixtures (22)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
281
Input
838
Total output
913
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
261
Input
604
Total output
595
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
286
Input
330
Total output
345
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
230
Input
627
Total output
710
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
273
Input
1,166
Total output
1,258
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
267
Input
1,491
Total output
1,531
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
246
Input
452
Total output
442
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
275
Input
472
Total output
468
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
232
Input
918
Total output
996
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
421
Input
745
Total output
768
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
267
Input
294
Total output
253
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
188
Input
1,843
Total output
1,838
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
155
Input
532
Total output
560
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
171
Input
673
Total output
715
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
140
Input
425
Total output
480
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
189
Input
519
Total output
559
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
163
Input
320
Total output
351
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
178
Input
170
Total output
163
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
157
Input
463
Total output
530
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
163
Input
253
Total output
249
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
139
Input
336
Total output
375
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
171
Input
318
Total output
317
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
128
Input
280
Total output
310
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
209
Input
406
Total output
367
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
136
Input
786
Total output
905
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
174
Input
633
Total output
588
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
144
Input
875
Total output
1,021
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
184
Input
11,440
Total output
13,569
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
205
Input
181
Total output
165
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
174
Input
959
Total output
936
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
166
Input
780
Total output
868
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
181
Input
232
Total output
217
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
149
Input
207
Total output
223
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
261
Input
925
Total output
1,036
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
204
Input
410
Total output
387
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
296
Input
1,627
Total output
1,787
Reasoning within output
commit_messages f001
89%
Passed
Tokens
160
Input
520
Total output
457
Reasoning within output
commit_messages f002
84.3%
Passed
Tokens
256
Input
323
Total output
306
Reasoning within output
commit_messages f003
91.7%
Passed
Tokens
141
Input
247
Total output
200
Reasoning within output
commit_messages f004
91%
Passed
Tokens
169
Input
37
Total output
32
Reasoning within output
commit_messages f005
91%
Passed
Tokens
162
Input
340
Total output
378
Reasoning within output
commit_messages f006
88.3%
Passed
Tokens
197
Input
211
Total output
230
Reasoning within output
commit_messages f007
90%
Passed
Tokens
234
Input
497
Total output
488
Reasoning within output
commit_messages f008
89%
Passed
Tokens
129
Input
390
Total output
378
Reasoning within output
commit_messages f009
87.7%
Passed
Tokens
181
Input
287
Total output
276
Reasoning within output
commit_messages f010
91%
Passed
Tokens
317
Input
1,122
Total output
1,101
Reasoning within output
commit_messages f011
86.7%
Passed
Tokens
199
Input
964
Total output
954
Reasoning within output
commit_messages f012
90%
Passed
Tokens
169
Input
402
Total output
364
Reasoning within output
commit_squash f001
100%
Passed
Tokens
195
Input
533
Total output
544
Reasoning within output
commit_squash f002
100%
Passed
Tokens
170
Input
443
Total output
477
Reasoning within output
commit_squash f003
100%
Passed
Tokens
185
Input
800
Total output
854
Reasoning within output
commit_squash f004
100%
Passed
Tokens
172
Input
538
Total output
535
Reasoning within output
commit_squash f005
100%
Passed
Tokens
170
Input
256
Total output
249
Reasoning within output
commit_squash f006
100%
Passed
Tokens
152
Input
151
Total output
140
Reasoning within output
commit_squash f007
100%
Passed
Tokens
155
Input
411
Total output
381
Reasoning within output
commit_squash f008
100%
Passed
Tokens
171
Input
462
Total output
470
Reasoning within output
commit_squash f009
100%
Passed
Tokens
158
Input
540
Total output
546
Reasoning within output
commit_squash f010
100%
Passed
Tokens
178
Input
146
Total output
131
Reasoning within output
commit_squash f011
100%
Passed
Tokens
184
Input
711
Total output
686
Reasoning within output
commit_squash f012
100%
Passed
Tokens
179
Input
508
Total output
484
Reasoning within output
git_bisect f001
100%
Passed
Tokens
216
Input
313
Total output
299
Reasoning within output
git_bisect f002
100%
Passed
Tokens
250
Input
299
Total output
289
Reasoning within output
git_bisect f003
100%
Passed
Tokens
246
Input
649
Total output
691
Reasoning within output
git_bisect f004
100%
Passed
Tokens
246
Input
1,515
Total output
1,641
Reasoning within output
git_bisect f005
100%
Passed
Tokens
248
Input
625
Total output
621
Reasoning within output
git_bisect f006
100%
Passed
Tokens
271
Input
384
Total output
342
Reasoning within output
git_bisect f007
100%
Passed
Tokens
252
Input
750
Total output
742
Reasoning within output
git_bisect f008
100%
Passed
Tokens
258
Input
715
Total output
706
Reasoning within output
git_bisect f009
100%
Passed
Tokens
239
Input
691
Total output
662
Reasoning within output
git_bisect f010
100%
Passed
Tokens
246
Input
402
Total output
370
Reasoning within output
git_bisect f011
100%
Passed
Tokens
244
Input
492
Total output
534
Reasoning within output
git_bisect f012
100%
Passed
Tokens
269
Input
689
Total output
669
Reasoning within output
git_clean f001
100%
Passed
Tokens
105
Input
370
Total output
390
Reasoning within output
git_clean f002
100%
Passed
Tokens
105
Input
326
Total output
334
Reasoning within output
git_clean f003
100%
Passed
Tokens
115
Input
501
Total output
558
Reasoning within output
git_clean f004
100%
Passed
Tokens
115
Input
1,260
Total output
1,256
Reasoning within output
git_clean f005
100%
Passed
Tokens
109
Input
652
Total output
652
Reasoning within output
git_clean f006
100%
Passed
Tokens
130
Input
257
Total output
250
Reasoning within output
git_clean f007
100%
Passed
Tokens
122
Input
219
Total output
211
Reasoning within output
git_clean f008
100%
Passed
Tokens
129
Input
247
Total output
231
Reasoning within output
git_clean f009
100%
Passed
Tokens
123
Input
257
Total output
251
Reasoning within output
git_clean f010
100%
Passed
Tokens
120
Input
473
Total output
448
Reasoning within output
git_clean f011
100%
Passed
Tokens
119
Input
381
Total output
366
Reasoning within output
git_clean f012
100%
Passed
Tokens
119
Input
842
Total output
852
Reasoning within output
git_grep f001
100%
Passed
Tokens
110
Input
120
Total output
117
Reasoning within output
git_grep f002
100%
Passed
Tokens
121
Input
147
Total output
140
Reasoning within output
git_grep f003
100%
Passed
Tokens
143
Input
26
Total output
25
Reasoning within output
git_grep f004
100%
Passed
Tokens
135
Input
249
Total output
220
Reasoning within output
git_grep f005
100%
Passed
Tokens
168
Input
283
Total output
287
Reasoning within output
git_grep f006
100%
Passed
Tokens
102
Input
421
Total output
486
Reasoning within output
git_grep f007
100%
Passed
Tokens
202
Input
1,177
Total output
1,247
Reasoning within output
git_grep f008
100%
Passed
Tokens
119
Input
319
Total output
371
Reasoning within output
git_grep f009
100%
Passed
Tokens
100
Input
210
Total output
193
Reasoning within output
git_grep f010
100%
Passed
Tokens
122
Input
238
Total output
223
Reasoning within output
git_grep f011
100%
Passed
Tokens
167
Input
195
Total output
185
Reasoning within output
git_grep f012
100%
Passed
Tokens
124
Input
96
Total output
88
Reasoning within output
git_log_format f001
100%
Passed
Tokens
760
Input
344
Total output
333
Reasoning within output
git_log_format f002
100%
Passed
Tokens
744
Input
473
Total output
530
Reasoning within output
git_log_format f003
100%
Passed
Tokens
619
Input
280
Total output
285
Reasoning within output
git_log_format f004
100%
Passed
Tokens
773
Input
203
Total output
170
Reasoning within output
git_log_format f005
100%
Passed
Tokens
624
Input
325
Total output
341
Reasoning within output
git_log_format f006
100%
Passed
Tokens
754
Input
124
Total output
113
Reasoning within output
git_log_format f007
100%
Passed
Tokens
748
Input
261
Total output
256
Reasoning within output
git_log_format f008
100%
Passed
Tokens
988
Input
129
Total output
114
Reasoning within output
git_log_format f009
100%
Passed
Tokens
611
Input
151
Total output
142
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,101
Input
204
Total output
182
Reasoning within output
git_log_format f011
100%
Passed
Tokens
409
Input
176
Total output
184
Reasoning within output
git_log_format f012
100%
Passed
Tokens
379
Input
216
Total output
190
Reasoning within output
git_show f001
100%
Passed
Tokens
222
Input
191
Total output
197
Reasoning within output
git_show f002
100%
Passed
Tokens
228
Input
214
Total output
212
Reasoning within output
git_show f003
100%
Passed
Tokens
622
Input
409
Total output
399
Reasoning within output
git_show f004
100%
Passed
Tokens
451
Input
220
Total output
184
Reasoning within output
git_show f005
100%
Passed
Tokens
234
Input
744
Total output
740
Reasoning within output
git_show f006
100%
Passed
Tokens
242
Input
162
Total output
161
Reasoning within output
git_show f007
100%
Passed
Tokens
224
Input
115
Total output
101
Reasoning within output
git_show f008
100%
Passed
Tokens
235
Input
437
Total output
283
Reasoning within output
git_show f009
100%
Passed
Tokens
311
Input
293
Total output
260
Reasoning within output
git_show f010
100%
Passed
Tokens
215
Input
1,228
Total output
1,209
Reasoning within output
git_show f011
100%
Passed
Tokens
255
Input
180
Total output
196
Reasoning within output
git_show f012
100%
Passed
Tokens
337
Input
275
Total output
251
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
128
Input
741
Total output
832
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
159
Input
660
Total output
635
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
138
Input
1,111
Total output
1,290
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
187
Input
1,737
Total output
1,900
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
192
Input
204
Total output
188
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
163
Input
893
Total output
872
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
181
Input
319
Total output
305
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
165
Input
164
Total output
171
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
162
Input
403
Total output
438
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
217
Input
572
Total output
624
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
199
Input
413
Total output
367
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
280
Input
1,026
Total output
1,028
Reasoning within output
rebase f001
100%
Passed
Tokens
138
Input
476
Total output
533
Reasoning within output
rebase f002
100%
Passed
Tokens
168
Input
914
Total output
909
Reasoning within output
rebase f003
100%
Passed
Tokens
159
Input
389
Total output
378
Reasoning within output
rebase f004
0%
Failed
Tokens
200
Input
983
Total output
971
Reasoning within output
rebase f005
100%
Passed
Tokens
195
Input
318
Total output
297
Reasoning within output
rebase f006
100%
Passed
Tokens
190
Input
591
Total output
564
Reasoning within output
rebase f007
100%
Passed
Tokens
188
Input
448
Total output
489
Reasoning within output
rebase f008
100%
Passed
Tokens
176
Input
277
Total output
315
Reasoning within output
rebase f009
100%
Passed
Tokens
147
Input
1,362
Total output
1,536
Reasoning within output
rebase f010
100%
Passed
Tokens
259
Input
1,023
Total output
1,202
Reasoning within output
rebase f011
100%
Passed
Tokens
209
Input
1,704
Total output
1,765
Reasoning within output
rebase f012
0%
Failed
Tokens
294
Input
3,155
Total output
3,462
Reasoning within output
reflog f001
100%
Passed
Tokens
267
Input
266
Total output
239
Reasoning within output
reflog f002
100%
Passed
Tokens
244
Input
537
Total output
317
Reasoning within output
reflog f003
100%
Passed
Tokens
241
Input
568
Total output
329
Reasoning within output
reflog f004
100%
Passed
Tokens
330
Input
1,442
Total output
1,099
Reasoning within output
reflog f005
100%
Passed
Tokens
393
Input
468
Total output
393
Reasoning within output
reflog f006
100%
Passed
Tokens
276
Input
698
Total output
254
Reasoning within output
reflog f007
100%
Passed
Tokens
306
Input
670
Total output
401
Reasoning within output
reflog f008
100%
Passed
Tokens
380
Input
1,101
Total output
807
Reasoning within output
reflog f009
100%
Passed
Tokens
334
Input
1,904
Total output
1,461
Reasoning within output
reflog f010
100%
Passed
Tokens
291
Input
757
Total output
549
Reasoning within output
reflog f011
100%
Passed
Tokens
324
Input
2,418
Total output
1,956
Reasoning within output
reflog f012
100%
Passed
Tokens
323
Input
3,340
Total output
2,258
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
185
Input
206
Total output
206
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
328
Input
290
Total output
203
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
175
Input
181
Total output
147
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
169
Input
250
Total output
202
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
179
Input
514
Total output
449
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
226
Input
359
Total output
302
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
254
Input
192
Total output
155
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
209
Input
210
Total output
150
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
254
Input
259
Total output
215
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
178
Input
202
Total output
173
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
168
Input
529
Total output
484
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
187
Input
260
Total output
246
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
101
Input
267
Total output
281
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
137
Input
1,245
Total output
1,399
Reasoning within output
submodule_usage f003
75%
Failed
Tokens
156
Input
4,930
Total output
5,312
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
139
Input
216
Total output
196
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
97
Input
683
Total output
717
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
141
Input
222
Total output
225
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
109
Input
544
Total output
573
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
145
Input
1,832
Total output
1,974
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
138
Input
470
Total output
517
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
149
Input
319
Total output
379
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
150
Input
61
Total output
57
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
107
Input
204
Total output
209
Reasoning within output
tag_management f001
100%
Passed
Tokens
100
Input
216
Total output
196
Reasoning within output
tag_management f002
100%
Passed
Tokens
115
Input
94
Total output
57
Reasoning within output
tag_management f003
100%
Passed
Tokens
121
Input
320
Total output
283
Reasoning within output
tag_management f004
100%
Passed
Tokens
113
Input
259
Total output
249
Reasoning within output
tag_management f005
100%
Passed
Tokens
141
Input
166
Total output
146
Reasoning within output
tag_management f006
100%
Passed
Tokens
119
Input
902
Total output
823
Reasoning within output
tag_management f007
100%
Passed
Tokens
119
Input
376
Total output
335
Reasoning within output
tag_management f008
100%
Passed
Tokens
127
Input
489
Total output
460
Reasoning within output
tag_management f009
100%
Passed
Tokens
129
Input
695
Total output
656
Reasoning within output
tag_management f010
100%
Passed
Tokens
107
Input
125
Total output
102
Reasoning within output
tag_management f011
100%
Passed
Tokens
96
Input
392
Total output
417
Reasoning within output
tag_management f012
100%
Passed
Tokens
128
Input
1,652
Total output
1,548
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
170
Input
855
Total output
915
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
185
Input
671
Total output
713
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
235
Input
343
Total output
352
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
243
Input
181
Total output
169
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
173
Input
399
Total output
405
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
186
Input
1,650
Total output
1,617
Reasoning within output
worktree_usage f007
0%
Failed
Tokens
179
Input
557
Total output
531
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
202
Input
1,282
Total output
1,234
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
272
Input
164
Total output
150
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
249
Input
522
Total output
433
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
244
Input
117
Total output
109
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
179
Input
541
Total output
513
Reasoning within output