Openai / gpt-oss-20b
high
97.1%
198 / 204 fixtures · 1 run(s)
46,163 input / 149,183 total output / 150,276 reasoning within output tokens $0.02609259
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-12.8%
Text: 97.1% →
JSON: 84.3%
+1
Gained
JSON pass / text fail
−27
Lost
Text pass / JSON fail
171
Unchanged Pass
Both pass
5
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| git_clean | 100% | 66.7% | -33.3% |
| reflog | 100% | 66.7% | -33.3% |
| submodule_usage | 100% | 75% | -25% |
| branch_cleanup | 100% | 83.3% | -16.7% |
| git_show | 100% | 83.3% | -16.7% |
| merge_conflicts | 91.7% | 75% | -16.7% |
| stash_recovery | 100% | 83.3% | -16.7% |
| rebase | 91.7% | 83.3% | -8.3% |
| cherry_pick | 83.3% | 75% | -8.3% |
| commit_squash | 100% | 91.7% | -8.3% |
| git_grep | 100% | 91.7% | -8.3% |
| git_log_format | 100% | 91.7% | -8.3% |
| tag_management | 100% | 91.7% | -8.3% |
| worktree_usage | 83.3% | 75% | -8.3% |
| blame_forensics | 100% | 100% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
Changed Fixtures (28)
f003 -loss f009 -loss f011 -loss f006 -loss f005 -loss f007 -loss f008 -loss f012 -loss f010 -loss f001 -loss f002 -loss f008 -loss f004 -loss f011 -loss f011 -loss f001 -loss f006 -loss f009 -loss f011 -loss f001 -loss f009 -loss f003 -loss f007 -loss f008 -loss f008 -loss f005 -loss f006 -loss f007 +gain
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
270
Input
670
Total output
748
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
264
Input
272
Total output
268
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
286
Input
316
Total output
297
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
212
Input
546
Total output
589
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
266
Input
7,414
Total output
8,455
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
273
Input
3,576
Total output
3,901
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
240
Input
251
Total output
255
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
269
Input
601
Total output
650
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
229
Input
964
Total output
1,095
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
408
Input
1,726
Total output
1,899
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
262
Input
341
Total output
338
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
177
Input
573
Total output
583
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
158
Input
399
Total output
392
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
171
Input
155
Total output
150
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
136
Input
393
Total output
430
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
180
Input
322
Total output
343
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
163
Input
100
Total output
97
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
164
Input
230
Total output
230
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
161
Input
265
Total output
287
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
175
Input
397
Total output
385
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
125
Input
495
Total output
562
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
168
Input
357
Total output
360
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
115
Input
258
Total output
291
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
205
Input
571
Total output
572
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
153
Input
1,073
Total output
1,249
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
172
Input
821
Total output
768
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
144
Input
1,255
Total output
1,252
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
200
Input
8,671
Total output
10,258
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
190
Input
212
Total output
229
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
175
Input
860
Total output
807
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
181
Input
114
Total output
106
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
178
Input
184
Total output
193
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
151
Input
180
Total output
185
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
261
Input
526
Total output
607
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
217
Input
565
Total output
551
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
311
Input
704
Total output
765
Reasoning within output
commit_messages f001
89.7%
Passed
Tokens
162
Input
120
Total output
108
Reasoning within output
commit_messages f002
81.7%
Passed
Tokens
243
Input
205
Total output
188
Reasoning within output
commit_messages f003
94.7%
Passed
Tokens
139
Input
366
Total output
308
Reasoning within output
commit_messages f004
93.3%
Passed
Tokens
156
Input
186
Total output
176
Reasoning within output
commit_messages f005
91%
Passed
Tokens
159
Input
256
Total output
214
Reasoning within output
commit_messages f006
91%
Passed
Tokens
192
Input
1,042
Total output
888
Reasoning within output
commit_messages f007
82.7%
Passed
Tokens
221
Input
174
Total output
173
Reasoning within output
commit_messages f008
79.7%
Passed
Tokens
129
Input
284
Total output
302
Reasoning within output
commit_messages f009
91%
Passed
Tokens
181
Input
189
Total output
181
Reasoning within output
commit_messages f010
89.3%
Passed
Tokens
317
Input
314
Total output
305
Reasoning within output
commit_messages f011
81.7%
Passed
Tokens
199
Input
825
Total output
815
Reasoning within output
commit_messages f012
90%
Passed
Tokens
169
Input
519
Total output
508
Reasoning within output
commit_squash f001
100%
Passed
Tokens
191
Input
1,518
Total output
1,631
Reasoning within output
commit_squash f002
100%
Passed
Tokens
172
Input
1,861
Total output
1,858
Reasoning within output
commit_squash f003
100%
Passed
Tokens
184
Input
308
Total output
296
Reasoning within output
commit_squash f004
100%
Passed
Tokens
174
Input
216
Total output
205
Reasoning within output
commit_squash f005
100%
Passed
Tokens
166
Input
1,220
Total output
1,335
Reasoning within output
commit_squash f006
100%
Passed
Tokens
156
Input
270
Total output
298
Reasoning within output
commit_squash f007
100%
Passed
Tokens
157
Input
442
Total output
436
Reasoning within output
commit_squash f008
100%
Passed
Tokens
160
Input
413
Total output
417
Reasoning within output
commit_squash f009
100%
Passed
Tokens
160
Input
272
Total output
261
Reasoning within output
commit_squash f010
100%
Passed
Tokens
163
Input
235
Total output
228
Reasoning within output
commit_squash f011
100%
Passed
Tokens
190
Input
392
Total output
377
Reasoning within output
commit_squash f012
100%
Passed
Tokens
188
Input
510
Total output
490
Reasoning within output
git_bisect f001
100%
Passed
Tokens
231
Input
102
Total output
97
Reasoning within output
git_bisect f002
100%
Passed
Tokens
246
Input
294
Total output
289
Reasoning within output
git_bisect f003
100%
Passed
Tokens
246
Input
915
Total output
961
Reasoning within output
git_bisect f004
100%
Passed
Tokens
243
Input
254
Total output
237
Reasoning within output
git_bisect f005
100%
Passed
Tokens
256
Input
419
Total output
414
Reasoning within output
git_bisect f006
100%
Passed
Tokens
276
Input
586
Total output
551
Reasoning within output
git_bisect f007
100%
Passed
Tokens
237
Input
650
Total output
604
Reasoning within output
git_bisect f008
100%
Passed
Tokens
252
Input
706
Total output
684
Reasoning within output
git_bisect f009
100%
Passed
Tokens
255
Input
863
Total output
905
Reasoning within output
git_bisect f010
100%
Passed
Tokens
243
Input
756
Total output
741
Reasoning within output
git_bisect f011
100%
Passed
Tokens
252
Input
215
Total output
197
Reasoning within output
git_bisect f012
100%
Passed
Tokens
277
Input
676
Total output
695
Reasoning within output
git_clean f001
100%
Passed
Tokens
107
Input
116
Total output
109
Reasoning within output
git_clean f002
100%
Passed
Tokens
116
Input
268
Total output
282
Reasoning within output
git_clean f003
100%
Passed
Tokens
113
Input
302
Total output
305
Reasoning within output
git_clean f004
100%
Passed
Tokens
113
Input
296
Total output
309
Reasoning within output
git_clean f005
100%
Passed
Tokens
106
Input
558
Total output
574
Reasoning within output
git_clean f006
100%
Passed
Tokens
130
Input
169
Total output
164
Reasoning within output
git_clean f007
100%
Passed
Tokens
120
Input
681
Total output
750
Reasoning within output
git_clean f008
100%
Passed
Tokens
129
Input
638
Total output
631
Reasoning within output
git_clean f009
100%
Passed
Tokens
123
Input
262
Total output
256
Reasoning within output
git_clean f010
100%
Passed
Tokens
118
Input
351
Total output
336
Reasoning within output
git_clean f011
100%
Passed
Tokens
119
Input
351
Total output
326
Reasoning within output
git_clean f012
100%
Passed
Tokens
119
Input
9,339
Total output
9,991
Reasoning within output
git_grep f001
100%
Passed
Tokens
110
Input
138
Total output
135
Reasoning within output
git_grep f002
100%
Passed
Tokens
111
Input
187
Total output
185
Reasoning within output
git_grep f003
100%
Passed
Tokens
147
Input
149
Total output
139
Reasoning within output
git_grep f004
100%
Passed
Tokens
133
Input
341
Total output
328
Reasoning within output
git_grep f005
100%
Passed
Tokens
175
Input
299
Total output
308
Reasoning within output
git_grep f006
100%
Passed
Tokens
100
Input
198
Total output
197
Reasoning within output
git_grep f007
100%
Passed
Tokens
215
Input
9,472
Total output
9,732
Reasoning within output
git_grep f008
100%
Passed
Tokens
117
Input
137
Total output
157
Reasoning within output
git_grep f009
100%
Passed
Tokens
113
Input
163
Total output
151
Reasoning within output
git_grep f010
100%
Passed
Tokens
126
Input
125
Total output
115
Reasoning within output
git_grep f011
100%
Passed
Tokens
167
Input
543
Total output
536
Reasoning within output
git_grep f012
100%
Passed
Tokens
124
Input
166
Total output
148
Reasoning within output
git_log_format f001
100%
Passed
Tokens
755
Input
426
Total output
417
Reasoning within output
git_log_format f002
100%
Passed
Tokens
751
Input
148
Total output
174
Reasoning within output
git_log_format f003
100%
Passed
Tokens
624
Input
289
Total output
271
Reasoning within output
git_log_format f004
100%
Passed
Tokens
731
Input
138
Total output
109
Reasoning within output
git_log_format f005
100%
Passed
Tokens
611
Input
758
Total output
868
Reasoning within output
git_log_format f006
100%
Passed
Tokens
752
Input
141
Total output
103
Reasoning within output
git_log_format f007
100%
Passed
Tokens
769
Input
458
Total output
404
Reasoning within output
git_log_format f008
100%
Passed
Tokens
998
Input
66
Total output
60
Reasoning within output
git_log_format f009
100%
Passed
Tokens
626
Input
52
Total output
51
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,123
Input
37
Total output
36
Reasoning within output
git_log_format f011
100%
Passed
Tokens
406
Input
149
Total output
139
Reasoning within output
git_log_format f012
100%
Passed
Tokens
362
Input
362
Total output
317
Reasoning within output
git_show f001
100%
Passed
Tokens
210
Input
174
Total output
180
Reasoning within output
git_show f002
100%
Passed
Tokens
218
Input
1,127
Total output
1,202
Reasoning within output
git_show f003
100%
Passed
Tokens
606
Input
226
Total output
187
Reasoning within output
git_show f004
100%
Passed
Tokens
446
Input
267
Total output
238
Reasoning within output
git_show f005
100%
Passed
Tokens
221
Input
336
Total output
354
Reasoning within output
git_show f006
100%
Passed
Tokens
242
Input
279
Total output
268
Reasoning within output
git_show f007
100%
Passed
Tokens
211
Input
282
Total output
255
Reasoning within output
git_show f008
100%
Passed
Tokens
241
Input
268
Total output
179
Reasoning within output
git_show f009
100%
Passed
Tokens
318
Input
262
Total output
218
Reasoning within output
git_show f010
100%
Passed
Tokens
233
Input
178
Total output
168
Reasoning within output
git_show f011
100%
Passed
Tokens
255
Input
51
Total output
39
Reasoning within output
git_show f012
100%
Passed
Tokens
347
Input
125
Total output
114
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
141
Input
339
Total output
328
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
161
Input
300
Total output
285
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
136
Input
1,392
Total output
1,395
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
187
Input
2,976
Total output
2,991
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
190
Input
494
Total output
553
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
181
Input
1,013
Total output
992
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
181
Input
450
Total output
436
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
161
Input
179
Total output
187
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
160
Input
371
Total output
366
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
230
Input
275
Total output
251
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
199
Input
312
Total output
291
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
280
Input
1,006
Total output
963
Reasoning within output
rebase f001
100%
Passed
Tokens
151
Input
1,326
Total output
1,540
Reasoning within output
rebase f002
100%
Passed
Tokens
183
Input
747
Total output
712
Reasoning within output
rebase f003
100%
Passed
Tokens
161
Input
234
Total output
260
Reasoning within output
rebase f004
100%
Passed
Tokens
200
Input
987
Total output
1,081
Reasoning within output
rebase f005
100%
Passed
Tokens
193
Input
590
Total output
681
Reasoning within output
rebase f006
100%
Passed
Tokens
185
Input
601
Total output
526
Reasoning within output
rebase f007
100%
Passed
Tokens
183
Input
533
Total output
518
Reasoning within output
rebase f008
100%
Passed
Tokens
176
Input
446
Total output
507
Reasoning within output
rebase f009
100%
Passed
Tokens
158
Input
239
Total output
228
Reasoning within output
rebase f010
100%
Passed
Tokens
255
Input
855
Total output
1,000
Reasoning within output
rebase f011
100%
Passed
Tokens
206
Input
484
Total output
469
Reasoning within output
rebase f012
0%
Failed
Tokens
307
Input
1,165
Total output
1,209
Reasoning within output
reflog f001
100%
Passed
Tokens
246
Input
616
Total output
526
Reasoning within output
reflog f002
100%
Passed
Tokens
262
Input
603
Total output
469
Reasoning within output
reflog f003
100%
Passed
Tokens
237
Input
595
Total output
365
Reasoning within output
reflog f004
100%
Passed
Tokens
330
Input
1,105
Total output
534
Reasoning within output
reflog f005
100%
Passed
Tokens
394
Input
2,323
Total output
1,785
Reasoning within output
reflog f006
100%
Passed
Tokens
278
Input
1,466
Total output
1,098
Reasoning within output
reflog f007
100%
Passed
Tokens
294
Input
974
Total output
809
Reasoning within output
reflog f008
100%
Passed
Tokens
368
Input
642
Total output
414
Reasoning within output
reflog f009
100%
Passed
Tokens
354
Input
2,370
Total output
2,248
Reasoning within output
reflog f010
100%
Passed
Tokens
301
Input
578
Total output
424
Reasoning within output
reflog f011
100%
Passed
Tokens
329
Input
3,096
Total output
2,842
Reasoning within output
reflog f012
100%
Passed
Tokens
333
Input
1,515
Total output
692
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
186
Input
227
Total output
194
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
315
Input
141
Total output
116
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
178
Input
177
Total output
118
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
170
Input
258
Total output
219
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
180
Input
391
Total output
380
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
228
Input
148
Total output
110
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
252
Input
266
Total output
248
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
220
Input
380
Total output
309
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
254
Input
306
Total output
293
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
167
Input
229
Total output
193
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
171
Input
570
Total output
500
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
184
Input
379
Total output
343
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
90
Input
212
Total output
211
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
150
Input
2,059
Total output
2,310
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
140
Input
2,733
Total output
2,874
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
139
Input
470
Total output
438
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
112
Input
474
Total output
499
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
140
Input
725
Total output
680
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
111
Input
131
Total output
112
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
147
Input
4,534
Total output
4,931
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
141
Input
244
Total output
239
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
152
Input
365
Total output
332
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
155
Input
76
Total output
61
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
107
Input
276
Total output
281
Reasoning within output
tag_management f001
100%
Passed
Tokens
114
Input
52
Total output
34
Reasoning within output
tag_management f002
100%
Passed
Tokens
115
Input
277
Total output
252
Reasoning within output
tag_management f003
100%
Passed
Tokens
120
Input
80
Total output
61
Reasoning within output
tag_management f004
100%
Passed
Tokens
123
Input
255
Total output
253
Reasoning within output
tag_management f005
100%
Passed
Tokens
138
Input
429
Total output
435
Reasoning within output
tag_management f006
100%
Passed
Tokens
107
Input
305
Total output
277
Reasoning within output
tag_management f007
100%
Passed
Tokens
122
Input
1,462
Total output
1,333
Reasoning within output
tag_management f008
100%
Passed
Tokens
131
Input
640
Total output
554
Reasoning within output
tag_management f009
100%
Passed
Tokens
130
Input
91
Total output
74
Reasoning within output
tag_management f010
100%
Passed
Tokens
112
Input
83
Total output
60
Reasoning within output
tag_management f011
100%
Passed
Tokens
94
Input
424
Total output
451
Reasoning within output
tag_management f012
100%
Passed
Tokens
139
Input
336
Total output
327
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
181
Input
308
Total output
292
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
192
Input
394
Total output
397
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
244
Input
590
Total output
623
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
238
Input
257
Total output
285
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
160
Input
1,330
Total output
1,391
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
178
Input
258
Total output
236
Reasoning within output
worktree_usage f007
0%
Failed
Tokens
167
Input
713
Total output
740
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
201
Input
1,467
Total output
1,513
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
269
Input
198
Total output
208
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
244
Input
3,058
Total output
3,069
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
241
Input
248
Total output
256
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
164
Input
182
Total output
154
Reasoning within output