Qwen / qwen3.6-27b
low
94.1%
192 / 204 fixtures · 1 run(s)
41,023 input / 230,675 total output / 207,835 reasoning within output tokens $0.68313196
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-19.6%
Text: 94.1% →
JSON: 74.5%
+4
Gained
JSON pass / text fail
−44
Lost
Text pass / JSON fail
148
Unchanged Pass
Both pass
8
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| branch_cleanup | 100% | 58.3% | -41.7% |
| blame_forensics | 100% | 66.7% | -33.3% |
| git_clean | 100% | 66.7% | -33.3% |
| merge_conflicts | 83.3% | 50% | -33.3% |
| tag_management | 100% | 66.7% | -33.3% |
| rebase | 83.3% | 58.3% | -25% |
| reflog | 83.3% | 58.3% | -25% |
| worktree_usage | 83.3% | 58.3% | -25% |
| commit_messages | 100% | 83.3% | -16.7% |
| git_log_format | 100% | 83.3% | -16.7% |
| cherry_pick | 83.3% | 75% | -8.3% |
| git_bisect | 100% | 91.7% | -8.3% |
| git_grep | 100% | 91.7% | -8.3% |
| git_show | 100% | 91.7% | -8.3% |
| stash_recovery | 100% | 91.7% | -8.3% |
| submodule_usage | 83.3% | 75% | -8.3% |
| commit_squash | 100% | 100% | + 0% |
Changed Fixtures (48)
f001 -loss f003 -loss f005 -loss f011 -loss f002 -loss f003 -loss f008 -loss f009 -loss f011 -loss f011 -loss f001 -loss f011 -loss f012 -loss f003 -loss f004 -loss f005 -loss f012 -loss f004 -loss f004 -loss f011 -loss f004 -loss f001 -loss f004 +gain f006 -loss f009 -loss f010 -loss f011 -loss f001 -loss f009 -loss f011 -loss f003 -loss f004 -loss f006 -loss f008 -loss f009 +gain f010 +gain f011 -loss f011 -loss f001 -loss f003 +gain f011 -loss f005 -loss f009 -loss f010 -loss f011 -loss f006 -loss f007 -loss f010 -loss
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
255
Input
769
Total output
689
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
250
Input
413
Total output
363
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
280
Input
1,131
Total output
958
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
202
Input
720
Total output
737
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
272
Input
1,096
Total output
970
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
251
Input
1,507
Total output
1,265
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
223
Input
259
Total output
230
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
256
Input
1,112
Total output
1,083
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
210
Input
320
Total output
310
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
449
Input
902
Total output
844
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
256
Input
978
Total output
832
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
149
Input
812
Total output
802
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
110
Input
724
Total output
645
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
127
Input
1,090
Total output
1,009
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
100
Input
626
Total output
598
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
141
Input
853
Total output
823
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
112
Input
1,084
Total output
991
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
142
Input
1,074
Total output
1,004
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
112
Input
737
Total output
716
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
128
Input
445
Total output
384
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
91
Input
823
Total output
779
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
125
Input
389
Total output
329
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
77
Input
526
Total output
516
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
165
Input
835
Total output
763
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
100
Input
931
Total output
986
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
120
Input
934
Total output
862
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
92
Input
1,317
Total output
1,395
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
164
Input
2,525
Total output
2,427
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
155
Input
1,012
Total output
997
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
147
Input
1,796
Total output
1,602
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
139
Input
874
Total output
848
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
126
Input
1,028
Total output
1,017
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
109
Input
891
Total output
881
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
222
Input
1,096
Total output
1,130
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
172
Input
1,362
Total output
1,179
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
277
Input
1,873
Total output
1,680
Reasoning within output
commit_messages f001
92.7%
Passed
Tokens
117
Input
1,210
Total output
1,113
Reasoning within output
commit_messages f002
84%
Passed
Tokens
233
Input
1,173
Total output
926
Reasoning within output
commit_messages f003
94%
Passed
Tokens
88
Input
898
Total output
790
Reasoning within output
commit_messages f004
94.3%
Passed
Tokens
125
Input
736
Total output
711
Reasoning within output
commit_messages f005
90%
Passed
Tokens
109
Input
1,305
Total output
1,192
Reasoning within output
commit_messages f006
90%
Passed
Tokens
156
Input
1,210
Total output
1,162
Reasoning within output
commit_messages f007
91%
Passed
Tokens
197
Input
1,535
Total output
1,524
Reasoning within output
commit_messages f008
91.7%
Passed
Tokens
81
Input
1,442
Total output
1,307
Reasoning within output
commit_messages f009
86.7%
Passed
Tokens
135
Input
1,774
Total output
1,762
Reasoning within output
commit_messages f010
87.7%
Passed
Tokens
305
Input
2,068
Total output
1,806
Reasoning within output
commit_messages f011
83.3%
Passed
Tokens
154
Input
1,761
Total output
1,609
Reasoning within output
commit_messages f012
91.7%
Passed
Tokens
135
Input
1,380
Total output
1,139
Reasoning within output
commit_squash f001
100%
Passed
Tokens
146
Input
1,244
Total output
1,228
Reasoning within output
commit_squash f002
100%
Passed
Tokens
123
Input
1,026
Total output
1,013
Reasoning within output
commit_squash f003
100%
Passed
Tokens
136
Input
1,171
Total output
1,088
Reasoning within output
commit_squash f004
100%
Passed
Tokens
125
Input
1,075
Total output
1,010
Reasoning within output
commit_squash f005
100%
Passed
Tokens
118
Input
1,112
Total output
1,128
Reasoning within output
commit_squash f006
100%
Passed
Tokens
104
Input
1,017
Total output
989
Reasoning within output
commit_squash f007
100%
Passed
Tokens
110
Input
1,248
Total output
1,187
Reasoning within output
commit_squash f008
100%
Passed
Tokens
124
Input
805
Total output
758
Reasoning within output
commit_squash f009
100%
Passed
Tokens
114
Input
896
Total output
851
Reasoning within output
commit_squash f010
100%
Passed
Tokens
130
Input
1,047
Total output
967
Reasoning within output
commit_squash f011
100%
Passed
Tokens
139
Input
827
Total output
728
Reasoning within output
commit_squash f012
100%
Passed
Tokens
138
Input
825
Total output
717
Reasoning within output
git_bisect f001
100%
Passed
Tokens
190
Input
328
Total output
269
Reasoning within output
git_bisect f002
100%
Passed
Tokens
226
Input
513
Total output
383
Reasoning within output
git_bisect f003
100%
Passed
Tokens
222
Input
778
Total output
624
Reasoning within output
git_bisect f004
100%
Passed
Tokens
222
Input
652
Total output
534
Reasoning within output
git_bisect f005
100%
Passed
Tokens
220
Input
1,101
Total output
884
Reasoning within output
git_bisect f006
100%
Passed
Tokens
246
Input
1,097
Total output
826
Reasoning within output
git_bisect f007
100%
Passed
Tokens
208
Input
354
Total output
286
Reasoning within output
git_bisect f008
100%
Passed
Tokens
218
Input
664
Total output
546
Reasoning within output
git_bisect f009
100%
Passed
Tokens
220
Input
1,757
Total output
1,378
Reasoning within output
git_bisect f010
100%
Passed
Tokens
224
Input
444
Total output
343
Reasoning within output
git_bisect f011
100%
Passed
Tokens
222
Input
608
Total output
481
Reasoning within output
git_bisect f012
100%
Passed
Tokens
250
Input
1,162
Total output
901
Reasoning within output
git_clean f001
100%
Passed
Tokens
55
Input
1,201
Total output
1,181
Reasoning within output
git_clean f002
100%
Passed
Tokens
66
Input
497
Total output
466
Reasoning within output
git_clean f003
100%
Passed
Tokens
65
Input
1,016
Total output
989
Reasoning within output
git_clean f004
100%
Passed
Tokens
62
Input
1,047
Total output
964
Reasoning within output
git_clean f005
100%
Passed
Tokens
54
Input
1,383
Total output
1,348
Reasoning within output
git_clean f006
100%
Passed
Tokens
79
Input
1,357
Total output
1,269
Reasoning within output
git_clean f007
100%
Passed
Tokens
70
Input
1,660
Total output
1,582
Reasoning within output
git_clean f008
100%
Passed
Tokens
82
Input
891
Total output
882
Reasoning within output
git_clean f009
100%
Passed
Tokens
73
Input
1,531
Total output
1,519
Reasoning within output
git_clean f010
100%
Passed
Tokens
68
Input
763
Total output
744
Reasoning within output
git_clean f011
100%
Passed
Tokens
66
Input
1,376
Total output
1,297
Reasoning within output
git_clean f012
100%
Passed
Tokens
68
Input
1,707
Total output
1,526
Reasoning within output
git_grep f001
100%
Passed
Tokens
54
Input
704
Total output
706
Reasoning within output
git_grep f002
100%
Passed
Tokens
68
Input
287
Total output
258
Reasoning within output
git_grep f003
100%
Passed
Tokens
89
Input
291
Total output
271
Reasoning within output
git_grep f004
100%
Passed
Tokens
78
Input
293
Total output
251
Reasoning within output
git_grep f005
100%
Passed
Tokens
119
Input
619
Total output
579
Reasoning within output
git_grep f006
100%
Passed
Tokens
43
Input
693
Total output
687
Reasoning within output
git_grep f007
100%
Passed
Tokens
171
Input
2,035
Total output
1,692
Reasoning within output
git_grep f008
100%
Passed
Tokens
60
Input
245
Total output
239
Reasoning within output
git_grep f009
100%
Passed
Tokens
56
Input
209
Total output
172
Reasoning within output
git_grep f010
100%
Passed
Tokens
66
Input
802
Total output
797
Reasoning within output
git_grep f011
100%
Passed
Tokens
114
Input
773
Total output
713
Reasoning within output
git_grep f012
100%
Passed
Tokens
67
Input
305
Total output
266
Reasoning within output
git_log_format f001
100%
Passed
Tokens
887
Input
163
Total output
147
Reasoning within output
git_log_format f002
100%
Passed
Tokens
896
Input
766
Total output
790
Reasoning within output
git_log_format f003
100%
Passed
Tokens
742
Input
1,030
Total output
947
Reasoning within output
git_log_format f004
100%
Passed
Tokens
893
Input
263
Total output
221
Reasoning within output
git_log_format f005
100%
Passed
Tokens
739
Input
1,256
Total output
1,113
Reasoning within output
git_log_format f006
100%
Passed
Tokens
913
Input
1,002
Total output
658
Reasoning within output
git_log_format f007
100%
Passed
Tokens
912
Input
181
Total output
155
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,208
Input
205
Total output
170
Reasoning within output
git_log_format f009
100%
Passed
Tokens
728
Input
126
Total output
119
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,397
Input
371
Total output
306
Reasoning within output
git_log_format f011
100%
Passed
Tokens
441
Input
211
Total output
185
Reasoning within output
git_log_format f012
100%
Passed
Tokens
404
Input
296
Total output
242
Reasoning within output
git_show f001
100%
Passed
Tokens
199
Input
356
Total output
333
Reasoning within output
git_show f002
100%
Passed
Tokens
203
Input
566
Total output
571
Reasoning within output
git_show f003
100%
Passed
Tokens
695
Input
415
Total output
309
Reasoning within output
git_show f004
100%
Passed
Tokens
464
Input
177
Total output
145
Reasoning within output
git_show f005
100%
Passed
Tokens
203
Input
281
Total output
280
Reasoning within output
git_show f006
100%
Passed
Tokens
212
Input
281
Total output
217
Reasoning within output
git_show f007
100%
Passed
Tokens
204
Input
448
Total output
396
Reasoning within output
git_show f008
100%
Passed
Tokens
210
Input
1,055
Total output
736
Reasoning within output
git_show f009
100%
Passed
Tokens
318
Input
383
Total output
318
Reasoning within output
git_show f010
100%
Passed
Tokens
201
Input
795
Total output
731
Reasoning within output
git_show f011
100%
Passed
Tokens
228
Input
164
Total output
142
Reasoning within output
git_show f012
100%
Passed
Tokens
346
Input
578
Total output
503
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
88
Input
1,398
Total output
1,469
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
106
Input
814
Total output
773
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
81
Input
1,871
Total output
1,945
Reasoning within output
merge_conflicts f004
0%
Failed
Tokens
148
Input
8,368
Total output
7,760
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
140
Input
991
Total output
1,025
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
132
Input
1,558
Total output
1,317
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
136
Input
1,128
Total output
1,142
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
108
Input
427
Total output
421
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
105
Input
954
Total output
926
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
185
Input
1,598
Total output
1,590
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
149
Input
351
Total output
253
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
240
Input
1,732
Total output
1,579
Reasoning within output
rebase f001
100%
Passed
Tokens
101
Input
1,200
Total output
1,268
Reasoning within output
rebase f002
100%
Passed
Tokens
129
Input
981
Total output
969
Reasoning within output
rebase f003
100%
Passed
Tokens
108
Input
1,299
Total output
1,300
Reasoning within output
rebase f004
0%
Failed
Tokens
161
Input
15,922
Total output
15,559
Reasoning within output
rebase f005
100%
Passed
Tokens
147
Input
1,188
Total output
1,227
Reasoning within output
rebase f006
100%
Passed
Tokens
148
Input
1,856
Total output
1,654
Reasoning within output
rebase f007
100%
Passed
Tokens
140
Input
977
Total output
901
Reasoning within output
rebase f008
100%
Passed
Tokens
121
Input
1,030
Total output
1,019
Reasoning within output
rebase f009
100%
Passed
Tokens
107
Input
1,002
Total output
964
Reasoning within output
rebase f010
100%
Passed
Tokens
214
Input
1,790
Total output
1,766
Reasoning within output
rebase f011
100%
Passed
Tokens
161
Input
2,457
Total output
2,105
Reasoning within output
rebase f012
0%
Failed
Tokens
273
Input
1,748
Total output
1,570
Reasoning within output
reflog f001
100%
Passed
Tokens
264
Input
324
Total output
188
Reasoning within output
reflog f002
100%
Passed
Tokens
249
Input
983
Total output
672
Reasoning within output
reflog f003
100%
Passed
Tokens
214
Input
9,782
Total output
7,861
Reasoning within output
reflog f004
100%
Passed
Tokens
357
Input
2,309
Total output
1,717
Reasoning within output
reflog f005
100%
Passed
Tokens
414
Input
1,430
Total output
918
Reasoning within output
reflog f006
100%
Passed
Tokens
272
Input
1,000
Total output
636
Reasoning within output
reflog f007
100%
Passed
Tokens
307
Input
4,104
Total output
2,815
Reasoning within output
reflog f008
100%
Passed
Tokens
393
Input
1,676
Total output
1,241
Reasoning within output
reflog f009
0%
Failed
Tokens
197
Input
1,006
Total output
1,006
Reasoning within output
reflog f010
0%
Failed
Tokens
295
Input
381
Total output
362
Reasoning within output
reflog f011
100%
Passed
Tokens
361
Input
4,134
Total output
2,806
Reasoning within output
reflog f012
100%
Passed
Tokens
342
Input
3,722
Total output
3,376
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
141
Input
480
Total output
454
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
311
Input
533
Total output
427
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
129
Input
812
Total output
775
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
124
Input
665
Total output
616
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
136
Input
425
Total output
374
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
188
Input
375
Total output
340
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
217
Input
639
Total output
578
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
186
Input
660
Total output
601
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
216
Input
871
Total output
810
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
133
Input
344
Total output
319
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
125
Input
853
Total output
806
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
139
Input
403
Total output
383
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
46
Input
277
Total output
255
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
108
Input
1,580
Total output
1,568
Reasoning within output
submodule_usage f003
0%
Failed
Tokens
110
Input
1,680
Total output
1,689
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
100
Input
742
Total output
782
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
53
Input
747
Total output
701
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
96
Input
1,001
Total output
1,069
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
53
Input
801
Total output
804
Reasoning within output
submodule_usage f008
33.3%
Failed
Tokens
102
Input
1,389
Total output
1,414
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
99
Input
683
Total output
721
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
107
Input
1,279
Total output
1,269
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
112
Input
307
Total output
305
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
51
Input
349
Total output
333
Reasoning within output
tag_management f001
100%
Passed
Tokens
65
Input
173
Total output
155
Reasoning within output
tag_management f002
100%
Passed
Tokens
62
Input
1,366
Total output
1,209
Reasoning within output
tag_management f003
100%
Passed
Tokens
70
Input
869
Total output
767
Reasoning within output
tag_management f004
100%
Passed
Tokens
74
Input
872
Total output
827
Reasoning within output
tag_management f005
100%
Passed
Tokens
88
Input
1,531
Total output
1,370
Reasoning within output
tag_management f006
100%
Passed
Tokens
74
Input
1,004
Total output
1
Reasoning within output
tag_management f007
100%
Passed
Tokens
68
Input
1,577
Total output
1,239
Reasoning within output
tag_management f008
100%
Passed
Tokens
73
Input
1,090
Total output
882
Reasoning within output
tag_management f009
100%
Passed
Tokens
76
Input
1,364
Total output
1,213
Reasoning within output
tag_management f010
100%
Passed
Tokens
55
Input
296
Total output
258
Reasoning within output
tag_management f011
100%
Passed
Tokens
58
Input
703
Total output
714
Reasoning within output
tag_management f012
100%
Passed
Tokens
94
Input
1,965
Total output
1,715
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
147
Input
1,163
Total output
1,095
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
156
Input
1,603
Total output
1,576
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
228
Input
347
Total output
343
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
231
Input
267
Total output
265
Reasoning within output
worktree_usage f005
33.3%
Failed
Tokens
142
Input
145
Total output
141
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
142
Input
1,330
Total output
1,224
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
149
Input
1,239
Total output
1,137
Reasoning within output
worktree_usage f008
50%
Failed
Tokens
173
Input
2,044
Total output
1,864
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
262
Input
753
Total output
1
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
240
Input
752
Total output
726
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
228
Input
492
Total output
511
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
141
Input
183
Total output
173
Reasoning within output