Qwen / qwen3.6-27b
high
93.1%
190 / 204 fixtures · 1 run(s)
41,305 input / 241,441 total output / 179,668 reasoning within output tokens $0.66387440
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-16.7%
Text: 93.1% →
JSON: 76.5%
+7
Gained
JSON pass / text fail
−41
Lost
Text pass / JSON fail
149
Unchanged Pass
Both pass
7
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| reflog | 100% | 50% | -50% |
| git_clean | 91.7% | 58.3% | -33.3% |
| branch_cleanup | 100% | 75% | -25% |
| cherry_pick | 83.3% | 58.3% | -25% |
| stash_recovery | 100% | 75% | -25% |
| tag_management | 100% | 75% | -25% |
| blame_forensics | 100% | 83.3% | -16.7% |
| commit_squash | 100% | 83.3% | -16.7% |
| git_grep | 91.7% | 75% | -16.7% |
| git_log_format | 100% | 83.3% | -16.7% |
| git_show | 100% | 83.3% | -16.7% |
| rebase | 83.3% | 66.7% | -16.7% |
| submodule_usage | 91.7% | 83.3% | -8.3% |
| merge_conflicts | 66.7% | 75% | + 8.3% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| worktree_usage | 75% | 75% | + 0% |
Changed Fixtures (48)
f006 -loss f012 -loss f003 -loss f009 -loss f011 -loss f003 -loss f005 -loss f011 -loss f001 -loss f002 -loss f001 -loss f003 -loss f004 -loss f005 -loss f010 -loss f011 +gain f004 +gain f006 -loss f008 -loss f011 -loss f001 -loss f002 -loss f009 -loss f010 -loss f001 +gain f005 -loss f006 +gain f002 -loss f011 -loss f002 -loss f003 -loss f004 -loss f006 -loss f007 -loss f012 -loss f001 -loss f002 -loss f007 -loss f003 +gain f006 -loss f008 -loss f004 -loss f011 -loss f012 -loss f002 +gain f004 -loss f006 -loss f008 +gain
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
259
Input
1,100
Total output
1,047
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
258
Input
439
Total output
382
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
281
Input
763
Total output
752
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
208
Input
1,525
Total output
1,538
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
273
Input
2,294
Total output
2,260
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
239
Input
1,424
Total output
1,256
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
223
Input
848
Total output
719
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
258
Input
1,195
Total output
1,092
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
212
Input
489
Total output
486
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
442
Input
1,034
Total output
1
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
259
Input
371
Total output
336
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
151
Input
501
Total output
1
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
112
Input
828
Total output
728
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
126
Input
861
Total output
851
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
103
Input
837
Total output
776
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
143
Input
1,285
Total output
1,275
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
114
Input
357
Total output
321
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
143
Input
839
Total output
825
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
112
Input
855
Total output
813
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
128
Input
1,002
Total output
1
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
90
Input
315
Total output
307
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
123
Input
419
Total output
356
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
75
Input
345
Total output
339
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
168
Input
1,022
Total output
1,007
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
99
Input
1,442
Total output
1,550
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
119
Input
1,138
Total output
1,102
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
94
Input
1,119
Total output
1,172
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
161
Input
7,882
Total output
1
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
156
Input
912
Total output
943
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
147
Input
1,645
Total output
1,422
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
135
Input
1,165
Total output
1,127
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
128
Input
822
Total output
832
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
112
Input
684
Total output
688
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
226
Input
1,645
Total output
1,611
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
172
Input
1,273
Total output
1,087
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
281
Input
1,869
Total output
1,717
Reasoning within output
commit_messages f001
95%
Passed
Tokens
117
Input
987
Total output
897
Reasoning within output
commit_messages f002
81.7%
Passed
Tokens
233
Input
1,476
Total output
1,281
Reasoning within output
commit_messages f003
95.7%
Passed
Tokens
88
Input
1,312
Total output
1,299
Reasoning within output
commit_messages f004
93.3%
Passed
Tokens
125
Input
556
Total output
548
Reasoning within output
commit_messages f005
89.3%
Passed
Tokens
109
Input
1,424
Total output
1
Reasoning within output
commit_messages f006
93.3%
Passed
Tokens
156
Input
1,038
Total output
912
Reasoning within output
commit_messages f007
89.7%
Passed
Tokens
197
Input
296
Total output
270
Reasoning within output
commit_messages f008
93.3%
Passed
Tokens
81
Input
1,111
Total output
1,102
Reasoning within output
commit_messages f009
88.3%
Passed
Tokens
135
Input
1,966
Total output
1,691
Reasoning within output
commit_messages f010
90.7%
Passed
Tokens
305
Input
1,300
Total output
1,152
Reasoning within output
commit_messages f011
64.3%
Passed
Tokens
154
Input
2,729
Total output
1,791
Reasoning within output
commit_messages f012
91.3%
Passed
Tokens
135
Input
1,070
Total output
1,023
Reasoning within output
commit_squash f001
100%
Passed
Tokens
149
Input
951
Total output
870
Reasoning within output
commit_squash f002
100%
Passed
Tokens
126
Input
1,018
Total output
941
Reasoning within output
commit_squash f003
100%
Passed
Tokens
137
Input
1,079
Total output
991
Reasoning within output
commit_squash f004
100%
Passed
Tokens
123
Input
1,502
Total output
1,469
Reasoning within output
commit_squash f005
100%
Passed
Tokens
122
Input
1,567
Total output
1,589
Reasoning within output
commit_squash f006
100%
Passed
Tokens
106
Input
971
Total output
941
Reasoning within output
commit_squash f007
100%
Passed
Tokens
111
Input
1,026
Total output
1,009
Reasoning within output
commit_squash f008
100%
Passed
Tokens
124
Input
970
Total output
864
Reasoning within output
commit_squash f009
100%
Passed
Tokens
116
Input
1,101
Total output
1,028
Reasoning within output
commit_squash f010
100%
Passed
Tokens
130
Input
830
Total output
765
Reasoning within output
commit_squash f011
100%
Passed
Tokens
136
Input
696
Total output
616
Reasoning within output
commit_squash f012
100%
Passed
Tokens
141
Input
1,173
Total output
1
Reasoning within output
git_bisect f001
100%
Passed
Tokens
190
Input
364
Total output
275
Reasoning within output
git_bisect f002
100%
Passed
Tokens
222
Input
1,382
Total output
1,091
Reasoning within output
git_bisect f003
100%
Passed
Tokens
216
Input
568
Total output
408
Reasoning within output
git_bisect f004
100%
Passed
Tokens
214
Input
740
Total output
580
Reasoning within output
git_bisect f005
100%
Passed
Tokens
218
Input
962
Total output
753
Reasoning within output
git_bisect f006
100%
Passed
Tokens
244
Input
470
Total output
357
Reasoning within output
git_bisect f007
100%
Passed
Tokens
218
Input
688
Total output
506
Reasoning within output
git_bisect f008
100%
Passed
Tokens
224
Input
652
Total output
523
Reasoning within output
git_bisect f009
100%
Passed
Tokens
218
Input
1,333
Total output
1
Reasoning within output
git_bisect f010
100%
Passed
Tokens
220
Input
432
Total output
333
Reasoning within output
git_bisect f011
100%
Passed
Tokens
224
Input
656
Total output
481
Reasoning within output
git_bisect f012
100%
Passed
Tokens
246
Input
449
Total output
365
Reasoning within output
git_clean f001
100%
Passed
Tokens
55
Input
962
Total output
938
Reasoning within output
git_clean f002
100%
Passed
Tokens
66
Input
996
Total output
1
Reasoning within output
git_clean f003
100%
Passed
Tokens
65
Input
1,457
Total output
1
Reasoning within output
git_clean f004
100%
Passed
Tokens
62
Input
2,134
Total output
1,926
Reasoning within output
git_clean f005
100%
Passed
Tokens
54
Input
1,049
Total output
1,040
Reasoning within output
git_clean f006
100%
Passed
Tokens
79
Input
1,547
Total output
1,402
Reasoning within output
git_clean f007
100%
Passed
Tokens
70
Input
1,879
Total output
1,742
Reasoning within output
git_clean f008
100%
Passed
Tokens
82
Input
820
Total output
778
Reasoning within output
git_clean f009
100%
Passed
Tokens
73
Input
1,344
Total output
1,318
Reasoning within output
git_clean f010
100%
Passed
Tokens
68
Input
907
Total output
898
Reasoning within output
git_clean f011
60%
Failed
Tokens
66
Input
918
Total output
905
Reasoning within output
git_clean f012
100%
Passed
Tokens
68
Input
1,521
Total output
1,383
Reasoning within output
git_grep f001
100%
Passed
Tokens
54
Input
533
Total output
526
Reasoning within output
git_grep f002
100%
Passed
Tokens
69
Input
243
Total output
219
Reasoning within output
git_grep f003
100%
Passed
Tokens
89
Input
443
Total output
437
Reasoning within output
git_grep f004
0%
Failed
Tokens
78
Input
1,066
Total output
1
Reasoning within output
git_grep f005
100%
Passed
Tokens
119
Input
826
Total output
766
Reasoning within output
git_grep f006
100%
Passed
Tokens
43
Input
758
Total output
1
Reasoning within output
git_grep f007
100%
Passed
Tokens
171
Input
2,039
Total output
1
Reasoning within output
git_grep f008
100%
Passed
Tokens
60
Input
295
Total output
294
Reasoning within output
git_grep f009
100%
Passed
Tokens
56
Input
261
Total output
1
Reasoning within output
git_grep f010
100%
Passed
Tokens
66
Input
342
Total output
1
Reasoning within output
git_grep f011
100%
Passed
Tokens
114
Input
412
Total output
1
Reasoning within output
git_grep f012
100%
Passed
Tokens
67
Input
639
Total output
626
Reasoning within output
git_log_format f001
100%
Passed
Tokens
897
Input
443
Total output
406
Reasoning within output
git_log_format f002
100%
Passed
Tokens
904
Input
555
Total output
603
Reasoning within output
git_log_format f003
100%
Passed
Tokens
733
Input
843
Total output
807
Reasoning within output
git_log_format f004
100%
Passed
Tokens
895
Input
358
Total output
264
Reasoning within output
git_log_format f005
100%
Passed
Tokens
739
Input
1,480
Total output
1,261
Reasoning within output
git_log_format f006
100%
Passed
Tokens
913
Input
591
Total output
1
Reasoning within output
git_log_format f007
100%
Passed
Tokens
921
Input
182
Total output
148
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,226
Input
374
Total output
319
Reasoning within output
git_log_format f009
100%
Passed
Tokens
737
Input
194
Total output
188
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,415
Input
150
Total output
133
Reasoning within output
git_log_format f011
100%
Passed
Tokens
437
Input
382
Total output
325
Reasoning within output
git_log_format f012
100%
Passed
Tokens
407
Input
146
Total output
133
Reasoning within output
git_show f001
100%
Passed
Tokens
198
Input
319
Total output
274
Reasoning within output
git_show f002
100%
Passed
Tokens
201
Input
2,010
Total output
2,041
Reasoning within output
git_show f003
100%
Passed
Tokens
699
Input
561
Total output
473
Reasoning within output
git_show f004
100%
Passed
Tokens
466
Input
255
Total output
220
Reasoning within output
git_show f005
100%
Passed
Tokens
205
Input
917
Total output
1
Reasoning within output
git_show f006
100%
Passed
Tokens
214
Input
270
Total output
221
Reasoning within output
git_show f007
100%
Passed
Tokens
204
Input
197
Total output
153
Reasoning within output
git_show f008
100%
Passed
Tokens
208
Input
223
Total output
1
Reasoning within output
git_show f009
100%
Passed
Tokens
321
Input
650
Total output
525
Reasoning within output
git_show f010
100%
Passed
Tokens
201
Input
503
Total output
477
Reasoning within output
git_show f011
100%
Passed
Tokens
228
Input
487
Total output
499
Reasoning within output
git_show f012
100%
Passed
Tokens
347
Input
229
Total output
210
Reasoning within output
merge_conflicts f001
0%
Failed
Tokens
88
Input
1,928
Total output
1,988
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
106
Input
998
Total output
911
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
81
Input
1,143
Total output
1,160
Reasoning within output
merge_conflicts f004
0%
Failed
Tokens
148
Input
2,917
Total output
2,693
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
140
Input
1,475
Total output
1,512
Reasoning within output
merge_conflicts f006
0%
Failed
Tokens
132
Input
2,187
Total output
1,845
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
136
Input
1,155
Total output
1,124
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
108
Input
923
Total output
1
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
105
Input
1,157
Total output
1,147
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
185
Input
1,264
Total output
1,229
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
149
Input
907
Total output
839
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
240
Input
1,845
Total output
1,677
Reasoning within output
rebase f001
0%
Failed
Tokens
100
Input
2,673
Total output
2,664
Reasoning within output
rebase f002
100%
Passed
Tokens
129
Input
902
Total output
841
Reasoning within output
rebase f003
100%
Passed
Tokens
107
Input
1,242
Total output
1,277
Reasoning within output
rebase f004
100%
Passed
Tokens
161
Input
1,154
Total output
1,087
Reasoning within output
rebase f005
100%
Passed
Tokens
148
Input
1,147
Total output
1,194
Reasoning within output
rebase f006
100%
Passed
Tokens
148
Input
1,692
Total output
1,461
Reasoning within output
rebase f007
100%
Passed
Tokens
139
Input
1,122
Total output
1,096
Reasoning within output
rebase f008
100%
Passed
Tokens
123
Input
1,036
Total output
1,018
Reasoning within output
rebase f009
100%
Passed
Tokens
107
Input
1,294
Total output
1
Reasoning within output
rebase f010
100%
Passed
Tokens
218
Input
1,437
Total output
1
Reasoning within output
rebase f011
100%
Passed
Tokens
161
Input
1,391
Total output
1,205
Reasoning within output
rebase f012
0%
Failed
Tokens
275
Input
2,455
Total output
1
Reasoning within output
reflog f001
100%
Passed
Tokens
256
Input
1,488
Total output
968
Reasoning within output
reflog f002
100%
Passed
Tokens
252
Input
5,487
Total output
3,725
Reasoning within output
reflog f003
100%
Passed
Tokens
223
Input
1,293
Total output
926
Reasoning within output
reflog f004
100%
Passed
Tokens
363
Input
3,230
Total output
3,066
Reasoning within output
reflog f005
100%
Passed
Tokens
401
Input
4,161
Total output
3,182
Reasoning within output
reflog f006
100%
Passed
Tokens
277
Input
3,233
Total output
2,393
Reasoning within output
reflog f007
100%
Passed
Tokens
320
Input
1,568
Total output
929
Reasoning within output
reflog f008
100%
Passed
Tokens
397
Input
4,752
Total output
1
Reasoning within output
reflog f009
100%
Passed
Tokens
345
Input
2,347
Total output
1,633
Reasoning within output
reflog f010
100%
Passed
Tokens
308
Input
4,214
Total output
3,803
Reasoning within output
reflog f011
100%
Passed
Tokens
355
Input
4,064
Total output
2,714
Reasoning within output
reflog f012
100%
Passed
Tokens
334
Input
5,165
Total output
4,141
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
140
Input
309
Total output
293
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
311
Input
957
Total output
946
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
129
Input
340
Total output
1
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
124
Input
381
Total output
369
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
136
Input
478
Total output
446
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
188
Input
336
Total output
1
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
219
Input
393
Total output
323
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
186
Input
374
Total output
349
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
216
Input
667
Total output
627
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
133
Input
356
Total output
1
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
127
Input
138
Total output
134
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
139
Input
327
Total output
1
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
46
Input
767
Total output
1
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
108
Input
1,433
Total output
1,510
Reasoning within output
submodule_usage f003
75%
Failed
Tokens
113
Input
2,952
Total output
2,766
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
101
Input
616
Total output
677
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
53
Input
2,427
Total output
2,372
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
97
Input
1,578
Total output
1,677
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
53
Input
930
Total output
931
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
106
Input
1,365
Total output
1,384
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
102
Input
1,151
Total output
1
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
108
Input
1,286
Total output
1,327
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
110
Input
624
Total output
624
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
51
Input
992
Total output
1
Reasoning within output
tag_management f001
100%
Passed
Tokens
66
Input
733
Total output
668
Reasoning within output
tag_management f002
100%
Passed
Tokens
61
Input
1,860
Total output
1,577
Reasoning within output
tag_management f003
100%
Passed
Tokens
67
Input
1,244
Total output
1,138
Reasoning within output
tag_management f004
100%
Passed
Tokens
77
Input
503
Total output
488
Reasoning within output
tag_management f005
100%
Passed
Tokens
87
Input
1,136
Total output
967
Reasoning within output
tag_management f006
100%
Passed
Tokens
74
Input
1,172
Total output
947
Reasoning within output
tag_management f007
100%
Passed
Tokens
68
Input
2,502
Total output
1,878
Reasoning within output
tag_management f008
100%
Passed
Tokens
74
Input
2,262
Total output
1,732
Reasoning within output
tag_management f009
100%
Passed
Tokens
76
Input
1,506
Total output
1,392
Reasoning within output
tag_management f010
100%
Passed
Tokens
54
Input
339
Total output
319
Reasoning within output
tag_management f011
100%
Passed
Tokens
57
Input
1,033
Total output
1,015
Reasoning within output
tag_management f012
100%
Passed
Tokens
93
Input
1,865
Total output
1
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
149
Input
250
Total output
217
Reasoning within output
worktree_usage f002
0%
Failed
Tokens
160
Input
1,557
Total output
1,411
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
235
Input
925
Total output
894
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
233
Input
573
Total output
584
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
141
Input
820
Total output
1
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
144
Input
564
Total output
545
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
143
Input
1,102
Total output
995
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
169
Input
2,452
Total output
2,181
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
257
Input
871
Total output
918
Reasoning within output
worktree_usage f010
0%
Failed
Tokens
234
Input
1,274
Total output
1,210
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
234
Input
977
Total output
860
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
141
Input
1,199
Total output
1,181
Reasoning within output