Qwen / qwen3.6-35b-a3b
low
95.1%
194 / 204 fixtures · 1 run(s)
41,299 input / 216,383 total output / 197,528 reasoning within output tokens $0.24623040
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-2.9%
Text: 95.1% →
JSON: 92.2%
+2
Gained
JSON pass / text fail
−8
Lost
Text pass / JSON fail
186
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% | 83.3% | -16.7% |
| worktree_usage | 91.7% | 75% | -16.7% |
| cherry_pick | 91.7% | 83.3% | -8.3% |
| merge_conflicts | 91.7% | 83.3% | -8.3% |
| git_grep | 91.7% | 100% | + 8.3% |
| tag_management | 100% | 91.7% | -8.3% |
| blame_forensics | 100% | 100% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| commit_squash | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_clean | 83.3% | 83.3% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 91.7% | 91.7% | + 0% |
| rebase | 83.3% | 83.3% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 91.7% | 91.7% | + 0% |
Changed Fixtures (10)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
255
Input
1,343
Total output
1,319
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
243
Input
1,396
Total output
1,237
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
279
Input
248
Total output
198
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
207
Input
855
Total output
873
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
275
Input
2,189
Total output
1,863
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
246
Input
1,216
Total output
1,043
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
226
Input
887
Total output
792
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
256
Input
686
Total output
677
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
212
Input
960
Total output
855
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
450
Input
837
Total output
735
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
258
Input
844
Total output
787
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
157
Input
1,351
Total output
1,198
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
110
Input
944
Total output
900
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
122
Input
736
Total output
671
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
103
Input
1,037
Total output
1,023
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
139
Input
773
Total output
763
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
114
Input
942
Total output
934
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
141
Input
796
Total output
704
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
112
Input
388
Total output
354
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
133
Input
747
Total output
664
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
88
Input
1,132
Total output
1,151
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
122
Input
417
Total output
334
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
76
Input
561
Total output
545
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
169
Input
747
Total output
705
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
101
Input
3,572
Total output
3,563
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
119
Input
956
Total output
874
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
93
Input
1,025
Total output
1,091
Reasoning within output
cherry_pick f004
100%
Passed
Tokens
164
Input
2,395
Total output
2,314
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
156
Input
1,003
Total output
1,050
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
146
Input
985
Total output
899
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
138
Input
1,029
Total output
912
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
126
Input
275
Total output
261
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
111
Input
890
Total output
880
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
224
Input
1,539
Total output
1,488
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
172
Input
573
Total output
469
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
277
Input
1,501
Total output
1,386
Reasoning within output
commit_messages f001
93.3%
Passed
Tokens
117
Input
986
Total output
871
Reasoning within output
commit_messages f002
88%
Passed
Tokens
233
Input
1,192
Total output
1,180
Reasoning within output
commit_messages f003
89.3%
Passed
Tokens
88
Input
703
Total output
690
Reasoning within output
commit_messages f004
91.7%
Passed
Tokens
125
Input
738
Total output
660
Reasoning within output
commit_messages f005
88.3%
Passed
Tokens
109
Input
1,336
Total output
1,327
Reasoning within output
commit_messages f006
93.7%
Passed
Tokens
156
Input
1,696
Total output
1,429
Reasoning within output
commit_messages f007
93.3%
Passed
Tokens
197
Input
1,234
Total output
1,223
Reasoning within output
commit_messages f008
91.7%
Passed
Tokens
81
Input
1,086
Total output
940
Reasoning within output
commit_messages f009
86.7%
Passed
Tokens
135
Input
989
Total output
820
Reasoning within output
commit_messages f010
91%
Passed
Tokens
305
Input
1,012
Total output
1,001
Reasoning within output
commit_messages f011
71.7%
Passed
Tokens
154
Input
2,242
Total output
1,794
Reasoning within output
commit_messages f012
90.7%
Passed
Tokens
135
Input
1,239
Total output
1,115
Reasoning within output
commit_squash f001
100%
Passed
Tokens
147
Input
974
Total output
957
Reasoning within output
commit_squash f002
100%
Passed
Tokens
123
Input
559
Total output
546
Reasoning within output
commit_squash f003
100%
Passed
Tokens
136
Input
2,292
Total output
2,200
Reasoning within output
commit_squash f004
100%
Passed
Tokens
121
Input
1,420
Total output
1,404
Reasoning within output
commit_squash f005
100%
Passed
Tokens
121
Input
859
Total output
857
Reasoning within output
commit_squash f006
100%
Passed
Tokens
107
Input
1,048
Total output
983
Reasoning within output
commit_squash f007
100%
Passed
Tokens
108
Input
1,078
Total output
1,061
Reasoning within output
commit_squash f008
100%
Passed
Tokens
121
Input
942
Total output
884
Reasoning within output
commit_squash f009
100%
Passed
Tokens
114
Input
1,057
Total output
981
Reasoning within output
commit_squash f010
100%
Passed
Tokens
128
Input
1,060
Total output
1,040
Reasoning within output
commit_squash f011
100%
Passed
Tokens
137
Input
546
Total output
486
Reasoning within output
commit_squash f012
100%
Passed
Tokens
139
Input
1,239
Total output
1,119
Reasoning within output
git_bisect f001
100%
Passed
Tokens
192
Input
299
Total output
239
Reasoning within output
git_bisect f002
100%
Passed
Tokens
212
Input
309
Total output
268
Reasoning within output
git_bisect f003
100%
Passed
Tokens
222
Input
345
Total output
269
Reasoning within output
git_bisect f004
100%
Passed
Tokens
226
Input
624
Total output
462
Reasoning within output
git_bisect f005
100%
Passed
Tokens
224
Input
637
Total output
485
Reasoning within output
git_bisect f006
100%
Passed
Tokens
252
Input
579
Total output
450
Reasoning within output
git_bisect f007
100%
Passed
Tokens
222
Input
423
Total output
309
Reasoning within output
git_bisect f008
100%
Passed
Tokens
216
Input
647
Total output
485
Reasoning within output
git_bisect f009
100%
Passed
Tokens
218
Input
360
Total output
298
Reasoning within output
git_bisect f010
100%
Passed
Tokens
220
Input
418
Total output
408
Reasoning within output
git_bisect f011
100%
Passed
Tokens
216
Input
398
Total output
387
Reasoning within output
git_bisect f012
100%
Passed
Tokens
252
Input
408
Total output
298
Reasoning within output
git_clean f001
100%
Passed
Tokens
55
Input
1,048
Total output
1,004
Reasoning within output
git_clean f002
100%
Passed
Tokens
66
Input
385
Total output
377
Reasoning within output
git_clean f003
100%
Passed
Tokens
65
Input
948
Total output
941
Reasoning within output
git_clean f004
33.3%
Failed
Tokens
62
Input
1,307
Total output
1,282
Reasoning within output
git_clean f005
100%
Passed
Tokens
54
Input
2,196
Total output
2,161
Reasoning within output
git_clean f006
100%
Passed
Tokens
79
Input
1,391
Total output
1,287
Reasoning within output
git_clean f007
100%
Passed
Tokens
70
Input
1,826
Total output
1,813
Reasoning within output
git_clean f008
100%
Passed
Tokens
82
Input
1,095
Total output
1,036
Reasoning within output
git_clean f009
100%
Passed
Tokens
73
Input
1,404
Total output
1,402
Reasoning within output
git_clean f010
100%
Passed
Tokens
68
Input
1,009
Total output
933
Reasoning within output
git_clean f011
60%
Failed
Tokens
66
Input
1,667
Total output
1,597
Reasoning within output
git_clean f012
100%
Passed
Tokens
68
Input
1,408
Total output
1,285
Reasoning within output
git_grep f001
100%
Passed
Tokens
54
Input
618
Total output
614
Reasoning within output
git_grep f002
100%
Passed
Tokens
69
Input
137
Total output
127
Reasoning within output
git_grep f003
100%
Passed
Tokens
89
Input
307
Total output
292
Reasoning within output
git_grep f004
0%
Failed
Tokens
78
Input
1,485
Total output
1,473
Reasoning within output
git_grep f005
100%
Passed
Tokens
119
Input
254
Total output
226
Reasoning within output
git_grep f006
100%
Passed
Tokens
43
Input
842
Total output
871
Reasoning within output
git_grep f007
100%
Passed
Tokens
171
Input
1,832
Total output
1,498
Reasoning within output
git_grep f008
100%
Passed
Tokens
60
Input
446
Total output
419
Reasoning within output
git_grep f009
100%
Passed
Tokens
56
Input
211
Total output
203
Reasoning within output
git_grep f010
100%
Passed
Tokens
66
Input
269
Total output
262
Reasoning within output
git_grep f011
100%
Passed
Tokens
114
Input
311
Total output
284
Reasoning within output
git_grep f012
100%
Passed
Tokens
67
Input
309
Total output
281
Reasoning within output
git_log_format f001
100%
Passed
Tokens
914
Input
221
Total output
226
Reasoning within output
git_log_format f002
100%
Passed
Tokens
901
Input
807
Total output
846
Reasoning within output
git_log_format f003
100%
Passed
Tokens
730
Input
296
Total output
263
Reasoning within output
git_log_format f004
100%
Passed
Tokens
890
Input
394
Total output
259
Reasoning within output
git_log_format f005
100%
Passed
Tokens
739
Input
816
Total output
806
Reasoning within output
git_log_format f006
100%
Passed
Tokens
913
Input
679
Total output
405
Reasoning within output
git_log_format f007
100%
Passed
Tokens
935
Input
169
Total output
158
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,200
Input
218
Total output
179
Reasoning within output
git_log_format f009
100%
Passed
Tokens
740
Input
346
Total output
264
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,412
Input
189
Total output
178
Reasoning within output
git_log_format f011
100%
Passed
Tokens
435
Input
183
Total output
171
Reasoning within output
git_log_format f012
100%
Passed
Tokens
408
Input
250
Total output
202
Reasoning within output
git_show f001
100%
Passed
Tokens
201
Input
228
Total output
220
Reasoning within output
git_show f002
0%
Failed
Tokens
203
Input
1,685
Total output
1,679
Reasoning within output
git_show f003
100%
Passed
Tokens
685
Input
521
Total output
439
Reasoning within output
git_show f004
100%
Passed
Tokens
470
Input
284
Total output
250
Reasoning within output
git_show f005
100%
Passed
Tokens
206
Input
960
Total output
942
Reasoning within output
git_show f006
100%
Passed
Tokens
215
Input
313
Total output
307
Reasoning within output
git_show f007
100%
Passed
Tokens
204
Input
179
Total output
161
Reasoning within output
git_show f008
100%
Passed
Tokens
212
Input
339
Total output
215
Reasoning within output
git_show f009
100%
Passed
Tokens
325
Input
446
Total output
440
Reasoning within output
git_show f010
100%
Passed
Tokens
201
Input
313
Total output
299
Reasoning within output
git_show f011
100%
Passed
Tokens
226
Input
128
Total output
128
Reasoning within output
git_show f012
100%
Passed
Tokens
348
Input
577
Total output
497
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
88
Input
2,287
Total output
2,278
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
106
Input
1,722
Total output
1,710
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
81
Input
1,281
Total output
1,314
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
148
Input
3,314
Total output
3,284
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
140
Input
1,190
Total output
1,212
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
132
Input
1,330
Total output
1,130
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
136
Input
1,129
Total output
1,097
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
108
Input
788
Total output
803
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
105
Input
1,138
Total output
1,128
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
185
Input
1,790
Total output
1,757
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
149
Input
470
Total output
371
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
240
Input
7,556
Total output
7,050
Reasoning within output
rebase f001
100%
Passed
Tokens
100
Input
1,702
Total output
1,693
Reasoning within output
rebase f002
100%
Passed
Tokens
129
Input
981
Total output
934
Reasoning within output
rebase f003
100%
Passed
Tokens
108
Input
1,159
Total output
1,222
Reasoning within output
rebase f004
0%
Failed
Tokens
162
Input
2,574
Total output
2,367
Reasoning within output
rebase f005
100%
Passed
Tokens
145
Input
1,049
Total output
1,066
Reasoning within output
rebase f006
100%
Passed
Tokens
148
Input
1,598
Total output
1,380
Reasoning within output
rebase f007
100%
Passed
Tokens
141
Input
1,135
Total output
1,085
Reasoning within output
rebase f008
100%
Passed
Tokens
123
Input
939
Total output
918
Reasoning within output
rebase f009
100%
Passed
Tokens
105
Input
1,122
Total output
1,106
Reasoning within output
rebase f010
100%
Passed
Tokens
218
Input
2,148
Total output
2,145
Reasoning within output
rebase f011
100%
Passed
Tokens
159
Input
1,536
Total output
1,316
Reasoning within output
rebase f012
0%
Failed
Tokens
275
Input
1,866
Total output
1,818
Reasoning within output
reflog f001
100%
Passed
Tokens
259
Input
1,361
Total output
1,319
Reasoning within output
reflog f002
100%
Passed
Tokens
253
Input
968
Total output
543
Reasoning within output
reflog f003
100%
Passed
Tokens
219
Input
1,126
Total output
906
Reasoning within output
reflog f004
100%
Passed
Tokens
360
Input
3,430
Total output
2,558
Reasoning within output
reflog f005
100%
Passed
Tokens
408
Input
1,517
Total output
1,008
Reasoning within output
reflog f006
100%
Passed
Tokens
275
Input
924
Total output
523
Reasoning within output
reflog f007
100%
Passed
Tokens
303
Input
839
Total output
732
Reasoning within output
reflog f008
100%
Passed
Tokens
400
Input
8,297
Total output
6,510
Reasoning within output
reflog f009
100%
Passed
Tokens
359
Input
1,400
Total output
878
Reasoning within output
reflog f010
100%
Passed
Tokens
309
Input
1,304
Total output
704
Reasoning within output
reflog f011
100%
Passed
Tokens
355
Input
2,726
Total output
1,859
Reasoning within output
reflog f012
100%
Passed
Tokens
362
Input
3,041
Total output
2,128
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
139
Input
796
Total output
735
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
305
Input
844
Total output
676
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
129
Input
597
Total output
567
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
124
Input
864
Total output
853
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
134
Input
707
Total output
687
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
188
Input
307
Total output
287
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
219
Input
484
Total output
375
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
186
Input
636
Total output
611
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
216
Input
474
Total output
448
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
133
Input
441
Total output
390
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
128
Input
786
Total output
755
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
139
Input
322
Total output
298
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
46
Input
298
Total output
280
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
105
Input
1,188
Total output
1,242
Reasoning within output
submodule_usage f003
75%
Failed
Tokens
113
Input
1,972
Total output
1,937
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
100
Input
628
Total output
620
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
53
Input
1,564
Total output
1,551
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
95
Input
1,396
Total output
1,450
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
53
Input
407
Total output
385
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
103
Input
1,339
Total output
1,410
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
102
Input
491
Total output
483
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
106
Input
1,265
Total output
1,255
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
110
Input
637
Total output
628
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
51
Input
526
Total output
504
Reasoning within output
tag_management f001
100%
Passed
Tokens
64
Input
322
Total output
311
Reasoning within output
tag_management f002
100%
Passed
Tokens
63
Input
1,633
Total output
1,347
Reasoning within output
tag_management f003
100%
Passed
Tokens
68
Input
911
Total output
797
Reasoning within output
tag_management f004
100%
Passed
Tokens
77
Input
1,029
Total output
918
Reasoning within output
tag_management f005
100%
Passed
Tokens
90
Input
848
Total output
765
Reasoning within output
tag_management f006
100%
Passed
Tokens
73
Input
372
Total output
298
Reasoning within output
tag_management f007
100%
Passed
Tokens
69
Input
1,911
Total output
1,521
Reasoning within output
tag_management f008
100%
Passed
Tokens
73
Input
1,507
Total output
1,192
Reasoning within output
tag_management f009
100%
Passed
Tokens
75
Input
914
Total output
808
Reasoning within output
tag_management f010
100%
Passed
Tokens
55
Input
239
Total output
215
Reasoning within output
tag_management f011
100%
Passed
Tokens
58
Input
901
Total output
872
Reasoning within output
tag_management f012
100%
Passed
Tokens
93
Input
1,287
Total output
1,159
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
155
Input
1,074
Total output
1,055
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
152
Input
1,242
Total output
1,247
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
229
Input
1,034
Total output
1,003
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
231
Input
690
Total output
705
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
144
Input
359
Total output
335
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
141
Input
1,039
Total output
1,022
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
149
Input
892
Total output
876
Reasoning within output
worktree_usage f008
50%
Failed
Tokens
170
Input
2,909
Total output
2,861
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
261
Input
401
Total output
392
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
235
Input
1,314
Total output
1,233
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
224
Input
733
Total output
672
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
144
Input
1,121
Total output
1,005
Reasoning within output