Qwen / qwen3.6-27b
xhigh
94.6%
193 / 204 fixtures · 1 run(s)
41,270 input / 232,096 total output / 183,613 reasoning within output tokens $0.63475452
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-17.2%
Text: 94.6% →
JSON: 77.5%
+3
Gained
JSON pass / text fail
−38
Lost
Text pass / JSON fail
155
Unchanged Pass
Both pass
8
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| reflog | 100% | 16.7% | -83.3% |
| branch_cleanup | 100% | 66.7% | -33.3% |
| blame_forensics | 100% | 75% | -25% |
| commit_squash | 100% | 75% | -25% |
| merge_conflicts | 91.7% | 66.7% | -25% |
| tag_management | 100% | 75% | -25% |
| commit_messages | 100% | 83.3% | -16.7% |
| git_bisect | 100% | 83.3% | -16.7% |
| git_grep | 91.7% | 75% | -16.7% |
| cherry_pick | 83.3% | 75% | -8.3% |
| git_log_format | 100% | 91.7% | -8.3% |
| rebase | 75% | 83.3% | + 8.3% |
| stash_recovery | 100% | 91.7% | -8.3% |
| worktree_usage | 83.3% | 75% | -8.3% |
| git_clean | 91.7% | 91.7% | + 0% |
| git_show | 91.7% | 91.7% | + 0% |
| submodule_usage | 100% | 100% | + 0% |
Changed Fixtures (41)
f002 -loss f004 -loss f005 -loss f001 -loss f003 -loss f009 -loss f011 -loss f011 -loss f007 -loss f011 -loss f007 -loss f011 -loss f012 -loss f004 -loss f012 -loss f004 -loss f011 +gain f005 -loss f011 -loss f012 -loss f002 +gain f003 -loss f003 -loss f004 -loss f010 -loss f004 +gain f001 -loss f002 -loss f003 -loss f004 -loss f005 -loss f008 -loss f009 -loss f010 -loss f011 -loss f012 -loss f005 -loss f002 -loss f005 -loss f010 -loss f004 -loss
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
256
Input
1,219
Total output
1,142
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
256
Input
422
Total output
1
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
287
Input
877
Total output
754
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
209
Input
920
Total output
910
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
268
Input
1,548
Total output
1
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
247
Input
1,228
Total output
1,085
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
223
Input
544
Total output
428
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
262
Input
1,242
Total output
1,170
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
209
Input
493
Total output
414
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
447
Input
1,062
Total output
1
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
258
Input
573
Total output
436
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
155
Input
1,148
Total output
1,073
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
106
Input
656
Total output
648
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
124
Input
851
Total output
801
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
103
Input
769
Total output
735
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
137
Input
409
Total output
371
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
113
Input
719
Total output
697
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
138
Input
1,018
Total output
928
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
115
Input
683
Total output
667
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
135
Input
1,031
Total output
960
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
90
Input
1,170
Total output
1,185
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
122
Input
870
Total output
790
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
75
Input
647
Total output
636
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
165
Input
1,172
Total output
1,110
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
101
Input
1,410
Total output
1,529
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
120
Input
1,417
Total output
1,308
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
92
Input
803
Total output
794
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
163
Input
1,703
Total output
1,650
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
153
Input
900
Total output
877
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
147
Input
1,727
Total output
1,493
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
137
Input
1,062
Total output
1,033
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
126
Input
524
Total output
509
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
111
Input
603
Total output
600
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
222
Input
1,505
Total output
1,561
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
171
Input
1,106
Total output
985
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
279
Input
1,600
Total output
1,460
Reasoning within output
commit_messages f001
94%
Passed
Tokens
117
Input
3,415
Total output
3,217
Reasoning within output
commit_messages f002
91%
Passed
Tokens
233
Input
1,343
Total output
1,334
Reasoning within output
commit_messages f003
93.3%
Passed
Tokens
88
Input
1,258
Total output
1,054
Reasoning within output
commit_messages f004
95%
Passed
Tokens
125
Input
841
Total output
794
Reasoning within output
commit_messages f005
91%
Passed
Tokens
109
Input
1,287
Total output
1,133
Reasoning within output
commit_messages f006
91.3%
Passed
Tokens
156
Input
1,257
Total output
1,156
Reasoning within output
commit_messages f007
91%
Passed
Tokens
197
Input
1,918
Total output
1,622
Reasoning within output
commit_messages f008
96%
Passed
Tokens
81
Input
1,021
Total output
885
Reasoning within output
commit_messages f009
85%
Passed
Tokens
135
Input
2,020
Total output
1
Reasoning within output
commit_messages f010
91.7%
Passed
Tokens
305
Input
1,685
Total output
1,301
Reasoning within output
commit_messages f011
60%
Passed
Tokens
154
Input
2,396
Total output
1,761
Reasoning within output
commit_messages f012
87.7%
Passed
Tokens
135
Input
783
Total output
765
Reasoning within output
commit_squash f001
100%
Passed
Tokens
143
Input
1,324
Total output
1,307
Reasoning within output
commit_squash f002
100%
Passed
Tokens
124
Input
784
Total output
743
Reasoning within output
commit_squash f003
100%
Passed
Tokens
135
Input
1,112
Total output
1,084
Reasoning within output
commit_squash f004
100%
Passed
Tokens
125
Input
1,319
Total output
1,297
Reasoning within output
commit_squash f005
100%
Passed
Tokens
120
Input
791
Total output
827
Reasoning within output
commit_squash f006
100%
Passed
Tokens
101
Input
920
Total output
904
Reasoning within output
commit_squash f007
100%
Passed
Tokens
109
Input
957
Total output
940
Reasoning within output
commit_squash f008
100%
Passed
Tokens
123
Input
1,245
Total output
1,182
Reasoning within output
commit_squash f009
100%
Passed
Tokens
116
Input
903
Total output
816
Reasoning within output
commit_squash f010
100%
Passed
Tokens
128
Input
951
Total output
931
Reasoning within output
commit_squash f011
100%
Passed
Tokens
136
Input
976
Total output
849
Reasoning within output
commit_squash f012
100%
Passed
Tokens
139
Input
869
Total output
787
Reasoning within output
git_bisect f001
100%
Passed
Tokens
196
Input
707
Total output
558
Reasoning within output
git_bisect f002
100%
Passed
Tokens
212
Input
1,027
Total output
831
Reasoning within output
git_bisect f003
100%
Passed
Tokens
218
Input
680
Total output
521
Reasoning within output
git_bisect f004
100%
Passed
Tokens
222
Input
964
Total output
952
Reasoning within output
git_bisect f005
100%
Passed
Tokens
220
Input
440
Total output
330
Reasoning within output
git_bisect f006
100%
Passed
Tokens
254
Input
802
Total output
605
Reasoning within output
git_bisect f007
100%
Passed
Tokens
218
Input
750
Total output
566
Reasoning within output
git_bisect f008
100%
Passed
Tokens
224
Input
626
Total output
458
Reasoning within output
git_bisect f009
100%
Passed
Tokens
222
Input
596
Total output
466
Reasoning within output
git_bisect f010
100%
Passed
Tokens
220
Input
568
Total output
442
Reasoning within output
git_bisect f011
100%
Passed
Tokens
218
Input
481
Total output
362
Reasoning within output
git_bisect f012
100%
Passed
Tokens
248
Input
1,213
Total output
983
Reasoning within output
git_clean f001
100%
Passed
Tokens
55
Input
1,203
Total output
1,157
Reasoning within output
git_clean f002
100%
Passed
Tokens
66
Input
1,031
Total output
1,022
Reasoning within output
git_clean f003
100%
Passed
Tokens
65
Input
1,318
Total output
1,256
Reasoning within output
git_clean f004
100%
Passed
Tokens
62
Input
1,679
Total output
1,532
Reasoning within output
git_clean f005
100%
Passed
Tokens
54
Input
1,234
Total output
1,210
Reasoning within output
git_clean f006
100%
Passed
Tokens
79
Input
1,365
Total output
1,307
Reasoning within output
git_clean f007
100%
Passed
Tokens
70
Input
1,454
Total output
1
Reasoning within output
git_clean f008
100%
Passed
Tokens
82
Input
1,053
Total output
1,019
Reasoning within output
git_clean f009
100%
Passed
Tokens
73
Input
2,417
Total output
2,339
Reasoning within output
git_clean f010
100%
Passed
Tokens
68
Input
960
Total output
937
Reasoning within output
git_clean f011
40%
Failed
Tokens
66
Input
1,420
Total output
1,365
Reasoning within output
git_clean f012
100%
Passed
Tokens
68
Input
1,707
Total output
1,581
Reasoning within output
git_grep f001
100%
Passed
Tokens
54
Input
596
Total output
594
Reasoning within output
git_grep f002
100%
Passed
Tokens
69
Input
248
Total output
212
Reasoning within output
git_grep f003
100%
Passed
Tokens
89
Input
410
Total output
381
Reasoning within output
git_grep f004
0%
Failed
Tokens
78
Input
770
Total output
590
Reasoning within output
git_grep f005
100%
Passed
Tokens
119
Input
426
Total output
382
Reasoning within output
git_grep f006
100%
Passed
Tokens
43
Input
1,122
Total output
1,117
Reasoning within output
git_grep f007
100%
Passed
Tokens
171
Input
1,390
Total output
1,125
Reasoning within output
git_grep f008
100%
Passed
Tokens
60
Input
338
Total output
311
Reasoning within output
git_grep f009
100%
Passed
Tokens
56
Input
246
Total output
218
Reasoning within output
git_grep f010
100%
Passed
Tokens
66
Input
618
Total output
575
Reasoning within output
git_grep f011
100%
Passed
Tokens
114
Input
241
Total output
225
Reasoning within output
git_grep f012
100%
Passed
Tokens
67
Input
323
Total output
280
Reasoning within output
git_log_format f001
100%
Passed
Tokens
905
Input
126
Total output
116
Reasoning within output
git_log_format f002
100%
Passed
Tokens
910
Input
505
Total output
539
Reasoning within output
git_log_format f003
100%
Passed
Tokens
726
Input
663
Total output
637
Reasoning within output
git_log_format f004
100%
Passed
Tokens
892
Input
322
Total output
262
Reasoning within output
git_log_format f005
100%
Passed
Tokens
739
Input
1,208
Total output
1,084
Reasoning within output
git_log_format f006
100%
Passed
Tokens
913
Input
628
Total output
413
Reasoning within output
git_log_format f007
100%
Passed
Tokens
909
Input
129
Total output
118
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,226
Input
225
Total output
182
Reasoning within output
git_log_format f009
100%
Passed
Tokens
738
Input
257
Total output
231
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,406
Input
642
Total output
580
Reasoning within output
git_log_format f011
100%
Passed
Tokens
442
Input
291
Total output
262
Reasoning within output
git_log_format f012
100%
Passed
Tokens
413
Input
442
Total output
1
Reasoning within output
git_show f001
100%
Passed
Tokens
199
Input
336
Total output
299
Reasoning within output
git_show f002
0%
Failed
Tokens
204
Input
1,150
Total output
1,108
Reasoning within output
git_show f003
100%
Passed
Tokens
687
Input
373
Total output
316
Reasoning within output
git_show f004
100%
Passed
Tokens
468
Input
241
Total output
230
Reasoning within output
git_show f005
100%
Passed
Tokens
202
Input
869
Total output
862
Reasoning within output
git_show f006
100%
Passed
Tokens
210
Input
309
Total output
291
Reasoning within output
git_show f007
100%
Passed
Tokens
204
Input
406
Total output
324
Reasoning within output
git_show f008
100%
Passed
Tokens
212
Input
281
Total output
155
Reasoning within output
git_show f009
100%
Passed
Tokens
327
Input
568
Total output
433
Reasoning within output
git_show f010
100%
Passed
Tokens
200
Input
423
Total output
395
Reasoning within output
git_show f011
100%
Passed
Tokens
230
Input
125
Total output
129
Reasoning within output
git_show f012
100%
Passed
Tokens
345
Input
217
Total output
208
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
88
Input
1,218
Total output
1,224
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
106
Input
894
Total output
844
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
81
Input
1,104
Total output
1,095
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
148
Input
1,783
Total output
1,708
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
140
Input
1,247
Total output
1,301
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
132
Input
1,604
Total output
1,405
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
136
Input
482
Total output
467
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
108
Input
363
Total output
340
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
105
Input
981
Total output
1
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
185
Input
1,329
Total output
1,331
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
149
Input
1,086
Total output
979
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
240
Input
2,084
Total output
1,857
Reasoning within output
rebase f001
0%
Failed
Tokens
101
Input
1,688
Total output
1,794
Reasoning within output
rebase f002
100%
Passed
Tokens
128
Input
1,054
Total output
948
Reasoning within output
rebase f003
100%
Passed
Tokens
107
Input
1,259
Total output
1,276
Reasoning within output
rebase f004
0%
Failed
Tokens
160
Input
2,890
Total output
2,818
Reasoning within output
rebase f005
100%
Passed
Tokens
146
Input
1,442
Total output
1,495
Reasoning within output
rebase f006
100%
Passed
Tokens
146
Input
1,900
Total output
1,668
Reasoning within output
rebase f007
100%
Passed
Tokens
140
Input
1,080
Total output
1
Reasoning within output
rebase f008
100%
Passed
Tokens
122
Input
1,043
Total output
1,027
Reasoning within output
rebase f009
100%
Passed
Tokens
106
Input
1,986
Total output
2,019
Reasoning within output
rebase f010
100%
Passed
Tokens
212
Input
1,509
Total output
1,498
Reasoning within output
rebase f011
100%
Passed
Tokens
161
Input
8,192
Total output
8,163
Reasoning within output
rebase f012
0%
Failed
Tokens
275
Input
2,349
Total output
1
Reasoning within output
reflog f001
100%
Passed
Tokens
262
Input
2,094
Total output
1,327
Reasoning within output
reflog f002
100%
Passed
Tokens
250
Input
1,072
Total output
754
Reasoning within output
reflog f003
100%
Passed
Tokens
220
Input
789
Total output
549
Reasoning within output
reflog f004
100%
Passed
Tokens
362
Input
2,609
Total output
2,086
Reasoning within output
reflog f005
100%
Passed
Tokens
417
Input
1,811
Total output
1,218
Reasoning within output
reflog f006
100%
Passed
Tokens
267
Input
1,464
Total output
981
Reasoning within output
reflog f007
100%
Passed
Tokens
302
Input
1,075
Total output
733
Reasoning within output
reflog f008
100%
Passed
Tokens
393
Input
1,630
Total output
1,097
Reasoning within output
reflog f009
100%
Passed
Tokens
369
Input
1,580
Total output
1,195
Reasoning within output
reflog f010
100%
Passed
Tokens
301
Input
3,835
Total output
1
Reasoning within output
reflog f011
100%
Passed
Tokens
340
Input
4,859
Total output
3,506
Reasoning within output
reflog f012
100%
Passed
Tokens
363
Input
9,502
Total output
1
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
142
Input
311
Total output
1
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
302
Input
549
Total output
434
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
129
Input
771
Total output
717
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
124
Input
811
Total output
1
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
134
Input
349
Total output
336
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
188
Input
355
Total output
344
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
219
Input
363
Total output
300
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
186
Input
911
Total output
895
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
216
Input
544
Total output
501
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
133
Input
732
Total output
688
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
125
Input
434
Total output
403
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
139
Input
919
Total output
854
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
46
Input
681
Total output
668
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
107
Input
1,133
Total output
1,202
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
113
Input
2,695
Total output
2,563
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
100
Input
375
Total output
367
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
53
Input
1,582
Total output
1,554
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
97
Input
1,385
Total output
1,377
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
53
Input
379
Total output
357
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
108
Input
1,253
Total output
1,240
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
98
Input
808
Total output
800
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
105
Input
1,201
Total output
1,238
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
111
Input
242
Total output
244
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
51
Input
1,103
Total output
1,086
Reasoning within output
tag_management f001
100%
Passed
Tokens
64
Input
706
Total output
610
Reasoning within output
tag_management f002
100%
Passed
Tokens
63
Input
4,744
Total output
4,231
Reasoning within output
tag_management f003
100%
Passed
Tokens
68
Input
958
Total output
859
Reasoning within output
tag_management f004
100%
Passed
Tokens
75
Input
670
Total output
628
Reasoning within output
tag_management f005
100%
Passed
Tokens
88
Input
984
Total output
889
Reasoning within output
tag_management f006
100%
Passed
Tokens
74
Input
767
Total output
589
Reasoning within output
tag_management f007
100%
Passed
Tokens
70
Input
1,131
Total output
919
Reasoning within output
tag_management f008
100%
Passed
Tokens
73
Input
1,614
Total output
1,586
Reasoning within output
tag_management f009
100%
Passed
Tokens
76
Input
1,034
Total output
1
Reasoning within output
tag_management f010
100%
Passed
Tokens
52
Input
319
Total output
294
Reasoning within output
tag_management f011
100%
Passed
Tokens
56
Input
959
Total output
1
Reasoning within output
tag_management f012
100%
Passed
Tokens
96
Input
1,808
Total output
1
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
150
Input
155
Total output
148
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
158
Input
1,886
Total output
1,764
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
229
Input
430
Total output
412
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
232
Input
465
Total output
478
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
140
Input
1,029
Total output
1
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
147
Input
1,126
Total output
1,047
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
146
Input
1,847
Total output
1,681
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
171
Input
3,700
Total output
3,650
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
260
Input
1,030
Total output
1,024
Reasoning within output
worktree_usage f010
0%
Failed
Tokens
235
Input
1,337
Total output
1,239
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
229
Input
259
Total output
265
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
142
Input
200
Total output
1
Reasoning within output