Qwen / qwen3.6-27b
medium
95.1%
194 / 204 fixtures · 1 run(s)
41,243 input / 228,922 total output / 196,263 reasoning within output tokens $0.66273233
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-15.2%
Text: 95.1% →
JSON: 79.9%
+5
Gained
JSON pass / text fail
−36
Lost
Text pass / JSON fail
158
Unchanged Pass
Both pass
5
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| cherry_pick | 83.3% | 41.7% | -41.7% |
| git_clean | 100% | 66.7% | -33.3% |
| branch_cleanup | 100% | 75% | -25% |
| git_grep | 100% | 75% | -25% |
| worktree_usage | 91.7% | 66.7% | -25% |
| commit_squash | 100% | 83.3% | -16.7% |
| git_show | 100% | 83.3% | -16.7% |
| rebase | 91.7% | 75% | -16.7% |
| merge_conflicts | 83.3% | 66.7% | -16.7% |
| commit_messages | 100% | 91.7% | -8.3% |
| git_bisect | 100% | 91.7% | -8.3% |
| git_log_format | 100% | 91.7% | -8.3% |
| reflog | 83.3% | 75% | -8.3% |
| tag_management | 100% | 91.7% | -8.3% |
| blame_forensics | 91.7% | 91.7% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 91.7% | 91.7% | + 0% |
Changed Fixtures (41)
f005 +gain f011 -loss f003 -loss f009 -loss f011 -loss f002 -loss f003 -loss f006 -loss f008 -loss f009 -loss f012 -loss f007 -loss f011 -loss f008 -loss f001 -loss f003 -loss f006 -loss f007 -loss f004 -loss f005 -loss f008 -loss f007 -loss f002 -loss f012 -loss f001 -loss f011 -loss f009 -loss f010 -loss f004 +gain f006 -loss f008 -loss f009 -loss f012 +gain f001 -loss f002 +gain f002 -loss f002 -loss f004 -loss f008 -loss f009 -loss f010 +gain
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
259
Input
1,254
Total output
1,191
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
258
Input
1,236
Total output
1,139
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
281
Input
986
Total output
825
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
206
Input
756
Total output
767
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
269
Input
2,016
Total output
1,965
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
245
Input
1,720
Total output
1,511
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
225
Input
836
Total output
719
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
262
Input
1,066
Total output
1,006
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
213
Input
780
Total output
724
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
455
Input
450
Total output
400
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
254
Input
220
Total output
194
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
155
Input
788
Total output
718
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
110
Input
769
Total output
1
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
127
Input
928
Total output
836
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
105
Input
740
Total output
721
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
144
Input
778
Total output
736
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
113
Input
313
Total output
300
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
137
Input
784
Total output
1
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
115
Input
904
Total output
860
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
126
Input
475
Total output
413
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
91
Input
866
Total output
840
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
125
Input
917
Total output
802
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
77
Input
484
Total output
469
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
161
Input
739
Total output
680
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
99
Input
1,161
Total output
1,216
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
121
Input
1,258
Total output
1,131
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
93
Input
1,142
Total output
1,133
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
162
Input
1,929
Total output
1,890
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
155
Input
1,143
Total output
1
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
148
Input
1,215
Total output
1,091
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
139
Input
1,390
Total output
1,358
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
127
Input
1,068
Total output
1
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
112
Input
903
Total output
909
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
224
Input
1,601
Total output
1
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
171
Input
1,010
Total output
938
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
281
Input
1,752
Total output
1,547
Reasoning within output
commit_messages f001
93%
Passed
Tokens
117
Input
1,256
Total output
1,091
Reasoning within output
commit_messages f002
91%
Passed
Tokens
233
Input
489
Total output
410
Reasoning within output
commit_messages f003
89.3%
Passed
Tokens
88
Input
1,049
Total output
817
Reasoning within output
commit_messages f004
94.3%
Passed
Tokens
125
Input
825
Total output
777
Reasoning within output
commit_messages f005
83.3%
Passed
Tokens
109
Input
1,230
Total output
1,125
Reasoning within output
commit_messages f006
88.3%
Passed
Tokens
156
Input
1,314
Total output
1,238
Reasoning within output
commit_messages f007
93.3%
Passed
Tokens
197
Input
970
Total output
937
Reasoning within output
commit_messages f008
93.3%
Passed
Tokens
81
Input
974
Total output
910
Reasoning within output
commit_messages f009
85%
Passed
Tokens
135
Input
1,596
Total output
1,357
Reasoning within output
commit_messages f010
90%
Passed
Tokens
305
Input
1,502
Total output
1,351
Reasoning within output
commit_messages f011
86.7%
Passed
Tokens
154
Input
2,593
Total output
2,052
Reasoning within output
commit_messages f012
90%
Passed
Tokens
135
Input
1,408
Total output
1,324
Reasoning within output
commit_squash f001
100%
Passed
Tokens
147
Input
1,176
Total output
1,144
Reasoning within output
commit_squash f002
100%
Passed
Tokens
122
Input
1,184
Total output
1,171
Reasoning within output
commit_squash f003
100%
Passed
Tokens
137
Input
1,026
Total output
952
Reasoning within output
commit_squash f004
100%
Passed
Tokens
122
Input
1,255
Total output
1,215
Reasoning within output
commit_squash f005
100%
Passed
Tokens
122
Input
980
Total output
982
Reasoning within output
commit_squash f006
100%
Passed
Tokens
105
Input
318
Total output
326
Reasoning within output
commit_squash f007
100%
Passed
Tokens
109
Input
921
Total output
854
Reasoning within output
commit_squash f008
100%
Passed
Tokens
121
Input
663
Total output
1
Reasoning within output
commit_squash f009
100%
Passed
Tokens
113
Input
925
Total output
876
Reasoning within output
commit_squash f010
100%
Passed
Tokens
123
Input
1,063
Total output
1,012
Reasoning within output
commit_squash f011
100%
Passed
Tokens
134
Input
1,066
Total output
973
Reasoning within output
commit_squash f012
100%
Passed
Tokens
137
Input
1,092
Total output
965
Reasoning within output
git_bisect f001
100%
Passed
Tokens
190
Input
377
Total output
329
Reasoning within output
git_bisect f002
100%
Passed
Tokens
218
Input
552
Total output
456
Reasoning within output
git_bisect f003
100%
Passed
Tokens
220
Input
1,079
Total output
843
Reasoning within output
git_bisect f004
100%
Passed
Tokens
226
Input
1,585
Total output
1,219
Reasoning within output
git_bisect f005
100%
Passed
Tokens
222
Input
811
Total output
648
Reasoning within output
git_bisect f006
100%
Passed
Tokens
246
Input
705
Total output
549
Reasoning within output
git_bisect f007
100%
Passed
Tokens
222
Input
811
Total output
612
Reasoning within output
git_bisect f008
100%
Passed
Tokens
222
Input
827
Total output
672
Reasoning within output
git_bisect f009
100%
Passed
Tokens
220
Input
615
Total output
489
Reasoning within output
git_bisect f010
100%
Passed
Tokens
216
Input
756
Total output
625
Reasoning within output
git_bisect f011
100%
Passed
Tokens
222
Input
316
Total output
229
Reasoning within output
git_bisect f012
100%
Passed
Tokens
238
Input
489
Total output
384
Reasoning within output
git_clean f001
100%
Passed
Tokens
55
Input
880
Total output
876
Reasoning within output
git_clean f002
100%
Passed
Tokens
66
Input
1,254
Total output
1,209
Reasoning within output
git_clean f003
100%
Passed
Tokens
65
Input
867
Total output
855
Reasoning within output
git_clean f004
100%
Passed
Tokens
62
Input
1,882
Total output
1,721
Reasoning within output
git_clean f005
100%
Passed
Tokens
54
Input
1,446
Total output
1,383
Reasoning within output
git_clean f006
100%
Passed
Tokens
79
Input
2,088
Total output
1,799
Reasoning within output
git_clean f007
100%
Passed
Tokens
70
Input
1,454
Total output
1,356
Reasoning within output
git_clean f008
100%
Passed
Tokens
82
Input
777
Total output
725
Reasoning within output
git_clean f009
100%
Passed
Tokens
73
Input
496
Total output
508
Reasoning within output
git_clean f010
100%
Passed
Tokens
68
Input
926
Total output
905
Reasoning within output
git_clean f011
100%
Passed
Tokens
66
Input
2,560
Total output
2,300
Reasoning within output
git_clean f012
100%
Passed
Tokens
68
Input
1,694
Total output
1,579
Reasoning within output
git_grep f001
100%
Passed
Tokens
54
Input
252
Total output
251
Reasoning within output
git_grep f002
100%
Passed
Tokens
69
Input
401
Total output
377
Reasoning within output
git_grep f003
100%
Passed
Tokens
89
Input
363
Total output
352
Reasoning within output
git_grep f004
100%
Passed
Tokens
78
Input
811
Total output
664
Reasoning within output
git_grep f005
100%
Passed
Tokens
119
Input
681
Total output
637
Reasoning within output
git_grep f006
100%
Passed
Tokens
43
Input
788
Total output
814
Reasoning within output
git_grep f007
100%
Passed
Tokens
171
Input
2,742
Total output
2,299
Reasoning within output
git_grep f008
100%
Passed
Tokens
60
Input
402
Total output
397
Reasoning within output
git_grep f009
100%
Passed
Tokens
56
Input
236
Total output
220
Reasoning within output
git_grep f010
100%
Passed
Tokens
66
Input
723
Total output
694
Reasoning within output
git_grep f011
100%
Passed
Tokens
114
Input
348
Total output
1
Reasoning within output
git_grep f012
100%
Passed
Tokens
67
Input
573
Total output
529
Reasoning within output
git_log_format f001
100%
Passed
Tokens
885
Input
285
Total output
264
Reasoning within output
git_log_format f002
100%
Passed
Tokens
883
Input
902
Total output
957
Reasoning within output
git_log_format f003
100%
Passed
Tokens
729
Input
455
Total output
369
Reasoning within output
git_log_format f004
100%
Passed
Tokens
893
Input
163
Total output
134
Reasoning within output
git_log_format f005
100%
Passed
Tokens
739
Input
647
Total output
574
Reasoning within output
git_log_format f006
100%
Passed
Tokens
913
Input
843
Total output
568
Reasoning within output
git_log_format f007
100%
Passed
Tokens
902
Input
189
Total output
1
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,203
Input
318
Total output
1
Reasoning within output
git_log_format f009
100%
Passed
Tokens
741
Input
216
Total output
193
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,379
Input
180
Total output
167
Reasoning within output
git_log_format f011
100%
Passed
Tokens
445
Input
222
Total output
214
Reasoning within output
git_log_format f012
100%
Passed
Tokens
410
Input
252
Total output
196
Reasoning within output
git_show f001
100%
Passed
Tokens
201
Input
206
Total output
168
Reasoning within output
git_show f002
100%
Passed
Tokens
201
Input
1,367
Total output
1,389
Reasoning within output
git_show f003
100%
Passed
Tokens
689
Input
363
Total output
308
Reasoning within output
git_show f004
100%
Passed
Tokens
472
Input
173
Total output
1
Reasoning within output
git_show f005
100%
Passed
Tokens
204
Input
872
Total output
1
Reasoning within output
git_show f006
100%
Passed
Tokens
210
Input
110
Total output
105
Reasoning within output
git_show f007
100%
Passed
Tokens
204
Input
171
Total output
1
Reasoning within output
git_show f008
100%
Passed
Tokens
212
Input
306
Total output
179
Reasoning within output
git_show f009
100%
Passed
Tokens
324
Input
378
Total output
327
Reasoning within output
git_show f010
100%
Passed
Tokens
198
Input
346
Total output
1
Reasoning within output
git_show f011
100%
Passed
Tokens
227
Input
189
Total output
1
Reasoning within output
git_show f012
100%
Passed
Tokens
345
Input
375
Total output
337
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
88
Input
997
Total output
1,028
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
106
Input
618
Total output
606
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
81
Input
1,730
Total output
1,738
Reasoning within output
merge_conflicts f004
0%
Failed
Tokens
148
Input
2,379
Total output
1
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
140
Input
1,681
Total output
1,763
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
132
Input
2,061
Total output
1,820
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
136
Input
1,423
Total output
1,363
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
108
Input
969
Total output
962
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
105
Input
1,084
Total output
1,081
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
185
Input
1,547
Total output
1,558
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
149
Input
2,850
Total output
2,616
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
240
Input
2,860
Total output
2,589
Reasoning within output
rebase f001
100%
Passed
Tokens
100
Input
1,213
Total output
1,250
Reasoning within output
rebase f002
100%
Passed
Tokens
128
Input
332
Total output
323
Reasoning within output
rebase f003
100%
Passed
Tokens
108
Input
1,006
Total output
998
Reasoning within output
rebase f004
100%
Passed
Tokens
160
Input
1,541
Total output
1,420
Reasoning within output
rebase f005
100%
Passed
Tokens
148
Input
2,902
Total output
3,074
Reasoning within output
rebase f006
100%
Passed
Tokens
147
Input
2,069
Total output
2,042
Reasoning within output
rebase f007
100%
Passed
Tokens
141
Input
919
Total output
904
Reasoning within output
rebase f008
100%
Passed
Tokens
122
Input
766
Total output
780
Reasoning within output
rebase f009
100%
Passed
Tokens
103
Input
1,068
Total output
1,044
Reasoning within output
rebase f010
100%
Passed
Tokens
212
Input
1,920
Total output
1,887
Reasoning within output
rebase f011
100%
Passed
Tokens
160
Input
1,464
Total output
1,274
Reasoning within output
rebase f012
0%
Failed
Tokens
275
Input
11,049
Total output
11,001
Reasoning within output
reflog f001
100%
Passed
Tokens
267
Input
1,604
Total output
1,011
Reasoning within output
reflog f002
100%
Passed
Tokens
251
Input
1,126
Total output
757
Reasoning within output
reflog f003
100%
Passed
Tokens
220
Input
1,063
Total output
800
Reasoning within output
reflog f004
0%
Failed
Tokens
359
Input
3,326
Total output
3,040
Reasoning within output
reflog f005
100%
Passed
Tokens
426
Input
1,728
Total output
1,109
Reasoning within output
reflog f006
100%
Passed
Tokens
270
Input
1,467
Total output
981
Reasoning within output
reflog f007
100%
Passed
Tokens
305
Input
1,773
Total output
1,245
Reasoning within output
reflog f008
100%
Passed
Tokens
415
Input
1,631
Total output
1,192
Reasoning within output
reflog f009
100%
Passed
Tokens
343
Input
2,659
Total output
2,093
Reasoning within output
reflog f010
100%
Passed
Tokens
303
Input
1,873
Total output
1,352
Reasoning within output
reflog f011
100%
Passed
Tokens
366
Input
5,303
Total output
4,027
Reasoning within output
reflog f012
0%
Failed
Tokens
360
Input
2,614
Total output
2,270
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
140
Input
323
Total output
305
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
308
Input
931
Total output
769
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
129
Input
805
Total output
739
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
124
Input
325
Total output
313
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
136
Input
796
Total output
1
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
188
Input
390
Total output
366
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
219
Input
1,044
Total output
1
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
186
Input
387
Total output
355
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
216
Input
703
Total output
650
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
133
Input
1,167
Total output
1,060
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
127
Input
391
Total output
365
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
139
Input
928
Total output
1
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
46
Input
291
Total output
278
Reasoning within output
submodule_usage f002
0%
Failed
Tokens
107
Input
838
Total output
904
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
117
Input
2,388
Total output
2,291
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
100
Input
167
Total output
193
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
53
Input
1,017
Total output
980
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
97
Input
1,551
Total output
1,636
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
53
Input
1,347
Total output
1,351
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
102
Input
988
Total output
1,034
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
100
Input
1,060
Total output
1,063
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
110
Input
1,148
Total output
1,197
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
108
Input
336
Total output
327
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
51
Input
1,102
Total output
1,093
Reasoning within output
tag_management f001
100%
Passed
Tokens
63
Input
635
Total output
566
Reasoning within output
tag_management f002
100%
Passed
Tokens
63
Input
1,213
Total output
1,191
Reasoning within output
tag_management f003
100%
Passed
Tokens
70
Input
986
Total output
972
Reasoning within output
tag_management f004
100%
Passed
Tokens
76
Input
986
Total output
937
Reasoning within output
tag_management f005
100%
Passed
Tokens
86
Input
1,113
Total output
980
Reasoning within output
tag_management f006
100%
Passed
Tokens
72
Input
894
Total output
723
Reasoning within output
tag_management f007
100%
Passed
Tokens
70
Input
2,084
Total output
1,599
Reasoning within output
tag_management f008
100%
Passed
Tokens
72
Input
1,628
Total output
1,353
Reasoning within output
tag_management f009
100%
Passed
Tokens
77
Input
1,152
Total output
1,131
Reasoning within output
tag_management f010
100%
Passed
Tokens
53
Input
561
Total output
531
Reasoning within output
tag_management f011
100%
Passed
Tokens
55
Input
1,095
Total output
1,085
Reasoning within output
tag_management f012
100%
Passed
Tokens
95
Input
1,161
Total output
1,072
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
154
Input
1,255
Total output
1,241
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
157
Input
1,479
Total output
1,412
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
232
Input
1,108
Total output
1,007
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
238
Input
975
Total output
966
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
143
Input
1,081
Total output
1,009
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
141
Input
1,490
Total output
1,360
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
147
Input
1,160
Total output
1,078
Reasoning within output
worktree_usage f008
100%
Passed
Tokens
170
Input
1,935
Total output
1,701
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
261
Input
1,172
Total output
1,102
Reasoning within output
worktree_usage f010
0%
Failed
Tokens
242
Input
870
Total output
840
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
229
Input
654
Total output
636
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
144
Input
2,850
Total output
2,644
Reasoning within output