Qwen / qwen3.6-35b-a3b
medium
94.1%
192 / 204 fixtures · 1 run(s)
41,344 input / 231,352 total output / 215,088 reasoning within output tokens $0.25469185
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-2.5%
Text: 94.1% →
JSON: 91.7%
+6
Gained
JSON pass / text fail
−11
Lost
Text pass / JSON fail
181
Unchanged Pass
Both pass
6
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| reflog | 100% | 58.3% | -41.7% |
| branch_cleanup | 100% | 75% | -25% |
| rebase | 75% | 91.7% | + 16.7% |
| cherry_pick | 83.3% | 91.7% | + 8.3% |
| git_clean | 83.3% | 91.7% | + 8.3% |
| worktree_usage | 91.7% | 83.3% | -8.3% |
| blame_forensics | 100% | 100% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| commit_squash | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_grep | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 91.7% | 91.7% | + 0% |
| merge_conflicts | 83.3% | 83.3% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 91.7% | 91.7% | + 0% |
| tag_management | 100% | 100% | + 0% |
Changed Fixtures (17)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
262
Input
401
Total output
391
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
255
Input
500
Total output
414
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
283
Input
361
Total output
350
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
206
Input
171
Total output
188
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
266
Input
512
Total output
444
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
248
Input
1,207
Total output
1,040
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
226
Input
874
Total output
864
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
264
Input
1,064
Total output
1,055
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
214
Input
516
Total output
507
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
443
Input
878
Total output
765
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
262
Input
2,601
Total output
2,286
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
148
Input
793
Total output
735
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
107
Input
1,082
Total output
1,036
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
125
Input
1,153
Total output
1,056
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
100
Input
1,319
Total output
1,326
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
136
Input
703
Total output
710
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
116
Input
805
Total output
797
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
138
Input
859
Total output
845
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
109
Input
774
Total output
789
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
132
Input
918
Total output
904
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
90
Input
579
Total output
552
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
127
Input
923
Total output
824
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
74
Input
333
Total output
327
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
162
Input
1,087
Total output
1,015
Reasoning within output
cherry_pick f001
0%
Failed
Tokens
100
Input
2,619
Total output
2,786
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
120
Input
1,083
Total output
1,071
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
93
Input
869
Total output
892
Reasoning within output
cherry_pick f004
100%
Passed
Tokens
164
Input
1,787
Total output
1,701
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
156
Input
905
Total output
882
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
147
Input
1,242
Total output
1,089
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
136
Input
1,006
Total output
973
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
127
Input
886
Total output
884
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
110
Input
910
Total output
894
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
224
Input
1,664
Total output
1,768
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
172
Input
1,020
Total output
991
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
275
Input
2,361
Total output
2,186
Reasoning within output
commit_messages f001
84.3%
Passed
Tokens
117
Input
1,478
Total output
1,270
Reasoning within output
commit_messages f002
91.7%
Passed
Tokens
233
Input
2,219
Total output
2,004
Reasoning within output
commit_messages f003
92.7%
Passed
Tokens
88
Input
553
Total output
488
Reasoning within output
commit_messages f004
96%
Passed
Tokens
125
Input
866
Total output
815
Reasoning within output
commit_messages f005
87.7%
Passed
Tokens
109
Input
956
Total output
887
Reasoning within output
commit_messages f006
92.3%
Passed
Tokens
156
Input
1,404
Total output
1,149
Reasoning within output
commit_messages f007
93.7%
Passed
Tokens
197
Input
423
Total output
366
Reasoning within output
commit_messages f008
93.3%
Passed
Tokens
81
Input
1,016
Total output
888
Reasoning within output
commit_messages f009
86.7%
Passed
Tokens
135
Input
1,726
Total output
1,512
Reasoning within output
commit_messages f010
89.3%
Passed
Tokens
305
Input
1,062
Total output
938
Reasoning within output
commit_messages f011
52.7%
Passed
Tokens
154
Input
2,644
Total output
1,807
Reasoning within output
commit_messages f012
90%
Passed
Tokens
135
Input
1,218
Total output
1,133
Reasoning within output
commit_squash f001
100%
Passed
Tokens
145
Input
1,233
Total output
1,110
Reasoning within output
commit_squash f002
100%
Passed
Tokens
123
Input
924
Total output
877
Reasoning within output
commit_squash f003
100%
Passed
Tokens
135
Input
1,296
Total output
1,203
Reasoning within output
commit_squash f004
100%
Passed
Tokens
124
Input
1,249
Total output
1,189
Reasoning within output
commit_squash f005
100%
Passed
Tokens
117
Input
1,032
Total output
1,020
Reasoning within output
commit_squash f006
100%
Passed
Tokens
107
Input
1,933
Total output
1,828
Reasoning within output
commit_squash f007
100%
Passed
Tokens
108
Input
229
Total output
212
Reasoning within output
commit_squash f008
100%
Passed
Tokens
125
Input
943
Total output
905
Reasoning within output
commit_squash f009
100%
Passed
Tokens
118
Input
885
Total output
808
Reasoning within output
commit_squash f010
100%
Passed
Tokens
127
Input
1,107
Total output
1,062
Reasoning within output
commit_squash f011
100%
Passed
Tokens
137
Input
932
Total output
816
Reasoning within output
commit_squash f012
100%
Passed
Tokens
137
Input
324
Total output
276
Reasoning within output
git_bisect f001
100%
Passed
Tokens
190
Input
416
Total output
405
Reasoning within output
git_bisect f002
100%
Passed
Tokens
216
Input
600
Total output
483
Reasoning within output
git_bisect f003
100%
Passed
Tokens
218
Input
1,439
Total output
1,427
Reasoning within output
git_bisect f004
100%
Passed
Tokens
222
Input
623
Total output
504
Reasoning within output
git_bisect f005
100%
Passed
Tokens
212
Input
397
Total output
387
Reasoning within output
git_bisect f006
100%
Passed
Tokens
246
Input
945
Total output
722
Reasoning within output
git_bisect f007
100%
Passed
Tokens
222
Input
735
Total output
522
Reasoning within output
git_bisect f008
100%
Passed
Tokens
216
Input
333
Total output
278
Reasoning within output
git_bisect f009
100%
Passed
Tokens
222
Input
381
Total output
370
Reasoning within output
git_bisect f010
100%
Passed
Tokens
218
Input
359
Total output
295
Reasoning within output
git_bisect f011
100%
Passed
Tokens
220
Input
846
Total output
834
Reasoning within output
git_bisect f012
100%
Passed
Tokens
248
Input
319
Total output
242
Reasoning within output
git_clean f001
50%
Failed
Tokens
55
Input
1,053
Total output
1,050
Reasoning within output
git_clean f002
100%
Passed
Tokens
66
Input
848
Total output
820
Reasoning within output
git_clean f003
100%
Passed
Tokens
65
Input
935
Total output
926
Reasoning within output
git_clean f004
100%
Passed
Tokens
62
Input
1,516
Total output
1,405
Reasoning within output
git_clean f005
100%
Passed
Tokens
54
Input
1,864
Total output
1,830
Reasoning within output
git_clean f006
100%
Passed
Tokens
79
Input
1,927
Total output
1,916
Reasoning within output
git_clean f007
100%
Passed
Tokens
70
Input
1,930
Total output
1,793
Reasoning within output
git_clean f008
100%
Passed
Tokens
82
Input
956
Total output
910
Reasoning within output
git_clean f009
100%
Passed
Tokens
73
Input
1,204
Total output
1,192
Reasoning within output
git_clean f010
100%
Passed
Tokens
68
Input
1,626
Total output
1,547
Reasoning within output
git_clean f011
60%
Failed
Tokens
66
Input
1,694
Total output
1,575
Reasoning within output
git_clean f012
100%
Passed
Tokens
68
Input
778
Total output
727
Reasoning within output
git_grep f001
100%
Passed
Tokens
54
Input
263
Total output
255
Reasoning within output
git_grep f002
100%
Passed
Tokens
68
Input
678
Total output
672
Reasoning within output
git_grep f003
100%
Passed
Tokens
89
Input
264
Total output
259
Reasoning within output
git_grep f004
100%
Passed
Tokens
78
Input
277
Total output
240
Reasoning within output
git_grep f005
100%
Passed
Tokens
119
Input
426
Total output
397
Reasoning within output
git_grep f006
100%
Passed
Tokens
43
Input
742
Total output
764
Reasoning within output
git_grep f007
100%
Passed
Tokens
171
Input
1,728
Total output
1,722
Reasoning within output
git_grep f008
100%
Passed
Tokens
60
Input
239
Total output
234
Reasoning within output
git_grep f009
100%
Passed
Tokens
56
Input
209
Total output
201
Reasoning within output
git_grep f010
100%
Passed
Tokens
66
Input
464
Total output
439
Reasoning within output
git_grep f011
100%
Passed
Tokens
114
Input
503
Total output
470
Reasoning within output
git_grep f012
100%
Passed
Tokens
67
Input
349
Total output
309
Reasoning within output
git_log_format f001
100%
Passed
Tokens
902
Input
212
Total output
197
Reasoning within output
git_log_format f002
100%
Passed
Tokens
905
Input
326
Total output
343
Reasoning within output
git_log_format f003
100%
Passed
Tokens
741
Input
924
Total output
872
Reasoning within output
git_log_format f004
100%
Passed
Tokens
888
Input
404
Total output
398
Reasoning within output
git_log_format f005
100%
Passed
Tokens
739
Input
939
Total output
821
Reasoning within output
git_log_format f006
100%
Passed
Tokens
913
Input
684
Total output
424
Reasoning within output
git_log_format f007
100%
Passed
Tokens
917
Input
206
Total output
158
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,233
Input
183
Total output
142
Reasoning within output
git_log_format f009
100%
Passed
Tokens
734
Input
316
Total output
303
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,386
Input
299
Total output
242
Reasoning within output
git_log_format f011
100%
Passed
Tokens
441
Input
211
Total output
197
Reasoning within output
git_log_format f012
100%
Passed
Tokens
408
Input
204
Total output
167
Reasoning within output
git_show f001
100%
Passed
Tokens
200
Input
196
Total output
168
Reasoning within output
git_show f002
0%
Failed
Tokens
200
Input
1,045
Total output
1,038
Reasoning within output
git_show f003
100%
Passed
Tokens
695
Input
830
Total output
819
Reasoning within output
git_show f004
100%
Passed
Tokens
474
Input
532
Total output
483
Reasoning within output
git_show f005
100%
Passed
Tokens
206
Input
884
Total output
864
Reasoning within output
git_show f006
100%
Passed
Tokens
214
Input
369
Total output
319
Reasoning within output
git_show f007
100%
Passed
Tokens
204
Input
121
Total output
116
Reasoning within output
git_show f008
100%
Passed
Tokens
209
Input
338
Total output
199
Reasoning within output
git_show f009
100%
Passed
Tokens
330
Input
470
Total output
367
Reasoning within output
git_show f010
100%
Passed
Tokens
199
Input
291
Total output
274
Reasoning within output
git_show f011
100%
Passed
Tokens
224
Input
214
Total output
208
Reasoning within output
git_show f012
100%
Passed
Tokens
346
Input
163
Total output
151
Reasoning within output
merge_conflicts f001
0%
Failed
Tokens
88
Input
2,160
Total output
2,220
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
106
Input
1,504
Total output
1,384
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
81
Input
1,876
Total output
1,867
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
148
Input
2,458
Total output
2,455
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
140
Input
1,223
Total output
1,241
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
132
Input
1,330
Total output
1,147
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
136
Input
1,241
Total output
1,226
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
108
Input
254
Total output
243
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
105
Input
1,111
Total output
1,094
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
185
Input
1,918
Total output
1,904
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
149
Input
1,161
Total output
1,132
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
240
Input
2,124
Total output
1,914
Reasoning within output
rebase f001
0%
Failed
Tokens
101
Input
2,628
Total output
2,630
Reasoning within output
rebase f002
100%
Passed
Tokens
127
Input
608
Total output
558
Reasoning within output
rebase f003
100%
Passed
Tokens
108
Input
921
Total output
957
Reasoning within output
rebase f004
0%
Failed
Tokens
163
Input
2,641
Total output
2,515
Reasoning within output
rebase f005
100%
Passed
Tokens
148
Input
1,828
Total output
1,926
Reasoning within output
rebase f006
100%
Passed
Tokens
147
Input
1,184
Total output
1,157
Reasoning within output
rebase f007
100%
Passed
Tokens
141
Input
830
Total output
815
Reasoning within output
rebase f008
100%
Passed
Tokens
124
Input
1,082
Total output
1,071
Reasoning within output
rebase f009
100%
Passed
Tokens
106
Input
1,376
Total output
1,366
Reasoning within output
rebase f010
100%
Passed
Tokens
218
Input
2,173
Total output
2,140
Reasoning within output
rebase f011
100%
Passed
Tokens
160
Input
1,630
Total output
1,426
Reasoning within output
rebase f012
0%
Failed
Tokens
273
Input
18,026
Total output
16,953
Reasoning within output
reflog f001
100%
Passed
Tokens
265
Input
370
Total output
232
Reasoning within output
reflog f002
100%
Passed
Tokens
255
Input
1,565
Total output
1,455
Reasoning within output
reflog f003
100%
Passed
Tokens
219
Input
1,546
Total output
1,131
Reasoning within output
reflog f004
100%
Passed
Tokens
364
Input
2,595
Total output
1,888
Reasoning within output
reflog f005
100%
Passed
Tokens
419
Input
1,286
Total output
793
Reasoning within output
reflog f006
100%
Passed
Tokens
268
Input
1,061
Total output
632
Reasoning within output
reflog f007
100%
Passed
Tokens
306
Input
1,533
Total output
986
Reasoning within output
reflog f008
100%
Passed
Tokens
409
Input
1,876
Total output
1,664
Reasoning within output
reflog f009
100%
Passed
Tokens
365
Input
5,902
Total output
5,707
Reasoning within output
reflog f010
100%
Passed
Tokens
306
Input
1,523
Total output
1,389
Reasoning within output
reflog f011
100%
Passed
Tokens
363
Input
2,791
Total output
1,901
Reasoning within output
reflog f012
100%
Passed
Tokens
367
Input
1,491
Total output
1,184
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
142
Input
354
Total output
343
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
311
Input
567
Total output
512
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
129
Input
588
Total output
566
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
124
Input
325
Total output
303
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
136
Input
716
Total output
705
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
188
Input
520
Total output
491
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
217
Input
462
Total output
392
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
186
Input
790
Total output
774
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
216
Input
1,186
Total output
1,164
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
133
Input
354
Total output
337
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
127
Input
336
Total output
311
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
139
Input
460
Total output
467
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
46
Input
864
Total output
854
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
108
Input
2,386
Total output
2,508
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
109
Input
2,815
Total output
2,770
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
99
Input
511
Total output
503
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
53
Input
1,433
Total output
1,406
Reasoning within output
submodule_usage f006
0%
Failed
Tokens
96
Input
3,378
Total output
3,363
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
53
Input
327
Total output
297
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
105
Input
1,120
Total output
1,152
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
101
Input
767
Total output
776
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
108
Input
1,574
Total output
1,689
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
114
Input
289
Total output
291
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
51
Input
1,137
Total output
1,112
Reasoning within output
tag_management f001
100%
Passed
Tokens
65
Input
1,118
Total output
964
Reasoning within output
tag_management f002
100%
Passed
Tokens
62
Input
777
Total output
754
Reasoning within output
tag_management f003
100%
Passed
Tokens
69
Input
585
Total output
522
Reasoning within output
tag_management f004
100%
Passed
Tokens
76
Input
810
Total output
807
Reasoning within output
tag_management f005
100%
Passed
Tokens
89
Input
1,399
Total output
1,387
Reasoning within output
tag_management f006
100%
Passed
Tokens
70
Input
1,112
Total output
1,093
Reasoning within output
tag_management f007
100%
Passed
Tokens
69
Input
1,659
Total output
1,313
Reasoning within output
tag_management f008
100%
Passed
Tokens
74
Input
1,805
Total output
1,336
Reasoning within output
tag_management f009
100%
Passed
Tokens
76
Input
379
Total output
318
Reasoning within output
tag_management f010
100%
Passed
Tokens
55
Input
567
Total output
520
Reasoning within output
tag_management f011
100%
Passed
Tokens
58
Input
830
Total output
830
Reasoning within output
tag_management f012
100%
Passed
Tokens
97
Input
1,686
Total output
1,672
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
152
Input
882
Total output
878
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
158
Input
1,682
Total output
1,576
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
235
Input
919
Total output
839
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
224
Input
261
Total output
252
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
142
Input
1,381
Total output
1,365
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
145
Input
1,487
Total output
1,332
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
146
Input
938
Total output
905
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
168
Input
3,358
Total output
2,946
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
264
Input
1,011
Total output
1,022
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
236
Input
1,075
Total output
989
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
232
Input
256
Total output
244
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
145
Input
646
Total output
543
Reasoning within output