Qwen / qwen3.8-max
max
96.6%
197 / 204 fixtures · 1 run(s)
48,946 input / 117,888 total output / 112,860 reasoning within output tokens $0.80522000
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-12.8%
Text: 96.6% →
JSON: 83.8%
+1
Gained
JSON pass / text fail
−27
Lost
Text pass / JSON fail
170
Unchanged Pass
Both pass
6
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| branch_cleanup | 100% | 50% | -50% |
| commit_squash | 100% | 50% | -50% |
| reflog | 100% | 58.3% | -41.7% |
| git_log_format | 100% | 75% | -25% |
| merge_conflicts | 91.7% | 75% | -16.7% |
| rebase | 91.7% | 83.3% | -8.3% |
| cherry_pick | 83.3% | 75% | -8.3% |
| git_grep | 100% | 91.7% | -8.3% |
| submodule_usage | 100% | 91.7% | -8.3% |
| tag_management | 100% | 91.7% | -8.3% |
| worktree_usage | 75% | 83.3% | + 8.3% |
| blame_forensics | 100% | 100% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_clean | 100% | 100% | + 0% |
| git_show | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
Changed Fixtures (28)
f002 -loss f003 -loss f004 -loss f008 -loss f009 -loss f011 -loss f010 -loss f001 -loss f002 -loss f003 -loss f005 -loss f006 -loss f008 -loss f007 -loss f003 -loss f005 -loss f012 -loss f003 -loss f010 -loss f001 -loss f001 -loss f003 -loss f005 -loss f008 -loss f012 -loss f003 -loss f007 -loss f007 +gain
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
298
Input
396
Total output
386
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
293
Input
120
Total output
111
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
325
Input
80
Total output
69
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
241
Input
221
Total output
211
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
311
Input
2,534
Total output
2,526
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
285
Input
352
Total output
344
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
263
Input
200
Total output
190
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
302
Input
289
Total output
280
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
244
Input
149
Total output
140
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
490
Input
283
Total output
275
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
298
Input
143
Total output
135
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
192
Input
241
Total output
231
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
146
Input
201
Total output
193
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
161
Input
315
Total output
305
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
137
Input
140
Total output
134
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
182
Input
251
Total output
241
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
152
Input
187
Total output
179
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
179
Input
126
Total output
112
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
150
Input
196
Total output
186
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
171
Input
201
Total output
187
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
127
Input
155
Total output
149
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
162
Input
199
Total output
189
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
113
Input
157
Total output
151
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
206
Input
91
Total output
76
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
139
Input
293
Total output
284
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
155
Input
585
Total output
573
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
131
Input
685
Total output
676
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
200
Input
1,599
Total output
1,571
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
192
Input
105
Total output
82
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
186
Input
1,005
Total output
978
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
177
Input
136
Total output
121
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
165
Input
54
Total output
43
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
150
Input
51
Total output
41
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
264
Input
417
Total output
384
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
210
Input
151
Total output
122
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
317
Input
1,199
Total output
1,149
Reasoning within output
commit_messages f001
94%
Passed
Tokens
155
Input
200
Total output
192
Reasoning within output
commit_messages f002
84.3%
Passed
Tokens
271
Input
387
Total output
373
Reasoning within output
commit_messages f003
94.7%
Passed
Tokens
126
Input
137
Total output
124
Reasoning within output
commit_messages f004
88.3%
Passed
Tokens
163
Input
57
Total output
49
Reasoning within output
commit_messages f005
88.3%
Passed
Tokens
147
Input
80
Total output
71
Reasoning within output
commit_messages f006
91.7%
Passed
Tokens
194
Input
235
Total output
224
Reasoning within output
commit_messages f007
91.7%
Passed
Tokens
235
Input
161
Total output
150
Reasoning within output
commit_messages f008
91.7%
Passed
Tokens
119
Input
85
Total output
76
Reasoning within output
commit_messages f009
90.3%
Passed
Tokens
173
Input
212
Total output
200
Reasoning within output
commit_messages f010
90%
Passed
Tokens
343
Input
255
Total output
244
Reasoning within output
commit_messages f011
64.7%
Passed
Tokens
192
Input
521
Total output
505
Reasoning within output
commit_messages f012
93.3%
Passed
Tokens
173
Input
155
Total output
145
Reasoning within output
commit_squash f001
100%
Passed
Tokens
186
Input
8,661
Total output
8,644
Reasoning within output
commit_squash f002
100%
Passed
Tokens
158
Input
87
Total output
74
Reasoning within output
commit_squash f003
100%
Passed
Tokens
176
Input
6,089
Total output
6,072
Reasoning within output
commit_squash f004
100%
Passed
Tokens
161
Input
3,397
Total output
3,381
Reasoning within output
commit_squash f005
100%
Passed
Tokens
156
Input
291
Total output
279
Reasoning within output
commit_squash f006
100%
Passed
Tokens
141
Input
142
Total output
126
Reasoning within output
commit_squash f007
100%
Passed
Tokens
149
Input
187
Total output
170
Reasoning within output
commit_squash f008
100%
Passed
Tokens
162
Input
239
Total output
222
Reasoning within output
commit_squash f009
100%
Passed
Tokens
153
Input
150
Total output
134
Reasoning within output
commit_squash f010
100%
Passed
Tokens
166
Input
140
Total output
120
Reasoning within output
commit_squash f011
100%
Passed
Tokens
174
Input
145
Total output
125
Reasoning within output
commit_squash f012
100%
Passed
Tokens
175
Input
194
Total output
169
Reasoning within output
git_bisect f001
100%
Passed
Tokens
228
Input
64
Total output
52
Reasoning within output
git_bisect f002
100%
Passed
Tokens
256
Input
158
Total output
148
Reasoning within output
git_bisect f003
100%
Passed
Tokens
254
Input
90
Total output
80
Reasoning within output
git_bisect f004
100%
Passed
Tokens
262
Input
98
Total output
86
Reasoning within output
git_bisect f005
100%
Passed
Tokens
254
Input
144
Total output
132
Reasoning within output
git_bisect f006
100%
Passed
Tokens
284
Input
82
Total output
70
Reasoning within output
git_bisect f007
100%
Passed
Tokens
254
Input
113
Total output
101
Reasoning within output
git_bisect f008
100%
Passed
Tokens
258
Input
102
Total output
90
Reasoning within output
git_bisect f009
100%
Passed
Tokens
254
Input
130
Total output
120
Reasoning within output
git_bisect f010
100%
Passed
Tokens
252
Input
181
Total output
170
Reasoning within output
git_bisect f011
100%
Passed
Tokens
260
Input
75
Total output
63
Reasoning within output
git_bisect f012
100%
Passed
Tokens
286
Input
102
Total output
91
Reasoning within output
git_clean f001
100%
Passed
Tokens
93
Input
158
Total output
146
Reasoning within output
git_clean f002
100%
Passed
Tokens
104
Input
188
Total output
179
Reasoning within output
git_clean f003
100%
Passed
Tokens
103
Input
235
Total output
226
Reasoning within output
git_clean f004
100%
Passed
Tokens
100
Input
259
Total output
249
Reasoning within output
git_clean f005
100%
Passed
Tokens
92
Input
203
Total output
194
Reasoning within output
git_clean f006
100%
Passed
Tokens
117
Input
587
Total output
576
Reasoning within output
git_clean f007
100%
Passed
Tokens
108
Input
419
Total output
406
Reasoning within output
git_clean f008
100%
Passed
Tokens
120
Input
277
Total output
268
Reasoning within output
git_clean f009
100%
Passed
Tokens
111
Input
237
Total output
226
Reasoning within output
git_clean f010
100%
Passed
Tokens
106
Input
186
Total output
175
Reasoning within output
git_clean f011
100%
Passed
Tokens
104
Input
371
Total output
361
Reasoning within output
git_clean f012
100%
Passed
Tokens
106
Input
306
Total output
294
Reasoning within output
git_grep f001
100%
Passed
Tokens
92
Input
52
Total output
44
Reasoning within output
git_grep f002
100%
Passed
Tokens
109
Input
75
Total output
69
Reasoning within output
git_grep f003
100%
Passed
Tokens
127
Input
39
Total output
33
Reasoning within output
git_grep f004
100%
Passed
Tokens
116
Input
79
Total output
69
Reasoning within output
git_grep f005
100%
Passed
Tokens
157
Input
52
Total output
46
Reasoning within output
git_grep f006
100%
Passed
Tokens
81
Input
121
Total output
115
Reasoning within output
git_grep f007
100%
Passed
Tokens
209
Input
1,182
Total output
1,175
Reasoning within output
git_grep f008
100%
Passed
Tokens
98
Input
57
Total output
51
Reasoning within output
git_grep f009
100%
Passed
Tokens
94
Input
85
Total output
77
Reasoning within output
git_grep f010
100%
Passed
Tokens
104
Input
172
Total output
166
Reasoning within output
git_grep f011
100%
Passed
Tokens
152
Input
43
Total output
38
Reasoning within output
git_grep f012
100%
Passed
Tokens
105
Input
54
Total output
41
Reasoning within output
git_log_format f001
100%
Passed
Tokens
939
Input
119
Total output
113
Reasoning within output
git_log_format f002
100%
Passed
Tokens
934
Input
98
Total output
86
Reasoning within output
git_log_format f003
100%
Passed
Tokens
776
Input
140
Total output
126
Reasoning within output
git_log_format f004
100%
Passed
Tokens
938
Input
72
Total output
67
Reasoning within output
git_log_format f005
100%
Passed
Tokens
777
Input
1,915
Total output
1,905
Reasoning within output
git_log_format f006
100%
Passed
Tokens
951
Input
189
Total output
183
Reasoning within output
git_log_format f007
100%
Passed
Tokens
948
Input
70
Total output
58
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,237
Input
68
Total output
62
Reasoning within output
git_log_format f009
100%
Passed
Tokens
756
Input
83
Total output
77
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,440
Input
68
Total output
62
Reasoning within output
git_log_format f011
100%
Passed
Tokens
465
Input
83
Total output
76
Reasoning within output
git_log_format f012
100%
Passed
Tokens
447
Input
69
Total output
63
Reasoning within output
git_show f001
100%
Passed
Tokens
236
Input
62
Total output
54
Reasoning within output
git_show f002
100%
Passed
Tokens
236
Input
652
Total output
645
Reasoning within output
git_show f003
100%
Passed
Tokens
727
Input
85
Total output
74
Reasoning within output
git_show f004
100%
Passed
Tokens
514
Input
79
Total output
68
Reasoning within output
git_show f005
100%
Passed
Tokens
238
Input
90
Total output
84
Reasoning within output
git_show f006
100%
Passed
Tokens
251
Input
65
Total output
60
Reasoning within output
git_show f007
100%
Passed
Tokens
242
Input
74
Total output
65
Reasoning within output
git_show f008
100%
Passed
Tokens
248
Input
108
Total output
69
Reasoning within output
git_show f009
100%
Passed
Tokens
363
Input
93
Total output
87
Reasoning within output
git_show f010
100%
Passed
Tokens
238
Input
83
Total output
77
Reasoning within output
git_show f011
100%
Passed
Tokens
262
Input
75
Total output
68
Reasoning within output
git_show f012
100%
Passed
Tokens
374
Input
69
Total output
63
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
126
Input
518
Total output
509
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
144
Input
321
Total output
309
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
119
Input
502
Total output
493
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
186
Input
3,444
Total output
3,414
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
178
Input
173
Total output
150
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
170
Input
532
Total output
505
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
174
Input
142
Total output
127
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
146
Input
135
Total output
124
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
143
Input
222
Total output
212
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
223
Input
603
Total output
570
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
187
Input
205
Total output
176
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
278
Input
9,517
Total output
9,467
Reasoning within output
rebase f001
100%
Passed
Tokens
140
Input
701
Total output
692
Reasoning within output
rebase f002
100%
Passed
Tokens
166
Input
149
Total output
137
Reasoning within output
rebase f003
100%
Passed
Tokens
145
Input
185
Total output
177
Reasoning within output
rebase f004
100%
Passed
Tokens
201
Input
9,325
Total output
9,295
Reasoning within output
rebase f005
100%
Passed
Tokens
186
Input
216
Total output
196
Reasoning within output
rebase f006
100%
Passed
Tokens
186
Input
483
Total output
456
Reasoning within output
rebase f007
100%
Passed
Tokens
178
Input
110
Total output
95
Reasoning within output
rebase f008
100%
Passed
Tokens
162
Input
275
Total output
264
Reasoning within output
rebase f009
100%
Passed
Tokens
144
Input
159
Total output
149
Reasoning within output
rebase f010
100%
Passed
Tokens
252
Input
453
Total output
418
Reasoning within output
rebase f011
100%
Passed
Tokens
199
Input
357
Total output
328
Reasoning within output
rebase f012
0%
Failed
Tokens
315
Input
2,672
Total output
2,622
Reasoning within output
reflog f001
100%
Passed
Tokens
299
Input
162
Total output
119
Reasoning within output
reflog f002
100%
Passed
Tokens
290
Input
244
Total output
136
Reasoning within output
reflog f003
100%
Passed
Tokens
263
Input
478
Total output
354
Reasoning within output
reflog f004
100%
Passed
Tokens
383
Input
1,649
Total output
1,404
Reasoning within output
reflog f005
100%
Passed
Tokens
432
Input
866
Total output
709
Reasoning within output
reflog f006
100%
Passed
Tokens
307
Input
1,510
Total output
1,207
Reasoning within output
reflog f007
100%
Passed
Tokens
355
Input
1,150
Total output
763
Reasoning within output
reflog f008
100%
Passed
Tokens
444
Input
733
Total output
517
Reasoning within output
reflog f009
100%
Passed
Tokens
389
Input
852
Total output
762
Reasoning within output
reflog f010
100%
Passed
Tokens
332
Input
566
Total output
463
Reasoning within output
reflog f011
100%
Passed
Tokens
395
Input
3,324
Total output
3,050
Reasoning within output
reflog f012
100%
Passed
Tokens
392
Input
3,520
Total output
3,234
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
180
Input
212
Total output
202
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
343
Input
126
Total output
110
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
167
Input
86
Total output
75
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
162
Input
172
Total output
144
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
171
Input
344
Total output
333
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
226
Input
117
Total output
106
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
257
Input
175
Total output
165
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
224
Input
335
Total output
324
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
254
Input
241
Total output
199
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
171
Input
171
Total output
160
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
166
Input
224
Total output
213
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
177
Input
176
Total output
165
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
84
Input
120
Total output
107
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
147
Input
492
Total output
480
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
153
Input
6,462
Total output
6,430
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
140
Input
70
Total output
62
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
91
Input
364
Total output
334
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
134
Input
2,222
Total output
2,214
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
91
Input
203
Total output
181
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
142
Input
93
Total output
83
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
140
Input
167
Total output
159
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
139
Input
211
Total output
200
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
148
Input
84
Total output
75
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
89
Input
163
Total output
147
Reasoning within output
tag_management f001
100%
Passed
Tokens
105
Input
68
Total output
57
Reasoning within output
tag_management f002
100%
Passed
Tokens
101
Input
121
Total output
98
Reasoning within output
tag_management f003
100%
Passed
Tokens
107
Input
170
Total output
156
Reasoning within output
tag_management f004
100%
Passed
Tokens
113
Input
71
Total output
64
Reasoning within output
tag_management f005
100%
Passed
Tokens
125
Input
121
Total output
109
Reasoning within output
tag_management f006
100%
Passed
Tokens
111
Input
163
Total output
146
Reasoning within output
tag_management f007
100%
Passed
Tokens
108
Input
1,017
Total output
1,001
Reasoning within output
tag_management f008
100%
Passed
Tokens
112
Input
3,660
Total output
3,630
Reasoning within output
tag_management f009
100%
Passed
Tokens
114
Input
129
Total output
108
Reasoning within output
tag_management f010
100%
Passed
Tokens
92
Input
71
Total output
59
Reasoning within output
tag_management f011
100%
Passed
Tokens
94
Input
119
Total output
109
Reasoning within output
tag_management f012
100%
Passed
Tokens
133
Input
433
Total output
419
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
189
Input
171
Total output
157
Reasoning within output
worktree_usage f002
0%
Failed
Tokens
194
Input
819
Total output
792
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
275
Input
124
Total output
111
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
268
Input
97
Total output
88
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
175
Input
93
Total output
77
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
184
Input
250
Total output
231
Reasoning within output
worktree_usage f007
0%
Failed
Tokens
187
Input
1,618
Total output
1,590
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
207
Input
1,346
Total output
1,290
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
295
Input
358
Total output
349
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
277
Input
139
Total output
119
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
264
Input
103
Total output
90
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
182
Input
145
Total output
127
Reasoning within output