Qwen / qwen3.8-max
low
94.1%
192 / 204 fixtures · 1 run(s)
46,496 input / 40,178 total output / 30,902 reasoning within output tokens $0.33406000
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-12.3%
Text: 94.1% →
JSON: 81.9%
+5
Gained
JSON pass / text fail
−30
Lost
Text pass / JSON fail
162
Unchanged Pass
Both pass
7
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| commit_squash | 100% | 50% | -50% |
| merge_conflicts | 91.7% | 58.3% | -33.3% |
| branch_cleanup | 100% | 66.7% | -33.3% |
| cherry_pick | 83.3% | 58.3% | -25% |
| reflog | 100% | 75% | -25% |
| git_clean | 100% | 83.3% | -16.7% |
| git_log_format | 100% | 83.3% | -16.7% |
| git_grep | 91.7% | 83.3% | -8.3% |
| blame_forensics | 91.7% | 100% | + 8.3% |
| git_show | 100% | 91.7% | -8.3% |
| tag_management | 100% | 91.7% | -8.3% |
| worktree_usage | 91.7% | 100% | + 8.3% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| rebase | 58.3% | 58.3% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 91.7% | 91.7% | + 0% |
Changed Fixtures (35)
f005 +gain f001 -loss f005 -loss f009 -loss f011 -loss f005 -loss f010 -loss f011 -loss f003 -loss f004 -loss f005 -loss f006 -loss f009 -loss f012 -loss f005 -loss f011 -loss f007 -loss f003 -loss f012 -loss f002 -loss f001 -loss f003 -loss f010 -loss f011 -loss f005 +gain f006 +gain f010 -loss f011 -loss f001 -loss f003 -loss f007 -loss f003 -loss f004 +gain f007 -loss f008 +gain
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
283
Input
253
Total output
243
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
281
Input
217
Total output
208
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
313
Input
80
Total output
69
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
234
Input
182
Total output
172
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
301
Input
661
Total output
652
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
275
Input
476
Total output
468
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
248
Input
80
Total output
70
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
282
Input
227
Total output
218
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
236
Input
189
Total output
180
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
465
Input
155
Total output
147
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
288
Input
254
Total output
246
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
178
Input
192
Total output
182
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
133
Input
191
Total output
183
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
153
Input
157
Total output
147
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
129
Input
87
Total output
81
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
166
Input
85
Total output
75
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
138
Input
138
Total output
130
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
165
Input
116
Total output
102
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
141
Input
115
Total output
105
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
157
Input
98
Total output
84
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
112
Input
115
Total output
110
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
149
Input
161
Total output
151
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
103
Input
132
Total output
126
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
189
Input
96
Total output
81
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
127
Input
158
Total output
149
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
144
Input
187
Total output
171
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
120
Input
196
Total output
183
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
189
Input
328
Total output
296
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
180
Input
155
Total output
127
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
173
Input
208
Total output
176
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
165
Input
180
Total output
161
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
153
Input
102
Total output
87
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
138
Input
54
Total output
44
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
248
Input
218
Total output
175
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
198
Input
195
Total output
161
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
299
Input
540
Total output
479
Reasoning within output
commit_messages f001
94.3%
Passed
Tokens
143
Input
116
Total output
108
Reasoning within output
commit_messages f002
88.3%
Passed
Tokens
259
Input
130
Total output
121
Reasoning within output
commit_messages f003
95%
Passed
Tokens
114
Input
83
Total output
70
Reasoning within output
commit_messages f004
99%
Passed
Tokens
151
Input
103
Total output
95
Reasoning within output
commit_messages f005
89.3%
Passed
Tokens
135
Input
65
Total output
55
Reasoning within output
commit_messages f006
89.3%
Passed
Tokens
182
Input
146
Total output
136
Reasoning within output
commit_messages f007
90%
Passed
Tokens
223
Input
111
Total output
100
Reasoning within output
commit_messages f008
93.3%
Passed
Tokens
107
Input
129
Total output
120
Reasoning within output
commit_messages f009
78.3%
Passed
Tokens
161
Input
142
Total output
125
Reasoning within output
commit_messages f010
88.3%
Passed
Tokens
331
Input
155
Total output
143
Reasoning within output
commit_messages f011
58.3%
Passed
Tokens
180
Input
169
Total output
154
Reasoning within output
commit_messages f012
89.3%
Passed
Tokens
161
Input
147
Total output
137
Reasoning within output
commit_squash f001
100%
Passed
Tokens
173
Input
253
Total output
236
Reasoning within output
commit_squash f002
100%
Passed
Tokens
151
Input
196
Total output
183
Reasoning within output
commit_squash f003
100%
Passed
Tokens
159
Input
202
Total output
185
Reasoning within output
commit_squash f004
100%
Passed
Tokens
150
Input
220
Total output
204
Reasoning within output
commit_squash f005
100%
Passed
Tokens
146
Input
169
Total output
157
Reasoning within output
commit_squash f006
100%
Passed
Tokens
134
Input
152
Total output
136
Reasoning within output
commit_squash f007
100%
Passed
Tokens
135
Input
115
Total output
98
Reasoning within output
commit_squash f008
100%
Passed
Tokens
151
Input
127
Total output
110
Reasoning within output
commit_squash f009
100%
Passed
Tokens
140
Input
254
Total output
238
Reasoning within output
commit_squash f010
100%
Passed
Tokens
157
Input
160
Total output
140
Reasoning within output
commit_squash f011
100%
Passed
Tokens
165
Input
155
Total output
135
Reasoning within output
commit_squash f012
100%
Passed
Tokens
162
Input
176
Total output
151
Reasoning within output
git_bisect f001
100%
Passed
Tokens
222
Input
208
Total output
103
Reasoning within output
git_bisect f002
100%
Passed
Tokens
238
Input
245
Total output
129
Reasoning within output
git_bisect f003
100%
Passed
Tokens
242
Input
250
Total output
131
Reasoning within output
git_bisect f004
100%
Passed
Tokens
246
Input
247
Total output
139
Reasoning within output
git_bisect f005
100%
Passed
Tokens
244
Input
220
Total output
139
Reasoning within output
git_bisect f006
100%
Passed
Tokens
268
Input
278
Total output
141
Reasoning within output
git_bisect f007
100%
Passed
Tokens
246
Input
202
Total output
128
Reasoning within output
git_bisect f008
100%
Passed
Tokens
246
Input
197
Total output
124
Reasoning within output
git_bisect f009
100%
Passed
Tokens
238
Input
271
Total output
149
Reasoning within output
git_bisect f010
100%
Passed
Tokens
246
Input
183
Total output
110
Reasoning within output
git_bisect f011
100%
Passed
Tokens
246
Input
243
Total output
138
Reasoning within output
git_bisect f012
100%
Passed
Tokens
276
Input
264
Total output
160
Reasoning within output
git_clean f001
100%
Passed
Tokens
81
Input
147
Total output
131
Reasoning within output
git_clean f002
100%
Passed
Tokens
92
Input
61
Total output
48
Reasoning within output
git_clean f003
100%
Passed
Tokens
91
Input
53
Total output
44
Reasoning within output
git_clean f004
100%
Passed
Tokens
88
Input
121
Total output
107
Reasoning within output
git_clean f005
100%
Passed
Tokens
80
Input
141
Total output
130
Reasoning within output
git_clean f006
100%
Passed
Tokens
105
Input
85
Total output
70
Reasoning within output
git_clean f007
100%
Passed
Tokens
96
Input
86
Total output
73
Reasoning within output
git_clean f008
100%
Passed
Tokens
108
Input
80
Total output
71
Reasoning within output
git_clean f009
100%
Passed
Tokens
99
Input
310
Total output
294
Reasoning within output
git_clean f010
100%
Passed
Tokens
94
Input
79
Total output
70
Reasoning within output
git_clean f011
100%
Passed
Tokens
92
Input
179
Total output
167
Reasoning within output
git_clean f012
100%
Passed
Tokens
94
Input
146
Total output
130
Reasoning within output
git_grep f001
100%
Passed
Tokens
80
Input
59
Total output
51
Reasoning within output
git_grep f002
100%
Passed
Tokens
97
Input
81
Total output
76
Reasoning within output
git_grep f003
100%
Passed
Tokens
115
Input
83
Total output
77
Reasoning within output
git_grep f004
0%
Failed
Tokens
104
Input
87
Total output
75
Reasoning within output
git_grep f005
100%
Passed
Tokens
145
Input
114
Total output
109
Reasoning within output
git_grep f006
100%
Passed
Tokens
69
Input
135
Total output
129
Reasoning within output
git_grep f007
100%
Passed
Tokens
197
Input
178
Total output
171
Reasoning within output
git_grep f008
100%
Passed
Tokens
86
Input
74
Total output
68
Reasoning within output
git_grep f009
100%
Passed
Tokens
82
Input
52
Total output
44
Reasoning within output
git_grep f010
100%
Passed
Tokens
92
Input
61
Total output
56
Reasoning within output
git_grep f011
100%
Passed
Tokens
140
Input
116
Total output
110
Reasoning within output
git_grep f012
100%
Passed
Tokens
93
Input
88
Total output
75
Reasoning within output
git_log_format f001
100%
Passed
Tokens
945
Input
97
Total output
91
Reasoning within output
git_log_format f002
100%
Passed
Tokens
912
Input
109
Total output
97
Reasoning within output
git_log_format f003
100%
Passed
Tokens
743
Input
69
Total output
55
Reasoning within output
git_log_format f004
100%
Passed
Tokens
914
Input
71
Total output
66
Reasoning within output
git_log_format f005
100%
Passed
Tokens
765
Input
196
Total output
186
Reasoning within output
git_log_format f006
100%
Passed
Tokens
939
Input
194
Total output
188
Reasoning within output
git_log_format f007
100%
Passed
Tokens
935
Input
49
Total output
38
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,241
Input
124
Total output
118
Reasoning within output
git_log_format f009
100%
Passed
Tokens
770
Input
61
Total output
56
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,407
Input
70
Total output
65
Reasoning within output
git_log_format f011
100%
Passed
Tokens
478
Input
92
Total output
86
Reasoning within output
git_log_format f012
100%
Passed
Tokens
428
Input
102
Total output
96
Reasoning within output
git_show f001
100%
Passed
Tokens
222
Input
38
Total output
30
Reasoning within output
git_show f002
100%
Passed
Tokens
226
Input
125
Total output
118
Reasoning within output
git_show f003
100%
Passed
Tokens
715
Input
105
Total output
94
Reasoning within output
git_show f004
100%
Passed
Tokens
498
Input
73
Total output
62
Reasoning within output
git_show f005
100%
Passed
Tokens
227
Input
121
Total output
114
Reasoning within output
git_show f006
100%
Passed
Tokens
236
Input
46
Total output
40
Reasoning within output
git_show f007
100%
Passed
Tokens
230
Input
117
Total output
108
Reasoning within output
git_show f008
100%
Passed
Tokens
237
Input
108
Total output
67
Reasoning within output
git_show f009
100%
Passed
Tokens
347
Input
149
Total output
144
Reasoning within output
git_show f010
100%
Passed
Tokens
226
Input
67
Total output
61
Reasoning within output
git_show f011
100%
Passed
Tokens
253
Input
59
Total output
52
Reasoning within output
git_show f012
100%
Passed
Tokens
369
Input
70
Total output
65
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
114
Input
122
Total output
113
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
132
Input
194
Total output
178
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
107
Input
384
Total output
375
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
174
Input
355
Total output
321
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
166
Input
207
Total output
179
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
158
Input
173
Total output
141
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
162
Input
138
Total output
119
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
134
Input
88
Total output
73
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
131
Input
177
Total output
167
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
211
Input
219
Total output
176
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
175
Input
214
Total output
180
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
266
Input
486
Total output
425
Reasoning within output
rebase f001
0%
Failed
Tokens
127
Input
550
Total output
541
Reasoning within output
rebase f002
100%
Passed
Tokens
153
Input
136
Total output
120
Reasoning within output
rebase f003
100%
Passed
Tokens
133
Input
140
Total output
128
Reasoning within output
rebase f004
0%
Failed
Tokens
188
Input
829
Total output
797
Reasoning within output
rebase f005
0%
Failed
Tokens
170
Input
710
Total output
686
Reasoning within output
rebase f006
0%
Failed
Tokens
174
Input
189
Total output
153
Reasoning within output
rebase f007
100%
Passed
Tokens
166
Input
118
Total output
99
Reasoning within output
rebase f008
100%
Passed
Tokens
148
Input
459
Total output
444
Reasoning within output
rebase f009
100%
Passed
Tokens
133
Input
110
Total output
100
Reasoning within output
rebase f010
100%
Passed
Tokens
242
Input
213
Total output
170
Reasoning within output
rebase f011
100%
Passed
Tokens
186
Input
228
Total output
194
Reasoning within output
rebase f012
0%
Failed
Tokens
301
Input
391
Total output
331
Reasoning within output
reflog f001
100%
Passed
Tokens
285
Input
185
Total output
144
Reasoning within output
reflog f002
100%
Passed
Tokens
274
Input
611
Total output
231
Reasoning within output
reflog f003
100%
Passed
Tokens
250
Input
692
Total output
268
Reasoning within output
reflog f004
100%
Passed
Tokens
381
Input
776
Total output
392
Reasoning within output
reflog f005
100%
Passed
Tokens
438
Input
1,022
Total output
624
Reasoning within output
reflog f006
100%
Passed
Tokens
291
Input
640
Total output
316
Reasoning within output
reflog f007
100%
Passed
Tokens
332
Input
846
Total output
379
Reasoning within output
reflog f008
100%
Passed
Tokens
425
Input
534
Total output
238
Reasoning within output
reflog f009
100%
Passed
Tokens
379
Input
952
Total output
452
Reasoning within output
reflog f010
100%
Passed
Tokens
322
Input
736
Total output
382
Reasoning within output
reflog f011
100%
Passed
Tokens
380
Input
834
Total output
543
Reasoning within output
reflog f012
100%
Passed
Tokens
379
Input
1,120
Total output
702
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
168
Input
130
Total output
75
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
337
Input
386
Total output
223
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
155
Input
207
Total output
106
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
150
Input
156
Total output
87
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
159
Input
153
Total output
94
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
214
Input
161
Total output
91
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
243
Input
136
Total output
88
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
212
Input
227
Total output
91
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
242
Input
344
Total output
153
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
159
Input
165
Total output
85
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
151
Input
146
Total output
95
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
165
Input
254
Total output
117
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
72
Input
77
Total output
64
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
132
Input
170
Total output
154
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
138
Input
273
Total output
243
Reasoning within output
submodule_usage f004
0%
Failed
Tokens
122
Input
41
Total output
29
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
79
Input
269
Total output
235
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
126
Input
151
Total output
139
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
79
Input
107
Total output
81
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
128
Input
49
Total output
35
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
126
Input
39
Total output
27
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
135
Input
157
Total output
143
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
141
Input
41
Total output
32
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
77
Input
85
Total output
69
Reasoning within output
tag_management f001
100%
Passed
Tokens
92
Input
50
Total output
39
Reasoning within output
tag_management f002
100%
Passed
Tokens
87
Input
114
Total output
88
Reasoning within output
tag_management f003
100%
Passed
Tokens
96
Input
62
Total output
48
Reasoning within output
tag_management f004
100%
Passed
Tokens
102
Input
43
Total output
37
Reasoning within output
tag_management f005
100%
Passed
Tokens
114
Input
63
Total output
47
Reasoning within output
tag_management f006
100%
Passed
Tokens
99
Input
71
Total output
52
Reasoning within output
tag_management f007
100%
Passed
Tokens
96
Input
212
Total output
192
Reasoning within output
tag_management f008
100%
Passed
Tokens
100
Input
182
Total output
154
Reasoning within output
tag_management f009
100%
Passed
Tokens
102
Input
89
Total output
69
Reasoning within output
tag_management f010
100%
Passed
Tokens
80
Input
40
Total output
28
Reasoning within output
tag_management f011
100%
Passed
Tokens
81
Input
39
Total output
29
Reasoning within output
tag_management f012
100%
Passed
Tokens
123
Input
108
Total output
90
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
173
Input
63
Total output
45
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
180
Input
210
Total output
179
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
262
Input
45
Total output
32
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
254
Input
35
Total output
26
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
167
Input
103
Total output
83
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
176
Input
96
Total output
73
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
169
Input
97
Total output
73
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
200
Input
133
Total output
77
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
292
Input
37
Total output
28
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
258
Input
66
Total output
42
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
263
Input
48
Total output
35
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
169
Input
81
Total output
59
Reasoning within output