Qwen / qwen3.8-max
high
94.1%
192 / 204 fixtures · 1 run(s)
48,599 input / 133,596 total output / 128,483 reasoning within output tokens $0.89877400
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-15.7%
Text: 94.1% →
JSON: 78.4%
+2
Gained
JSON pass / text fail
−34
Lost
Text pass / JSON fail
158
Unchanged Pass
Both pass
10
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| branch_cleanup | 100% | 58.3% | -41.7% |
| reflog | 100% | 58.3% | -41.7% |
| commit_squash | 91.7% | 58.3% | -33.3% |
| git_log_format | 100% | 66.7% | -33.3% |
| merge_conflicts | 83.3% | 58.3% | -25% |
| git_clean | 100% | 83.3% | -16.7% |
| git_grep | 100% | 83.3% | -16.7% |
| submodule_usage | 100% | 83.3% | -16.7% |
| tag_management | 100% | 83.3% | -16.7% |
| cherry_pick | 83.3% | 66.7% | -16.7% |
| git_show | 100% | 91.7% | -8.3% |
| blame_forensics | 91.7% | 91.7% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| rebase | 75% | 75% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| worktree_usage | 75% | 75% | + 0% |
Changed Fixtures (36)
f003 -loss f007 -loss f008 -loss f009 -loss f011 -loss f003 -loss f010 -loss f003 +gain f008 -loss f009 -loss f010 -loss f011 -loss f012 -loss f005 -loss f012 -loss f006 -loss f007 -loss f002 -loss f003 -loss f005 -loss f012 -loss f006 -loss f001 -loss f002 -loss f010 -loss f005 +gain f011 -loss f002 -loss f003 -loss f004 -loss f009 -loss f011 -loss f002 -loss f003 -loss f007 -loss f008 -loss
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
297
Input
208
Total output
198
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
290
Input
226
Total output
217
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
322
Input
82
Total output
71
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
243
Input
254
Total output
244
Reasoning within output
blame_forensics f005
0%
Failed
blame_forensics f006
100%
Passed
Tokens
287
Input
306
Total output
298
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
265
Input
98
Total output
88
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
293
Input
461
Total output
452
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
249
Input
147
Total output
138
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
483
Input
400
Total output
392
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
293
Input
212
Total output
204
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
189
Input
160
Total output
150
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
151
Input
126
Total output
118
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
167
Input
264
Total output
254
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
142
Input
116
Total output
110
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
180
Input
183
Total output
173
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
153
Input
159
Total output
151
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
178
Input
234
Total output
220
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
150
Input
206
Total output
196
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
169
Input
254
Total output
240
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
127
Input
133
Total output
127
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
162
Input
242
Total output
232
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
115
Input
147
Total output
141
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
206
Input
157
Total output
142
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
137
Input
289
Total output
280
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
157
Input
265
Total output
253
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
131
Input
486
Total output
477
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
200
Input
644
Total output
616
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
193
Input
218
Total output
195
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
185
Input
149
Total output
118
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
175
Input
168
Total output
153
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
62
Total output
52
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
258
Input
540
Total output
507
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
208
Input
182
Total output
153
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
319
Input
3,889
Total output
3,839
Reasoning within output
commit_messages f001
95.7%
Passed
Tokens
155
Input
253
Total output
245
Reasoning within output
commit_messages f002
91%
Passed
Tokens
271
Input
327
Total output
318
Reasoning within output
commit_messages f003
93.3%
Passed
Tokens
126
Input
185
Total output
172
Reasoning within output
commit_messages f004
95%
Passed
Tokens
163
Input
57
Total output
49
Reasoning within output
commit_messages f005
88.3%
Passed
Tokens
147
Input
103
Total output
94
Reasoning within output
commit_messages f006
91.7%
Passed
Tokens
194
Input
84
Total output
73
Reasoning within output
commit_messages f007
91%
Passed
Tokens
235
Input
214
Total output
203
Reasoning within output
commit_messages f008
90%
Passed
Tokens
119
Input
80
Total output
71
Reasoning within output
commit_messages f009
85%
Passed
Tokens
173
Input
206
Total output
194
Reasoning within output
commit_messages f010
89.3%
Passed
Tokens
343
Input
381
Total output
369
Reasoning within output
commit_messages f011
66.7%
Passed
Tokens
192
Input
476
Total output
460
Reasoning within output
commit_messages f012
89%
Passed
Tokens
173
Input
155
Total output
145
Reasoning within output
commit_squash f001
100%
Passed
Tokens
182
Input
4,297
Total output
4,280
Reasoning within output
commit_squash f002
100%
Passed
Tokens
164
Input
146
Total output
133
Reasoning within output
commit_squash f003
50%
Failed
Tokens
175
Input
12,172
Total output
12,162
Reasoning within output
commit_squash f004
100%
Passed
Tokens
164
Input
345
Total output
329
Reasoning within output
commit_squash f005
100%
Passed
Tokens
158
Input
236
Total output
224
Reasoning within output
commit_squash f006
100%
Passed
Tokens
146
Input
159
Total output
143
Reasoning within output
commit_squash f007
100%
Passed
Tokens
150
Input
170
Total output
153
Reasoning within output
commit_squash f008
100%
Passed
Tokens
162
Input
164
Total output
147
Reasoning within output
commit_squash f009
100%
Passed
Tokens
151
Input
173
Total output
157
Reasoning within output
commit_squash f010
100%
Passed
Tokens
168
Input
132
Total output
112
Reasoning within output
commit_squash f011
100%
Passed
Tokens
175
Input
89
Total output
69
Reasoning within output
commit_squash f012
100%
Passed
Tokens
175
Input
190
Total output
165
Reasoning within output
git_bisect f001
100%
Passed
Tokens
232
Input
125
Total output
111
Reasoning within output
git_bisect f002
100%
Passed
Tokens
258
Input
96
Total output
85
Reasoning within output
git_bisect f003
100%
Passed
Tokens
250
Input
166
Total output
155
Reasoning within output
git_bisect f004
100%
Passed
Tokens
254
Input
230
Total output
218
Reasoning within output
git_bisect f005
100%
Passed
Tokens
254
Input
112
Total output
101
Reasoning within output
git_bisect f006
100%
Passed
Tokens
290
Input
110
Total output
98
Reasoning within output
git_bisect f007
100%
Passed
Tokens
258
Input
102
Total output
91
Reasoning within output
git_bisect f008
100%
Passed
Tokens
262
Input
80
Total output
68
Reasoning within output
git_bisect f009
100%
Passed
Tokens
256
Input
116
Total output
104
Reasoning within output
git_bisect f010
100%
Passed
Tokens
260
Input
169
Total output
157
Reasoning within output
git_bisect f011
100%
Passed
Tokens
254
Input
94
Total output
84
Reasoning within output
git_bisect f012
100%
Passed
Tokens
286
Input
80
Total output
69
Reasoning within output
git_clean f001
100%
Passed
Tokens
93
Input
162
Total output
150
Reasoning within output
git_clean f002
100%
Passed
Tokens
104
Input
166
Total output
157
Reasoning within output
git_clean f003
100%
Passed
Tokens
103
Input
99
Total output
90
Reasoning within output
git_clean f004
100%
Passed
Tokens
100
Input
185
Total output
175
Reasoning within output
git_clean f005
100%
Passed
Tokens
92
Input
266
Total output
257
Reasoning within output
git_clean f006
100%
Passed
Tokens
117
Input
353
Total output
341
Reasoning within output
git_clean f007
100%
Passed
Tokens
108
Input
258
Total output
245
Reasoning within output
git_clean f008
100%
Passed
Tokens
120
Input
237
Total output
228
Reasoning within output
git_clean f009
100%
Passed
Tokens
111
Input
239
Total output
227
Reasoning within output
git_clean f010
100%
Passed
Tokens
106
Input
187
Total output
178
Reasoning within output
git_clean f011
100%
Passed
Tokens
104
Input
210
Total output
200
Reasoning within output
git_clean f012
100%
Passed
Tokens
106
Input
212
Total output
200
Reasoning within output
git_grep f001
100%
Passed
Tokens
92
Input
60
Total output
52
Reasoning within output
git_grep f002
100%
Passed
Tokens
105
Input
86
Total output
80
Reasoning within output
git_grep f003
100%
Passed
Tokens
127
Input
38
Total output
32
Reasoning within output
git_grep f004
100%
Passed
Tokens
116
Input
64
Total output
54
Reasoning within output
git_grep f005
100%
Passed
Tokens
157
Input
54
Total output
48
Reasoning within output
git_grep f006
100%
Passed
Tokens
81
Input
202
Total output
196
Reasoning within output
git_grep f007
100%
Passed
Tokens
209
Input
1,641
Total output
1,634
Reasoning within output
git_grep f008
100%
Passed
Tokens
98
Input
74
Total output
68
Reasoning within output
git_grep f009
100%
Passed
Tokens
94
Input
86
Total output
78
Reasoning within output
git_grep f010
100%
Passed
Tokens
104
Input
191
Total output
185
Reasoning within output
git_grep f011
100%
Passed
Tokens
152
Input
114
Total output
108
Reasoning within output
git_grep f012
100%
Passed
Tokens
105
Input
64
Total output
51
Reasoning within output
git_log_format f001
100%
Passed
Tokens
936
Input
127
Total output
121
Reasoning within output
git_log_format f002
100%
Passed
Tokens
929
Input
89
Total output
77
Reasoning within output
git_log_format f003
100%
Passed
Tokens
754
Input
113
Total output
99
Reasoning within output
git_log_format f004
100%
Passed
Tokens
936
Input
51
Total output
45
Reasoning within output
git_log_format f005
100%
Passed
Tokens
777
Input
131
Total output
121
Reasoning within output
git_log_format f006
100%
Passed
Tokens
951
Input
151
Total output
145
Reasoning within output
git_log_format f007
100%
Passed
Tokens
954
Input
81
Total output
70
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,249
Input
43
Total output
37
Reasoning within output
git_log_format f009
100%
Passed
Tokens
771
Input
79
Total output
73
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,418
Input
71
Total output
66
Reasoning within output
git_log_format f011
100%
Passed
Tokens
492
Input
92
Total output
86
Reasoning within output
git_log_format f012
100%
Passed
Tokens
447
Input
64
Total output
58
Reasoning within output
git_show f001
100%
Passed
Tokens
238
Input
153
Total output
145
Reasoning within output
git_show f002
100%
Passed
Tokens
235
Input
883
Total output
876
Reasoning within output
git_show f003
100%
Passed
Tokens
735
Input
86
Total output
75
Reasoning within output
git_show f004
100%
Passed
Tokens
508
Input
91
Total output
80
Reasoning within output
git_show f005
100%
Passed
Tokens
246
Input
110
Total output
103
Reasoning within output
git_show f006
100%
Passed
Tokens
254
Input
72
Total output
66
Reasoning within output
git_show f007
100%
Passed
Tokens
242
Input
156
Total output
147
Reasoning within output
git_show f008
100%
Passed
Tokens
250
Input
138
Total output
97
Reasoning within output
git_show f009
100%
Passed
Tokens
354
Input
93
Total output
88
Reasoning within output
git_show f010
100%
Passed
Tokens
237
Input
211
Total output
205
Reasoning within output
git_show f011
100%
Passed
Tokens
264
Input
79
Total output
72
Reasoning within output
git_show f012
100%
Passed
Tokens
382
Input
61
Total output
55
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
126
Input
428
Total output
419
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
144
Input
232
Total output
220
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
119
Input
2,776
Total output
2,767
Reasoning within output
merge_conflicts f004
0%
Failed
Tokens
186
Input
4,419
Total output
4,391
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
178
Input
166
Total output
143
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
170
Input
412
Total output
385
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
174
Input
107
Total output
92
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
146
Input
103
Total output
92
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
143
Input
170
Total output
160
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
223
Input
306
Total output
273
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
187
Input
125
Total output
96
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
278
Input
5,500
Total output
5,450
Reasoning within output
rebase f001
100%
Passed
Tokens
139
Input
1,153
Total output
1,144
Reasoning within output
rebase f002
100%
Passed
Tokens
166
Input
180
Total output
168
Reasoning within output
rebase f003
100%
Passed
Tokens
144
Input
193
Total output
185
Reasoning within output
rebase f004
0%
Failed
Tokens
201
Input
9,076
Total output
9,048
Reasoning within output
rebase f005
0%
Failed
Tokens
185
Input
8,341
Total output
8,322
Reasoning within output
rebase f006
100%
Passed
Tokens
184
Input
614
Total output
587
Reasoning within output
rebase f007
100%
Passed
Tokens
179
Input
233
Total output
218
Reasoning within output
rebase f008
100%
Passed
Tokens
159
Input
134
Total output
123
Reasoning within output
rebase f009
100%
Passed
Tokens
142
Input
179
Total output
169
Reasoning within output
rebase f010
100%
Passed
Tokens
254
Input
1,256
Total output
1,223
Reasoning within output
rebase f011
100%
Passed
Tokens
199
Input
553
Total output
524
Reasoning within output
rebase f012
0%
Failed
Tokens
313
Input
4,004
Total output
3,954
Reasoning within output
reflog f001
100%
Passed
Tokens
303
Input
365
Total output
324
Reasoning within output
reflog f002
100%
Passed
Tokens
285
Input
269
Total output
167
Reasoning within output
reflog f003
100%
Passed
Tokens
256
Input
393
Total output
227
Reasoning within output
reflog f004
100%
Passed
Tokens
378
Input
1,650
Total output
1,377
Reasoning within output
reflog f005
100%
Passed
Tokens
437
Input
802
Total output
554
Reasoning within output
reflog f006
100%
Passed
Tokens
302
Input
853
Total output
684
Reasoning within output
reflog f007
100%
Passed
Tokens
349
Input
1,024
Total output
847
Reasoning within output
reflog f008
100%
Passed
Tokens
434
Input
745
Total output
490
Reasoning within output
reflog f009
100%
Passed
Tokens
397
Input
1,185
Total output
1,048
Reasoning within output
reflog f010
100%
Passed
Tokens
344
Input
1,435
Total output
1,202
Reasoning within output
reflog f011
100%
Passed
Tokens
390
Input
4,919
Total output
4,611
Reasoning within output
reflog f012
100%
Passed
Tokens
388
Input
2,707
Total output
2,348
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
179
Input
86
Total output
76
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
340
Input
134
Total output
123
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
167
Input
115
Total output
104
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
162
Input
127
Total output
116
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
173
Input
236
Total output
225
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
226
Input
102
Total output
91
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
259
Input
165
Total output
154
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
224
Input
249
Total output
238
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
254
Input
266
Total output
243
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
171
Input
178
Total output
157
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
163
Input
289
Total output
278
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
177
Input
173
Total output
162
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
84
Input
125
Total output
112
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
146
Input
444
Total output
430
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
148
Input
5,768
Total output
5,740
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
134
Input
174
Total output
166
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
91
Input
293
Total output
263
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
135
Input
4,522
Total output
4,514
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
91
Input
354
Total output
332
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
138
Input
534
Total output
524
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
139
Input
109
Total output
101
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
144
Input
221
Total output
210
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
147
Input
76
Total output
67
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
89
Input
123
Total output
107
Reasoning within output
tag_management f001
100%
Passed
Tokens
105
Input
109
Total output
98
Reasoning within output
tag_management f002
100%
Passed
Tokens
98
Input
167
Total output
144
Reasoning within output
tag_management f003
100%
Passed
Tokens
106
Input
141
Total output
127
Reasoning within output
tag_management f004
100%
Passed
Tokens
115
Input
185
Total output
179
Reasoning within output
tag_management f005
100%
Passed
Tokens
125
Input
128
Total output
116
Reasoning within output
tag_management f006
100%
Passed
Tokens
112
Input
169
Total output
151
Reasoning within output
tag_management f007
100%
Passed
Tokens
106
Input
4,783
Total output
4,763
Reasoning within output
tag_management f008
100%
Passed
Tokens
111
Input
262
Total output
234
Reasoning within output
tag_management f009
100%
Passed
Tokens
115
Input
376
Total output
355
Reasoning within output
tag_management f010
100%
Passed
Tokens
92
Input
91
Total output
79
Reasoning within output
tag_management f011
100%
Passed
Tokens
93
Input
170
Total output
160
Reasoning within output
tag_management f012
100%
Passed
Tokens
133
Input
980
Total output
966
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
189
Input
249
Total output
235
Reasoning within output
worktree_usage f002
0%
Failed
Tokens
196
Input
1,749
Total output
1,722
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
265
Input
108
Total output
95
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
261
Input
72
Total output
63
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
178
Input
229
Total output
213
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
184
Input
278
Total output
259
Reasoning within output
worktree_usage f007
0%
Failed
Tokens
183
Input
3,977
Total output
3,949
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
209
Input
4,291
Total output
4,235
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
298
Input
334
Total output
325
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
270
Input
181
Total output
161
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
265
Input
105
Total output
92
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
180
Input
124
Total output
106
Reasoning within output