Qwen / qwen3.8-flash
medium
95.6%
195 / 204 fixtures · 1 run(s)
51,619 input / 107,572 total output / 103,319 reasoning within output tokens $0.05830169
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-14.2%
Text: 95.6% →
JSON: 81.4%
+5
Gained
JSON pass / text fail
−34
Lost
Text pass / JSON fail
161
Unchanged Pass
Both pass
4
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|---|---|---|
| f005 | 0% (0/1) | 100% (1/1) | -100% |
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| branch_cleanup | 100% | 33.3% | -66.7% |
| commit_squash | 100% | 41.7% | -58.3% |
| git_clean | 100% | 58.3% | -41.7% |
| submodule_usage | 91.7% | 58.3% | -33.3% |
| git_grep | 100% | 75% | -25% |
| reflog | 100% | 83.3% | -16.7% |
| cherry_pick | 83.3% | 91.7% | + 8.3% |
| rebase | 83.3% | 91.7% | + 8.3% |
| worktree_usage | 91.7% | 83.3% | -8.3% |
| blame_forensics | 100% | 91.7% | -8.3% |
| commit_messages | 91.7% | 100% | + 8.3% |
| git_log_format | 100% | 91.7% | -8.3% |
| git_bisect | 100% | 100% | + 0% |
| git_show | 91.7% | 91.7% | + 0% |
| merge_conflicts | 91.7% | 91.7% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
Changed Fixtures (39)
f001 -loss f001 -loss f003 -loss f004 -loss f008 -loss f009 -loss f010 -loss f011 -loss f012 -loss f004 +gain f005 +gain f001 -loss f002 -loss f003 -loss f004 -loss f008 -loss f009 -loss f012 -loss f001 -loss f004 -loss f007 -loss f008 -loss f011 -loss f004 -loss f006 -loss f007 -loss f012 -loss f002 +gain f005 -loss f004 +gain f001 -loss f008 -loss f003 -loss f004 -loss f006 -loss f007 -loss f006 -loss f007 -loss f008 +gain
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
311
Input
351
Total output
343
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
306
Input
159
Total output
152
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
337
Input
80
Total output
71
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
257
Input
130
Total output
122
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
326
Input
654
Total output
648
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
294
Input
887
Total output
881
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
278
Input
303
Total output
295
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
303
Input
210
Total output
203
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
261
Input
195
Total output
188
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
500
Input
383
Total output
377
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
305
Input
188
Total output
182
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
207
Input
336
Total output
328
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
159
Input
272
Total output
266
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
175
Input
220
Total output
212
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
155
Input
174
Total output
170
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
189
Input
182
Total output
174
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
164
Input
231
Total output
225
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
191
Input
216
Total output
204
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
160
Input
141
Total output
133
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
182
Input
238
Total output
226
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
138
Input
145
Total output
142
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
177
Input
364
Total output
356
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
128
Input
157
Total output
154
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
218
Input
301
Total output
288
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
150
Input
341
Total output
334
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
170
Input
2,490
Total output
2,480
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
145
Input
498
Total output
491
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
215
Input
3,652
Total output
3,626
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
203
Input
142
Total output
121
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
199
Input
212
Total output
187
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
187
Input
95
Total output
82
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
178
Input
56
Total output
47
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
161
Input
48
Total output
40
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
273
Input
204
Total output
173
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
221
Input
202
Total output
175
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
332
Input
836
Total output
788
Reasoning within output
commit_messages f001
84%
Passed
Tokens
168
Input
159
Total output
148
Reasoning within output
commit_messages f002
95%
Passed
Tokens
284
Input
222
Total output
215
Reasoning within output
commit_messages f003
91.5%
Passed
Tokens
139
Input
180
Total output
169
Reasoning within output
commit_messages f004
92.5%
Passed
Tokens
176
Input
72
Total output
66
Reasoning within output
commit_messages f005
32.5%
Failed
Tokens
160
Input
84
Total output
77
Reasoning within output
commit_messages f006
77.5%
Passed
Tokens
207
Input
168
Total output
159
Reasoning within output
commit_messages f007
90%
Passed
Tokens
248
Input
369
Total output
359
Reasoning within output
commit_messages f008
90%
Passed
Tokens
132
Input
96
Total output
89
Reasoning within output
commit_messages f009
89%
Passed
Tokens
186
Input
144
Total output
134
Reasoning within output
commit_messages f010
90%
Passed
Tokens
356
Input
251
Total output
241
Reasoning within output
commit_messages f011
77.5%
Passed
Tokens
205
Input
692
Total output
680
Reasoning within output
commit_messages f012
86.5%
Passed
Tokens
186
Input
219
Total output
211
Reasoning within output
commit_squash f001
100%
Passed
Tokens
199
Input
3,398
Total output
3,383
Reasoning within output
commit_squash f002
100%
Passed
Tokens
173
Input
215
Total output
204
Reasoning within output
commit_squash f003
100%
Passed
Tokens
188
Input
271
Total output
256
Reasoning within output
commit_squash f004
100%
Passed
Tokens
174
Input
241
Total output
227
Reasoning within output
commit_squash f005
100%
Passed
Tokens
172
Input
249
Total output
239
Reasoning within output
commit_squash f006
100%
Passed
Tokens
156
Input
177
Total output
163
Reasoning within output
commit_squash f007
100%
Passed
Tokens
162
Input
423
Total output
408
Reasoning within output
commit_squash f008
100%
Passed
Tokens
174
Input
166
Total output
151
Reasoning within output
commit_squash f009
100%
Passed
Tokens
168
Input
238
Total output
224
Reasoning within output
commit_squash f010
100%
Passed
Tokens
182
Input
873
Total output
855
Reasoning within output
commit_squash f011
100%
Passed
Tokens
185
Input
170
Total output
152
Reasoning within output
commit_squash f012
100%
Passed
Tokens
188
Input
3,664
Total output
3,641
Reasoning within output
git_bisect f001
100%
Passed
Tokens
245
Input
113
Total output
103
Reasoning within output
git_bisect f002
100%
Passed
Tokens
269
Input
159
Total output
150
Reasoning within output
git_bisect f003
100%
Passed
Tokens
265
Input
197
Total output
188
Reasoning within output
git_bisect f004
100%
Passed
Tokens
269
Input
186
Total output
177
Reasoning within output
git_bisect f005
100%
Passed
Tokens
271
Input
133
Total output
123
Reasoning within output
git_bisect f006
100%
Passed
Tokens
299
Input
164
Total output
154
Reasoning within output
git_bisect f007
100%
Passed
Tokens
269
Input
163
Total output
154
Reasoning within output
git_bisect f008
100%
Passed
Tokens
273
Input
77
Total output
67
Reasoning within output
git_bisect f009
100%
Passed
Tokens
269
Input
119
Total output
109
Reasoning within output
git_bisect f010
100%
Passed
Tokens
269
Input
141
Total output
133
Reasoning within output
git_bisect f011
100%
Passed
Tokens
277
Input
123
Total output
113
Reasoning within output
git_bisect f012
100%
Passed
Tokens
299
Input
194
Total output
184
Reasoning within output
git_clean f001
100%
Passed
Tokens
106
Input
141
Total output
131
Reasoning within output
git_clean f002
100%
Passed
Tokens
117
Input
534
Total output
527
Reasoning within output
git_clean f003
100%
Passed
Tokens
116
Input
347
Total output
340
Reasoning within output
git_clean f004
100%
Passed
Tokens
113
Input
226
Total output
218
Reasoning within output
git_clean f005
100%
Passed
Tokens
105
Input
182
Total output
175
Reasoning within output
git_clean f006
100%
Passed
Tokens
130
Input
1,331
Total output
1,322
Reasoning within output
git_clean f007
100%
Passed
Tokens
121
Input
219
Total output
208
Reasoning within output
git_clean f008
100%
Passed
Tokens
133
Input
184
Total output
177
Reasoning within output
git_clean f009
100%
Passed
Tokens
124
Input
310
Total output
300
Reasoning within output
git_clean f010
100%
Passed
Tokens
119
Input
194
Total output
187
Reasoning within output
git_clean f011
100%
Passed
Tokens
117
Input
558
Total output
550
Reasoning within output
git_clean f012
100%
Passed
Tokens
119
Input
549
Total output
539
Reasoning within output
git_grep f001
100%
Passed
Tokens
105
Input
61
Total output
55
Reasoning within output
git_grep f002
100%
Passed
Tokens
122
Input
91
Total output
87
Reasoning within output
git_grep f003
100%
Passed
Tokens
140
Input
63
Total output
59
Reasoning within output
git_grep f004
100%
Passed
Tokens
129
Input
100
Total output
92
Reasoning within output
git_grep f005
100%
Passed
Tokens
170
Input
142
Total output
138
Reasoning within output
git_grep f006
100%
Passed
Tokens
94
Input
159
Total output
155
Reasoning within output
git_grep f007
100%
Passed
Tokens
222
Input
2,198
Total output
2,193
Reasoning within output
git_grep f008
100%
Passed
Tokens
111
Input
70
Total output
66
Reasoning within output
git_grep f009
100%
Passed
Tokens
107
Input
83
Total output
77
Reasoning within output
git_grep f010
100%
Passed
Tokens
117
Input
279
Total output
275
Reasoning within output
git_grep f011
100%
Passed
Tokens
165
Input
183
Total output
179
Reasoning within output
git_grep f012
100%
Passed
Tokens
118
Input
112
Total output
101
Reasoning within output
git_log_format f001
100%
Passed
Tokens
947
Input
112
Total output
108
Reasoning within output
git_log_format f002
100%
Passed
Tokens
938
Input
125
Total output
115
Reasoning within output
git_log_format f003
100%
Passed
Tokens
791
Input
143
Total output
131
Reasoning within output
git_log_format f004
100%
Passed
Tokens
959
Input
52
Total output
48
Reasoning within output
git_log_format f005
100%
Passed
Tokens
790
Input
134
Total output
126
Reasoning within output
git_log_format f006
100%
Passed
Tokens
964
Input
182
Total output
178
Reasoning within output
git_log_format f007
100%
Passed
Tokens
977
Input
102
Total output
93
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,288
Input
31
Total output
28
Reasoning within output
git_log_format f009
100%
Passed
Tokens
779
Input
53
Total output
49
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,458
Input
103
Total output
99
Reasoning within output
git_log_format f011
100%
Passed
Tokens
496
Input
111
Total output
106
Reasoning within output
git_log_format f012
100%
Passed
Tokens
454
Input
70
Total output
67
Reasoning within output
git_show f001
100%
Passed
Tokens
253
Input
86
Total output
80
Reasoning within output
git_show f002
0%
Failed
Tokens
254
Input
1,194
Total output
1,189
Reasoning within output
git_show f003
100%
Passed
Tokens
744
Input
94
Total output
85
Reasoning within output
git_show f004
100%
Passed
Tokens
531
Input
78
Total output
69
Reasoning within output
git_show f005
100%
Passed
Tokens
256
Input
124
Total output
120
Reasoning within output
git_show f006
100%
Passed
Tokens
265
Input
70
Total output
67
Reasoning within output
git_show f007
100%
Passed
Tokens
255
Input
76
Total output
69
Reasoning within output
git_show f008
100%
Passed
Tokens
263
Input
191
Total output
152
Reasoning within output
git_show f009
100%
Passed
Tokens
374
Input
198
Total output
195
Reasoning within output
git_show f010
100%
Passed
Tokens
253
Input
174
Total output
170
Reasoning within output
git_show f011
100%
Passed
Tokens
280
Input
77
Total output
72
Reasoning within output
git_show f012
100%
Passed
Tokens
400
Input
104
Total output
100
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
139
Input
168
Total output
161
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
157
Input
566
Total output
556
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
132
Input
203
Total output
196
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
199
Input
1,884
Total output
1,856
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
191
Input
165
Total output
144
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
183
Input
346
Total output
321
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
187
Input
189
Total output
176
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
159
Input
97
Total output
88
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
156
Input
113
Total output
105
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
236
Input
292
Total output
261
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
200
Input
172
Total output
145
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
291
Input
636
Total output
590
Reasoning within output
rebase f001
100%
Passed
Tokens
153
Input
403
Total output
396
Reasoning within output
rebase f002
100%
Passed
Tokens
178
Input
185
Total output
175
Reasoning within output
rebase f003
100%
Passed
Tokens
158
Input
162
Total output
156
Reasoning within output
rebase f004
0%
Failed
Tokens
211
Input
8,963
Total output
8,937
Reasoning within output
rebase f005
100%
Passed
Tokens
198
Input
350
Total output
332
Reasoning within output
rebase f006
100%
Passed
Tokens
198
Input
362
Total output
337
Reasoning within output
rebase f007
100%
Passed
Tokens
192
Input
195
Total output
182
Reasoning within output
rebase f008
100%
Passed
Tokens
173
Input
326
Total output
317
Reasoning within output
rebase f009
100%
Passed
Tokens
157
Input
49
Total output
41
Reasoning within output
rebase f010
100%
Passed
Tokens
263
Input
911
Total output
878
Reasoning within output
rebase f011
100%
Passed
Tokens
211
Input
503
Total output
476
Reasoning within output
rebase f012
0%
Failed
Tokens
328
Input
1,343
Total output
1,297
Reasoning within output
reflog f001
100%
Passed
Tokens
315
Input
340
Total output
302
Reasoning within output
reflog f002
100%
Passed
Tokens
299
Input
364
Total output
214
Reasoning within output
reflog f003
100%
Passed
Tokens
273
Input
444
Total output
272
Reasoning within output
reflog f004
100%
Passed
Tokens
407
Input
1,240
Total output
996
Reasoning within output
reflog f005
100%
Passed
Tokens
467
Input
992
Total output
862
Reasoning within output
reflog f006
100%
Passed
Tokens
327
Input
527
Total output
323
Reasoning within output
reflog f007
100%
Passed
Tokens
360
Input
213
Total output
79
Reasoning within output
reflog f008
100%
Passed
Tokens
450
Input
1,167
Total output
1,049
Reasoning within output
reflog f009
100%
Passed
Tokens
410
Input
2,085
Total output
1,883
Reasoning within output
reflog f010
100%
Passed
Tokens
359
Input
655
Total output
551
Reasoning within output
reflog f011
100%
Passed
Tokens
399
Input
3,117
Total output
2,928
Reasoning within output
reflog f012
100%
Passed
Tokens
405
Input
4,290
Total output
4,021
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
191
Input
171
Total output
163
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
356
Input
89
Total output
75
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
180
Input
160
Total output
152
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
175
Input
171
Total output
162
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
187
Input
67
Total output
58
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
239
Input
109
Total output
100
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
272
Input
142
Total output
117
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
237
Input
727
Total output
691
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
267
Input
115
Total output
106
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
184
Input
75
Total output
66
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
179
Input
213
Total output
196
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
190
Input
167
Total output
158
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
97
Input
111
Total output
100
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
158
Input
3,085
Total output
3,073
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
161
Input
4,999
Total output
4,948
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
147
Input
215
Total output
209
Reasoning within output
submodule_usage f005
0%
Failed
submodule_usage f006
100%
Passed
Tokens
149
Input
6,677
Total output
6,672
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
104
Input
231
Total output
211
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
158
Input
99
Total output
89
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
153
Input
69
Total output
63
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
156
Input
213
Total output
204
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
158
Input
134
Total output
127
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
102
Input
132
Total output
118
Reasoning within output
tag_management f001
100%
Passed
Tokens
113
Input
113
Total output
104
Reasoning within output
tag_management f002
100%
Passed
Tokens
114
Input
201
Total output
180
Reasoning within output
tag_management f003
100%
Passed
Tokens
121
Input
78
Total output
66
Reasoning within output
tag_management f004
100%
Passed
Tokens
127
Input
160
Total output
155
Reasoning within output
tag_management f005
100%
Passed
Tokens
140
Input
205
Total output
195
Reasoning within output
tag_management f006
100%
Passed
Tokens
126
Input
229
Total output
212
Reasoning within output
tag_management f007
100%
Passed
Tokens
121
Input
567
Total output
553
Reasoning within output
tag_management f008
100%
Passed
Tokens
124
Input
648
Total output
619
Reasoning within output
tag_management f009
100%
Passed
Tokens
127
Input
170
Total output
151
Reasoning within output
tag_management f010
100%
Passed
Tokens
104
Input
67
Total output
57
Reasoning within output
tag_management f011
100%
Passed
Tokens
107
Input
146
Total output
138
Reasoning within output
tag_management f012
100%
Passed
Tokens
149
Input
1,055
Total output
1,043
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
201
Input
154
Total output
142
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
209
Input
468
Total output
445
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
280
Input
202
Total output
191
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
281
Input
82
Total output
75
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
190
Input
269
Total output
255
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
196
Input
143
Total output
126
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
200
Input
1,891
Total output
1,869
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
220
Input
5,586
Total output
5,531
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
312
Input
718
Total output
711
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
282
Input
232
Total output
213
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
277
Input
112
Total output
101
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
191
Input
85
Total output
69
Reasoning within output