Deepseek / deepseek-v4-flash
high
95.6%
195 / 204 fixtures · 1 run(s)
34,705 input / 56,237 total output / 53,048 reasoning within output tokens $0.01864862
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-20.6%
Text: 95.6% →
JSON: 75%
+2
Gained
JSON pass / text fail
−44
Lost
Text pass / JSON fail
151
Unchanged Pass
Both pass
7
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| branch_cleanup | 100% | 58.3% | -41.7% |
| commit_squash | 91.7% | 58.3% | -33.3% |
| tag_management | 91.7% | 58.3% | -33.3% |
| blame_forensics | 100% | 75% | -25% |
| git_grep | 100% | 75% | -25% |
| merge_conflicts | 91.7% | 66.7% | -25% |
| rebase | 91.7% | 66.7% | -25% |
| reflog | 100% | 75% | -25% |
| worktree_usage | 91.7% | 66.7% | -25% |
| commit_messages | 100% | 83.3% | -16.7% |
| git_clean | 100% | 83.3% | -16.7% |
| git_log_format | 100% | 83.3% | -16.7% |
| git_show | 91.7% | 75% | -16.7% |
| cherry_pick | 83.3% | 66.7% | -16.7% |
| submodule_usage | 91.7% | 83.3% | -8.3% |
| git_bisect | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
Changed Fixtures (46)
f003 -loss f008 -loss f009 -loss f001 -loss f003 -loss f004 -loss f009 -loss f011 -loss f001 -loss f004 +gain f007 -loss f010 -loss f007 -loss f010 -loss f002 -loss f003 -loss f009 -loss f010 -loss f005 -loss f011 -loss f007 -loss f010 -loss f011 -loss f006 -loss f010 -loss f007 -loss f010 -loss f001 -loss f004 -loss f011 -loss f001 -loss f004 -loss f011 -loss f004 -loss f005 -loss f009 -loss f003 +gain f007 -loss f010 -loss f003 -loss f007 -loss f011 -loss f012 -loss f004 -loss f007 -loss f010 -loss
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
229
Input
359
Total output
355
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
204
Input
491
Total output
485
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
232
Input
70
Total output
63
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
164
Input
557
Total output
550
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
222
Input
304
Total output
306
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
203
Input
341
Total output
345
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
183
Input
204
Total output
197
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
208
Input
487
Total output
481
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
176
Input
363
Total output
328
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
361
Input
295
Total output
309
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
196
Input
128
Total output
123
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
128
Input
325
Total output
343
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
99
Input
127
Total output
123
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
110
Input
105
Total output
99
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
92
Input
129
Total output
125
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
125
Input
126
Total output
128
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
118
Input
118
Total output
113
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
117
Input
103
Total output
96
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
101
Input
117
Total output
111
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
119
Input
198
Total output
186
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
78
Input
146
Total output
143
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
111
Input
108
Total output
101
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
68
Input
65
Total output
62
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
149
Input
157
Total output
143
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
94
Input
307
Total output
347
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
120
Input
574
Total output
566
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
89
Input
391
Total output
436
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
145
Input
804
Total output
785
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
148
Input
139
Total output
139
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
134
Input
130
Total output
103
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
147
Input
155
Total output
144
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
123
Input
76
Total output
68
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
108
Input
95
Total output
89
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
213
Input
209
Total output
183
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
161
Input
154
Total output
113
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
262
Input
1,123
Total output
1,080
Reasoning within output
commit_messages f001
95%
Passed
Tokens
100
Input
98
Total output
93
Reasoning within output
commit_messages f002
93.3%
Passed
Tokens
196
Input
244
Total output
234
Reasoning within output
commit_messages f003
94.3%
Passed
Tokens
81
Input
116
Total output
101
Reasoning within output
commit_messages f004
94%
Passed
Tokens
108
Input
114
Total output
109
Reasoning within output
commit_messages f005
90%
Passed
Tokens
96
Input
187
Total output
181
Reasoning within output
commit_messages f006
90%
Passed
Tokens
131
Input
253
Total output
246
Reasoning within output
commit_messages f007
91%
Passed
Tokens
180
Input
254
Total output
257
Reasoning within output
commit_messages f008
95%
Passed
Tokens
66
Input
200
Total output
195
Reasoning within output
commit_messages f009
89.7%
Passed
Tokens
119
Input
157
Total output
148
Reasoning within output
commit_messages f010
91.7%
Passed
Tokens
266
Input
131
Total output
123
Reasoning within output
commit_messages f011
90%
Passed
Tokens
137
Input
425
Total output
414
Reasoning within output
commit_messages f012
90.7%
Passed
Tokens
120
Input
156
Total output
148
Reasoning within output
commit_squash f001
100%
Passed
Tokens
129
Input
546
Total output
557
Reasoning within output
commit_squash f002
100%
Passed
Tokens
111
Input
206
Total output
197
Reasoning within output
commit_squash f003
100%
Passed
Tokens
124
Input
443
Total output
429
Reasoning within output
commit_squash f004
100%
Failed
Tokens
112
Input
149
Total output
132
Reasoning within output
commit_squash f005
100%
Passed
Tokens
107
Input
479
Total output
470
Reasoning within output
commit_squash f006
100%
Passed
Tokens
95
Input
79
Total output
71
Reasoning within output
commit_squash f007
100%
Passed
Tokens
97
Input
293
Total output
279
Reasoning within output
commit_squash f008
100%
Passed
Tokens
108
Input
213
Total output
206
Reasoning within output
commit_squash f009
100%
Passed
Tokens
98
Input
276
Total output
270
Reasoning within output
commit_squash f010
100%
Passed
Tokens
115
Input
188
Total output
171
Reasoning within output
commit_squash f011
100%
Passed
Tokens
126
Input
226
Total output
209
Reasoning within output
commit_squash f012
100%
Passed
Tokens
120
Input
263
Total output
241
Reasoning within output
git_bisect f001
100%
Passed
Tokens
164
Input
106
Total output
101
Reasoning within output
git_bisect f002
100%
Passed
Tokens
187
Input
145
Total output
139
Reasoning within output
git_bisect f003
100%
Passed
Tokens
189
Input
158
Total output
152
Reasoning within output
git_bisect f004
100%
Passed
Tokens
189
Input
77
Total output
71
Reasoning within output
git_bisect f005
100%
Passed
Tokens
187
Input
102
Total output
96
Reasoning within output
git_bisect f006
100%
Passed
Tokens
222
Input
199
Total output
191
Reasoning within output
git_bisect f007
100%
Passed
Tokens
189
Input
129
Total output
125
Reasoning within output
git_bisect f008
100%
Passed
Tokens
195
Input
113
Total output
106
Reasoning within output
git_bisect f009
100%
Passed
Tokens
193
Input
95
Total output
89
Reasoning within output
git_bisect f010
100%
Passed
Tokens
183
Input
131
Total output
121
Reasoning within output
git_bisect f011
100%
Passed
Tokens
187
Input
136
Total output
129
Reasoning within output
git_bisect f012
100%
Passed
Tokens
224
Input
105
Total output
99
Reasoning within output
git_clean f001
100%
Passed
Tokens
49
Input
501
Total output
495
Reasoning within output
git_clean f002
100%
Passed
Tokens
59
Input
104
Total output
95
Reasoning within output
git_clean f003
100%
Passed
Tokens
57
Input
128
Total output
124
Reasoning within output
git_clean f004
100%
Passed
Tokens
57
Input
273
Total output
266
Reasoning within output
git_clean f005
100%
Passed
Tokens
47
Input
451
Total output
420
Reasoning within output
git_clean f006
100%
Passed
Tokens
74
Input
506
Total output
506
Reasoning within output
git_clean f007
100%
Passed
Tokens
69
Input
230
Total output
208
Reasoning within output
git_clean f008
100%
Passed
Tokens
72
Input
171
Total output
167
Reasoning within output
git_clean f009
100%
Passed
Tokens
67
Input
749
Total output
739
Reasoning within output
git_clean f010
100%
Passed
Tokens
63
Input
244
Total output
238
Reasoning within output
git_clean f011
100%
Passed
Tokens
60
Input
294
Total output
284
Reasoning within output
git_clean f012
100%
Passed
Tokens
63
Input
697
Total output
688
Reasoning within output
git_grep f001
100%
Passed
Tokens
52
Input
76
Total output
71
Reasoning within output
git_grep f002
100%
Passed
Tokens
60
Input
38
Total output
35
Reasoning within output
git_grep f003
100%
Passed
Tokens
84
Input
45
Total output
42
Reasoning within output
git_grep f004
100%
Passed
Tokens
72
Input
57
Total output
50
Reasoning within output
git_grep f005
100%
Passed
Tokens
107
Input
65
Total output
62
Reasoning within output
git_grep f006
100%
Passed
Tokens
37
Input
283
Total output
280
Reasoning within output
git_grep f007
100%
Passed
Tokens
156
Input
1,760
Total output
1,757
Reasoning within output
git_grep f008
100%
Passed
Tokens
57
Input
68
Total output
65
Reasoning within output
git_grep f009
100%
Passed
Tokens
50
Input
52
Total output
40
Reasoning within output
git_grep f010
100%
Passed
Tokens
60
Input
128
Total output
125
Reasoning within output
git_grep f011
100%
Passed
Tokens
114
Input
216
Total output
213
Reasoning within output
git_grep f012
100%
Passed
Tokens
64
Input
163
Total output
153
Reasoning within output
git_log_format f001
100%
Passed
Tokens
704
Input
99
Total output
96
Reasoning within output
git_log_format f002
100%
Passed
Tokens
702
Input
111
Total output
102
Reasoning within output
git_log_format f003
100%
Passed
Tokens
571
Input
58
Total output
47
Reasoning within output
git_log_format f004
100%
Passed
Tokens
715
Input
80
Total output
77
Reasoning within output
git_log_format f005
100%
Passed
Tokens
573
Input
109
Total output
91
Reasoning within output
git_log_format f006
100%
Passed
Tokens
703
Input
93
Total output
90
Reasoning within output
git_log_format f007
100%
Passed
Tokens
718
Input
97
Total output
90
Reasoning within output
git_log_format f008
100%
Passed
Tokens
952
Input
40
Total output
37
Reasoning within output
git_log_format f009
100%
Passed
Tokens
547
Input
50
Total output
43
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,081
Input
103
Total output
100
Reasoning within output
git_log_format f011
100%
Passed
Tokens
346
Input
130
Total output
126
Reasoning within output
git_log_format f012
100%
Passed
Tokens
319
Input
42
Total output
40
Reasoning within output
git_show f001
100%
Passed
Tokens
171
Input
82
Total output
62
Reasoning within output
git_show f002
100%
Passed
Tokens
166
Input
572
Total output
569
Reasoning within output
git_show f003
0%
Failed
Tokens
563
Input
93
Total output
69
Reasoning within output
git_show f004
100%
Passed
Tokens
390
Input
68
Total output
60
Reasoning within output
git_show f005
100%
Passed
Tokens
172
Input
155
Total output
159
Reasoning within output
git_show f006
100%
Passed
Tokens
179
Input
66
Total output
64
Reasoning within output
git_show f007
100%
Passed
Tokens
162
Input
81
Total output
75
Reasoning within output
git_show f008
100%
Passed
Tokens
181
Input
91
Total output
52
Reasoning within output
git_show f009
100%
Passed
Tokens
261
Input
100
Total output
97
Reasoning within output
git_show f010
100%
Passed
Tokens
168
Input
115
Total output
113
Reasoning within output
git_show f011
100%
Passed
Tokens
199
Input
48
Total output
44
Reasoning within output
git_show f012
100%
Passed
Tokens
294
Input
70
Total output
67
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
84
Input
331
Total output
326
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
109
Input
630
Total output
620
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
79
Input
442
Total output
436
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
134
Input
674
Total output
693
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
136
Input
132
Total output
125
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
122
Input
269
Total output
248
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
130
Input
305
Total output
286
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
106
Input
82
Total output
76
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
103
Input
327
Total output
320
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
178
Input
320
Total output
295
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
142
Input
132
Total output
93
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
231
Input
375
Total output
333
Reasoning within output
rebase f001
100%
Passed
Tokens
93
Input
429
Total output
423
Reasoning within output
rebase f002
100%
Passed
Tokens
127
Input
95
Total output
86
Reasoning within output
rebase f003
100%
Passed
Tokens
102
Input
113
Total output
109
Reasoning within output
rebase f004
100%
Passed
Tokens
145
Input
3,168
Total output
3,542
Reasoning within output
rebase f005
100%
Passed
Tokens
140
Input
95
Total output
94
Reasoning within output
rebase f006
100%
Passed
Tokens
135
Input
213
Total output
189
Reasoning within output
rebase f007
100%
Passed
Tokens
132
Input
149
Total output
138
Reasoning within output
rebase f008
100%
Passed
Tokens
119
Input
219
Total output
216
Reasoning within output
rebase f009
100%
Passed
Tokens
102
Input
124
Total output
118
Reasoning within output
rebase f010
100%
Passed
Tokens
203
Input
419
Total output
393
Reasoning within output
rebase f011
100%
Passed
Tokens
152
Input
500
Total output
400
Reasoning within output
rebase f012
0%
Failed
Tokens
262
Input
519
Total output
478
Reasoning within output
reflog f001
100%
Passed
Tokens
200
Input
322
Total output
239
Reasoning within output
reflog f002
100%
Passed
Tokens
190
Input
118
Total output
85
Reasoning within output
reflog f003
100%
Passed
Tokens
168
Input
184
Total output
113
Reasoning within output
reflog f004
100%
Passed
Tokens
266
Input
1,111
Total output
736
Reasoning within output
reflog f005
100%
Passed
Tokens
317
Input
3,298
Total output
3,248
Reasoning within output
reflog f006
100%
Passed
Tokens
204
Input
445
Total output
369
Reasoning within output
reflog f007
100%
Passed
Tokens
235
Input
164
Total output
65
Reasoning within output
reflog f008
100%
Passed
Tokens
297
Input
1,120
Total output
1,027
Reasoning within output
reflog f009
100%
Passed
Tokens
278
Input
1,019
Total output
826
Reasoning within output
reflog f010
100%
Passed
Tokens
229
Input
240
Total output
219
Reasoning within output
reflog f011
100%
Passed
Tokens
265
Input
1,099
Total output
966
Reasoning within output
reflog f012
100%
Passed
Tokens
262
Input
1,729
Total output
1,344
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
122
Input
60
Total output
53
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
266
Input
153
Total output
139
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
111
Input
129
Total output
89
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
110
Input
97
Total output
80
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
121
Input
98
Total output
78
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
167
Input
151
Total output
129
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
194
Input
156
Total output
145
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
163
Input
115
Total output
94
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
198
Input
147
Total output
126
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
118
Input
107
Total output
86
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
108
Input
266
Total output
220
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
127
Input
96
Total output
79
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
40
Input
53
Total output
42
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
88
Input
248
Total output
237
Reasoning within output
submodule_usage f003
0%
Failed
Tokens
93
Input
855
Total output
860
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
84
Input
78
Total output
72
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
47
Input
251
Total output
241
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
80
Input
353
Total output
389
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
48
Input
135
Total output
115
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
81
Input
87
Total output
79
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
81
Input
89
Total output
85
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
89
Input
295
Total output
286
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
98
Input
71
Total output
65
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
46
Input
71
Total output
59
Reasoning within output
tag_management f001
100%
Passed
Tokens
53
Input
56
Total output
48
Reasoning within output
tag_management f002
100%
Passed
Tokens
52
Input
91
Total output
71
Reasoning within output
tag_management f003
100%
Passed
Tokens
58
Input
247
Total output
237
Reasoning within output
tag_management f004
100%
Passed
Tokens
61
Input
98
Total output
81
Reasoning within output
tag_management f005
100%
Passed
Tokens
74
Input
81
Total output
61
Reasoning within output
tag_management f006
100%
Passed
Tokens
57
Input
82
Total output
58
Reasoning within output
tag_management f007
100%
Passed
Tokens
60
Input
152
Total output
139
Reasoning within output
tag_management f008
33.3%
Failed
Tokens
66
Input
440
Total output
376
Reasoning within output
tag_management f009
100%
Passed
Tokens
65
Input
96
Total output
78
Reasoning within output
tag_management f010
100%
Passed
Tokens
43
Input
45
Total output
36
Reasoning within output
tag_management f011
100%
Passed
Tokens
45
Input
46
Total output
43
Reasoning within output
tag_management f012
100%
Passed
Tokens
76
Input
564
Total output
554
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
119
Input
247
Total output
237
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
130
Input
316
Total output
321
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
187
Input
261
Total output
258
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
191
Input
42
Total output
36
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
117
Input
240
Total output
222
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
120
Input
105
Total output
92
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
124
Input
310
Total output
289
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
144
Input
600
Total output
557
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
222
Input
122
Total output
113
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
199
Input
82
Total output
65
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
190
Input
84
Total output
76
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
120
Input
134
Total output
117
Reasoning within output