Deepseek / deepseek-v4-flash-0731
low
95.1%
194 / 204 fixtures · 1 run(s)
35,927 input / 74,446 total output / 72,093 reasoning within output tokens $0.02421513
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-9.3%
Text: 95.1% →
JSON: 85.8%
+3
Gained
JSON pass / text fail
−22
Lost
Text pass / JSON fail
172
Unchanged Pass
Both pass
7
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| reflog | 100% | 66.7% | -33.3% |
| branch_cleanup | 100% | 83.3% | -16.7% |
| commit_squash | 66.7% | 50% | -16.7% |
| git_log_format | 100% | 83.3% | -16.7% |
| submodule_usage | 100% | 83.3% | -16.7% |
| cherry_pick | 91.7% | 83.3% | -8.3% |
| merge_conflicts | 91.7% | 83.3% | -8.3% |
| rebase | 91.7% | 83.3% | -8.3% |
| worktree_usage | 91.7% | 83.3% | -8.3% |
| blame_forensics | 100% | 91.7% | -8.3% |
| stash_recovery | 100% | 91.7% | -8.3% |
| tag_management | 100% | 91.7% | -8.3% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_clean | 83.3% | 83.3% | + 0% |
| git_grep | 100% | 100% | + 0% |
| git_show | 100% | 100% | + 0% |
Changed Fixtures (25)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
219
Input
433
Total output
428
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
281
Input
264
Total output
259
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
226
Input
212
Total output
200
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
168
Input
40
Total output
34
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
231
Input
45
Total output
55
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
200
Input
140
Total output
148
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
190
Input
113
Total output
103
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
208
Input
67
Total output
62
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
171
Input
203
Total output
226
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
365
Input
338
Total output
333
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
202
Input
418
Total output
414
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
128
Input
302
Total output
297
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
101
Input
346
Total output
340
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
111
Input
60
Total output
54
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
92
Input
52
Total output
50
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
123
Input
216
Total output
231
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
98
Input
258
Total output
241
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
117
Input
521
Total output
539
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
94
Input
36
Total output
30
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
118
Input
159
Total output
148
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
155
Input
72
Total output
70
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
119
Input
384
Total output
371
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
74
Input
68
Total output
79
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
148
Input
312
Total output
346
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
94
Input
895
Total output
1,003
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
120
Input
326
Total output
278
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
89
Input
275
Total output
313
Reasoning within output
cherry_pick f004
100%
Passed
Tokens
145
Input
1,232
Total output
1,209
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
227
Input
144
Total output
157
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
213
Input
139
Total output
119
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
128
Input
311
Total output
316
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
128
Input
191
Total output
200
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
107
Input
85
Total output
87
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
209
Input
358
Total output
368
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
161
Input
244
Total output
208
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
266
Input
156
Total output
128
Reasoning within output
commit_messages f001
91.7%
Passed
Tokens
100
Input
77
Total output
70
Reasoning within output
commit_messages f002
85.3%
Passed
Tokens
196
Input
210
Total output
200
Reasoning within output
commit_messages f003
95%
Passed
Tokens
160
Input
228
Total output
170
Reasoning within output
commit_messages f004
92.7%
Passed
Tokens
108
Input
135
Total output
139
Reasoning within output
commit_messages f005
80%
Passed
Tokens
96
Input
154
Total output
148
Reasoning within output
commit_messages f006
90%
Passed
Tokens
131
Input
487
Total output
450
Reasoning within output
commit_messages f007
87.7%
Passed
Tokens
180
Input
216
Total output
211
Reasoning within output
commit_messages f008
90.3%
Passed
Tokens
66
Input
147
Total output
149
Reasoning within output
commit_messages f009
85%
Passed
Tokens
119
Input
217
Total output
204
Reasoning within output
commit_messages f010
95.7%
Passed
Tokens
266
Input
288
Total output
281
Reasoning within output
commit_messages f011
81.7%
Passed
Tokens
137
Input
1,011
Total output
790
Reasoning within output
commit_messages f012
90%
Passed
Tokens
120
Input
78
Total output
70
Reasoning within output
commit_squash f001
100%
Passed
Tokens
131
Input
592
Total output
579
Reasoning within output
commit_squash f002
100%
Passed
Tokens
114
Input
358
Total output
347
Reasoning within output
commit_squash f003
100%
Passed
Tokens
120
Input
359
Total output
346
Reasoning within output
commit_squash f004
100%
Passed
Tokens
110
Input
60
Total output
60
Reasoning within output
commit_squash f005
0%
Failed
Tokens
186
Input
182
Total output
182
Reasoning within output
commit_squash f006
100%
Passed
Tokens
95
Input
181
Total output
171
Reasoning within output
commit_squash f007
0%
Failed
Tokens
94
Input
492
Total output
471
Reasoning within output
commit_squash f008
100%
Passed
Tokens
110
Input
455
Total output
425
Reasoning within output
commit_squash f009
100%
Passed
Tokens
177
Input
8,125
Total output
8,500
Reasoning within output
commit_squash f010
0%
Failed
Tokens
113
Input
52
Total output
27
Reasoning within output
commit_squash f011
100%
Passed
Tokens
123
Input
47
Total output
33
Reasoning within output
commit_squash f012
0%
Failed
Tokens
120
Input
77
Total output
44
Reasoning within output
git_bisect f001
100%
Passed
Tokens
166
Input
62
Total output
55
Reasoning within output
git_bisect f002
100%
Passed
Tokens
264
Input
156
Total output
152
Reasoning within output
git_bisect f003
100%
Passed
Tokens
185
Input
141
Total output
135
Reasoning within output
git_bisect f004
100%
Passed
Tokens
191
Input
237
Total output
208
Reasoning within output
git_bisect f005
100%
Passed
Tokens
266
Input
262
Total output
256
Reasoning within output
git_bisect f006
100%
Passed
Tokens
220
Input
274
Total output
267
Reasoning within output
git_bisect f007
100%
Passed
Tokens
187
Input
117
Total output
92
Reasoning within output
git_bisect f008
100%
Passed
Tokens
189
Input
320
Total output
315
Reasoning within output
git_bisect f009
100%
Passed
Tokens
185
Input
124
Total output
118
Reasoning within output
git_bisect f010
100%
Passed
Tokens
189
Input
353
Total output
347
Reasoning within output
git_bisect f011
100%
Passed
Tokens
189
Input
214
Total output
219
Reasoning within output
git_bisect f012
100%
Passed
Tokens
218
Input
294
Total output
268
Reasoning within output
git_clean f001
100%
Passed
Tokens
49
Input
233
Total output
220
Reasoning within output
git_clean f002
100%
Passed
Tokens
59
Input
133
Total output
132
Reasoning within output
git_clean f003
100%
Passed
Tokens
57
Input
152
Total output
148
Reasoning within output
git_clean f004
66.7%
Failed
Tokens
57
Input
235
Total output
240
Reasoning within output
git_clean f005
100%
Passed
Tokens
47
Input
231
Total output
219
Reasoning within output
git_clean f006
100%
Passed
Tokens
74
Input
391
Total output
384
Reasoning within output
git_clean f007
100%
Passed
Tokens
69
Input
341
Total output
325
Reasoning within output
git_clean f008
100%
Passed
Tokens
72
Input
169
Total output
165
Reasoning within output
git_clean f009
100%
Passed
Tokens
67
Input
492
Total output
483
Reasoning within output
git_clean f010
100%
Passed
Tokens
63
Input
74
Total output
78
Reasoning within output
git_clean f011
60%
Failed
Tokens
60
Input
501
Total output
506
Reasoning within output
git_clean f012
100%
Passed
Tokens
63
Input
222
Total output
218
Reasoning within output
git_grep f001
100%
Passed
Tokens
52
Input
50
Total output
50
Reasoning within output
git_grep f002
100%
Passed
Tokens
64
Input
104
Total output
106
Reasoning within output
git_grep f003
100%
Passed
Tokens
84
Input
62
Total output
64
Reasoning within output
git_grep f004
100%
Passed
Tokens
72
Input
140
Total output
123
Reasoning within output
git_grep f005
100%
Passed
Tokens
107
Input
154
Total output
152
Reasoning within output
git_grep f006
100%
Passed
Tokens
37
Input
402
Total output
399
Reasoning within output
git_grep f007
100%
Passed
Tokens
156
Input
1,648
Total output
1,645
Reasoning within output
git_grep f008
100%
Passed
Tokens
57
Input
93
Total output
90
Reasoning within output
git_grep f009
100%
Passed
Tokens
50
Input
131
Total output
113
Reasoning within output
git_grep f010
100%
Passed
Tokens
60
Input
127
Total output
123
Reasoning within output
git_grep f011
100%
Passed
Tokens
114
Input
172
Total output
169
Reasoning within output
git_grep f012
100%
Passed
Tokens
64
Input
78
Total output
65
Reasoning within output
git_log_format f001
100%
Passed
Tokens
712
Input
81
Total output
78
Reasoning within output
git_log_format f002
100%
Passed
Tokens
691
Input
25
Total output
23
Reasoning within output
git_log_format f003
100%
Passed
Tokens
579
Input
54
Total output
50
Reasoning within output
git_log_format f004
100%
Passed
Tokens
695
Input
44
Total output
42
Reasoning within output
git_log_format f005
100%
Passed
Tokens
573
Input
94
Total output
88
Reasoning within output
git_log_format f006
100%
Passed
Tokens
703
Input
69
Total output
56
Reasoning within output
git_log_format f007
100%
Passed
Tokens
784
Input
36
Total output
32
Reasoning within output
git_log_format f008
100%
Passed
Tokens
942
Input
96
Total output
69
Reasoning within output
git_log_format f009
100%
Passed
Tokens
579
Input
35
Total output
32
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,068
Input
53
Total output
38
Reasoning within output
git_log_format f011
100%
Passed
Tokens
346
Input
66
Total output
67
Reasoning within output
git_log_format f012
100%
Passed
Tokens
319
Input
91
Total output
87
Reasoning within output
git_show f001
100%
Passed
Tokens
176
Input
54
Total output
46
Reasoning within output
git_show f002
100%
Passed
Tokens
244
Input
5,775
Total output
5,960
Reasoning within output
git_show f003
100%
Passed
Tokens
559
Input
60
Total output
49
Reasoning within output
git_show f004
100%
Passed
Tokens
392
Input
61
Total output
46
Reasoning within output
git_show f005
100%
Passed
Tokens
172
Input
85
Total output
82
Reasoning within output
git_show f006
100%
Passed
Tokens
183
Input
80
Total output
83
Reasoning within output
git_show f007
100%
Passed
Tokens
162
Input
89
Total output
67
Reasoning within output
git_show f008
100%
Passed
Tokens
175
Input
68
Total output
46
Reasoning within output
git_show f009
100%
Passed
Tokens
265
Input
112
Total output
109
Reasoning within output
git_show f010
100%
Passed
Tokens
176
Input
105
Total output
102
Reasoning within output
git_show f011
100%
Passed
Tokens
197
Input
12
Total output
14
Reasoning within output
git_show f012
100%
Passed
Tokens
293
Input
66
Total output
64
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
84
Input
533
Total output
595
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
109
Input
374
Total output
365
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
79
Input
897
Total output
997
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
134
Input
633
Total output
610
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
136
Input
240
Total output
218
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
123
Input
240
Total output
189
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
130
Input
212
Total output
214
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
106
Input
131
Total output
147
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
104
Input
308
Total output
319
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
178
Input
485
Total output
511
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
142
Input
217
Total output
160
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
231
Input
550
Total output
572
Reasoning within output
rebase f001
100%
Passed
Tokens
94
Input
990
Total output
1,120
Reasoning within output
rebase f002
100%
Passed
Tokens
127
Input
150
Total output
139
Reasoning within output
rebase f003
100%
Passed
Tokens
101
Input
266
Total output
284
Reasoning within output
rebase f004
100%
Passed
Tokens
147
Input
1,805
Total output
2,221
Reasoning within output
rebase f005
100%
Passed
Tokens
140
Input
254
Total output
240
Reasoning within output
rebase f006
100%
Passed
Tokens
136
Input
298
Total output
278
Reasoning within output
rebase f007
100%
Passed
Tokens
130
Input
205
Total output
195
Reasoning within output
rebase f008
100%
Passed
Tokens
118
Input
38
Total output
47
Reasoning within output
rebase f009
100%
Passed
Tokens
103
Input
124
Total output
131
Reasoning within output
rebase f010
100%
Passed
Tokens
203
Input
520
Total output
495
Reasoning within output
rebase f011
100%
Passed
Tokens
154
Input
461
Total output
370
Reasoning within output
rebase f012
0%
Failed
Tokens
264
Input
1,118
Total output
1,091
Reasoning within output
reflog f001
100%
Passed
Tokens
204
Input
643
Total output
518
Reasoning within output
reflog f002
100%
Passed
Tokens
202
Input
373
Total output
300
Reasoning within output
reflog f003
100%
Passed
Tokens
170
Input
207
Total output
123
Reasoning within output
reflog f004
100%
Passed
Tokens
273
Input
1,362
Total output
1,185
Reasoning within output
reflog f005
100%
Passed
Tokens
309
Input
2,288
Total output
2,189
Reasoning within output
reflog f006
100%
Passed
Tokens
213
Input
473
Total output
258
Reasoning within output
reflog f007
100%
Passed
Tokens
240
Input
715
Total output
592
Reasoning within output
reflog f008
100%
Passed
Tokens
312
Input
897
Total output
754
Reasoning within output
reflog f009
100%
Passed
Tokens
274
Input
1,753
Total output
1,535
Reasoning within output
reflog f010
100%
Passed
Tokens
222
Input
282
Total output
232
Reasoning within output
reflog f011
100%
Passed
Tokens
276
Input
1,288
Total output
1,068
Reasoning within output
reflog f012
100%
Passed
Tokens
277
Input
2,024
Total output
1,819
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
123
Input
181
Total output
184
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
266
Input
231
Total output
219
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
111
Input
109
Total output
112
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
110
Input
155
Total output
136
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
127
Input
139
Total output
128
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
167
Input
231
Total output
196
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
192
Input
304
Total output
256
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
242
Input
118
Total output
83
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
198
Input
272
Total output
227
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
118
Input
222
Total output
209
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
109
Input
313
Total output
309
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
133
Input
160
Total output
149
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
40
Input
93
Total output
83
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
94
Input
248
Total output
237
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
174
Input
195
Total output
178
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
84
Input
174
Total output
182
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
47
Input
308
Total output
298
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
78
Input
361
Total output
356
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
48
Input
237
Total output
231
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
88
Input
149
Total output
141
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
85
Input
53
Total output
47
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
88
Input
199
Total output
205
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
91
Input
99
Total output
100
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
125
Input
63
Total output
50
Reasoning within output
tag_management f001
100%
Passed
Tokens
53
Input
57
Total output
49
Reasoning within output
tag_management f002
100%
Passed
Tokens
51
Input
157
Total output
127
Reasoning within output
tag_management f003
100%
Passed
Tokens
58
Input
96
Total output
81
Reasoning within output
tag_management f004
100%
Passed
Tokens
60
Input
74
Total output
70
Reasoning within output
tag_management f005
100%
Passed
Tokens
73
Input
243
Total output
202
Reasoning within output
tag_management f006
100%
Passed
Tokens
57
Input
111
Total output
83
Reasoning within output
tag_management f007
100%
Passed
Tokens
59
Input
65
Total output
61
Reasoning within output
tag_management f008
100%
Passed
Tokens
66
Input
329
Total output
273
Reasoning within output
tag_management f009
100%
Passed
Tokens
74
Input
82
Total output
75
Reasoning within output
tag_management f010
100%
Passed
Tokens
44
Input
20
Total output
12
Reasoning within output
tag_management f011
100%
Passed
Tokens
42
Input
123
Total output
117
Reasoning within output
tag_management f012
100%
Passed
Tokens
77
Input
471
Total output
414
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
127
Input
236
Total output
225
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
130
Input
235
Total output
211
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
193
Input
77
Total output
94
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
182
Input
61
Total output
60
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
115
Input
178
Total output
164
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
119
Input
135
Total output
122
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
123
Input
578
Total output
541
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
225
Input
2,678
Total output
2,626
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
219
Input
198
Total output
214
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
200
Input
152
Total output
135
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
193
Input
154
Total output
151
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
118
Input
125
Total output
99
Reasoning within output