Deepseek / deepseek-v4-flash
low
96.6%
197 / 204 fixtures · 1 run(s)
34,641 input / 53,659 total output / 50,269 reasoning within output tokens $0.01782324
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-22.1%
Text: 96.6% →
JSON: 74.5%
+2
Gained
JSON pass / text fail
−47
Lost
Text pass / JSON fail
150
Unchanged Pass
Both pass
5
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| commit_squash | 100% | 58.3% | -41.7% |
| blame_forensics | 91.7% | 58.3% | -33.3% |
| branch_cleanup | 100% | 66.7% | -33.3% |
| commit_messages | 100% | 66.7% | -33.3% |
| worktree_usage | 100% | 66.7% | -33.3% |
| git_clean | 100% | 75% | -25% |
| git_log_format | 100% | 75% | -25% |
| reflog | 100% | 75% | -25% |
| submodule_usage | 100% | 75% | -25% |
| tag_management | 100% | 75% | -25% |
| git_bisect | 100% | 83.3% | -16.7% |
| git_grep | 100% | 83.3% | -16.7% |
| git_show | 100% | 83.3% | -16.7% |
| stash_recovery | 100% | 83.3% | -16.7% |
| rebase | 83.3% | 91.7% | + 8.3% |
| cherry_pick | 83.3% | 75% | -8.3% |
| merge_conflicts | 83.3% | 75% | -8.3% |
Changed Fixtures (49)
f003 -loss f004 -loss f006 -loss f010 -loss f003 -loss f008 -loss f009 -loss f011 -loss f010 -loss f005 -loss f009 -loss f010 -loss f012 -loss f003 -loss f004 -loss f006 -loss f010 -loss f011 -loss f005 -loss f006 -loss f001 -loss f004 -loss f005 -loss f008 -loss f010 -loss f001 -loss f010 -loss f011 -loss f002 -loss f008 -loss f001 +gain f004 -loss f011 -loss f001 +gain f001 -loss f007 -loss f011 -loss f001 -loss f009 -loss f003 -loss f007 -loss f012 -loss f004 -loss f008 -loss f010 -loss f003 -loss f005 -loss f008 -loss f009 -loss
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
218
Input
339
Total output
333
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
197
Input
224
Total output
220
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
228
Input
105
Total output
97
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
166
Input
176
Total output
169
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
228
Input
1,588
Total output
1,624
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
202
Input
320
Total output
315
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
188
Input
455
Total output
410
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
209
Input
267
Total output
293
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
175
Input
270
Total output
270
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
374
Input
298
Total output
290
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
201
Input
196
Total output
191
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
131
Input
341
Total output
335
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
100
Input
217
Total output
212
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
108
Input
93
Total output
86
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
92
Input
137
Total output
136
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
122
Input
128
Total output
114
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
97
Input
169
Total output
164
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
117
Input
90
Total output
82
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
95
Input
128
Total output
119
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
118
Input
83
Total output
65
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
76
Input
131
Total output
128
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
112
Input
129
Total output
117
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
67
Input
105
Total output
104
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
149
Input
196
Total output
182
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
92
Input
498
Total output
492
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
121
Input
470
Total output
439
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
86
Input
308
Total output
303
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
147
Input
1,645
Total output
1,624
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
147
Input
144
Total output
128
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
136
Input
549
Total output
522
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
128
Input
144
Total output
133
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
124
Input
90
Total output
82
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
108
Input
93
Total output
83
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
209
Input
456
Total output
430
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
161
Input
147
Total output
101
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
264
Input
686
Total output
697
Reasoning within output
commit_messages f001
93.3%
Passed
Tokens
100
Input
271
Total output
264
Reasoning within output
commit_messages f002
81.7%
Passed
Tokens
196
Input
142
Total output
134
Reasoning within output
commit_messages f003
95%
Passed
Tokens
81
Input
102
Total output
91
Reasoning within output
commit_messages f004
92.7%
Passed
Tokens
108
Input
130
Total output
127
Reasoning within output
commit_messages f005
90%
Passed
Tokens
96
Input
262
Total output
255
Reasoning within output
commit_messages f006
90%
Passed
Tokens
131
Input
538
Total output
473
Reasoning within output
commit_messages f007
92.7%
Passed
Tokens
180
Input
186
Total output
178
Reasoning within output
commit_messages f008
90%
Passed
Tokens
66
Input
205
Total output
199
Reasoning within output
commit_messages f009
91.7%
Passed
Tokens
119
Input
266
Total output
255
Reasoning within output
commit_messages f010
92.3%
Passed
Tokens
266
Input
734
Total output
775
Reasoning within output
commit_messages f011
90%
Passed
Tokens
137
Input
521
Total output
508
Reasoning within output
commit_messages f012
90.7%
Passed
Tokens
120
Input
216
Total output
208
Reasoning within output
commit_squash f001
100%
Passed
Tokens
134
Input
322
Total output
308
Reasoning within output
commit_squash f002
100%
Passed
Tokens
115
Input
130
Total output
119
Reasoning within output
commit_squash f003
100%
Passed
Tokens
121
Input
396
Total output
382
Reasoning within output
commit_squash f004
100%
Passed
Tokens
111
Input
619
Total output
642
Reasoning within output
commit_squash f005
100%
Passed
Tokens
107
Input
105
Total output
97
Reasoning within output
commit_squash f006
100%
Passed
Tokens
93
Input
109
Total output
95
Reasoning within output
commit_squash f007
100%
Passed
Tokens
96
Input
204
Total output
187
Reasoning within output
commit_squash f008
100%
Passed
Tokens
109
Input
132
Total output
122
Reasoning within output
commit_squash f009
100%
Passed
Tokens
101
Input
385
Total output
372
Reasoning within output
commit_squash f010
100%
Passed
Tokens
114
Input
248
Total output
231
Reasoning within output
commit_squash f011
100%
Passed
Tokens
127
Input
326
Total output
309
Reasoning within output
commit_squash f012
100%
Passed
Tokens
119
Input
248
Total output
198
Reasoning within output
git_bisect f001
100%
Passed
Tokens
168
Input
142
Total output
134
Reasoning within output
git_bisect f002
100%
Passed
Tokens
183
Input
102
Total output
90
Reasoning within output
git_bisect f003
100%
Passed
Tokens
189
Input
185
Total output
178
Reasoning within output
git_bisect f004
100%
Passed
Tokens
191
Input
181
Total output
178
Reasoning within output
git_bisect f005
100%
Passed
Tokens
189
Input
131
Total output
127
Reasoning within output
git_bisect f006
100%
Passed
Tokens
204
Input
78
Total output
72
Reasoning within output
git_bisect f007
100%
Passed
Tokens
189
Input
125
Total output
119
Reasoning within output
git_bisect f008
100%
Passed
Tokens
187
Input
142
Total output
125
Reasoning within output
git_bisect f009
100%
Passed
Tokens
185
Input
148
Total output
141
Reasoning within output
git_bisect f010
100%
Passed
Tokens
189
Input
163
Total output
158
Reasoning within output
git_bisect f011
100%
Passed
Tokens
189
Input
154
Total output
134
Reasoning within output
git_bisect f012
100%
Passed
Tokens
212
Input
99
Total output
93
Reasoning within output
git_clean f001
100%
Passed
Tokens
49
Input
275
Total output
265
Reasoning within output
git_clean f002
100%
Passed
Tokens
59
Input
107
Total output
101
Reasoning within output
git_clean f003
100%
Passed
Tokens
57
Input
166
Total output
161
Reasoning within output
git_clean f004
100%
Passed
Tokens
57
Input
141
Total output
135
Reasoning within output
git_clean f005
100%
Passed
Tokens
47
Input
394
Total output
386
Reasoning within output
git_clean f006
100%
Passed
Tokens
74
Input
411
Total output
397
Reasoning within output
git_clean f007
100%
Passed
Tokens
69
Input
321
Total output
298
Reasoning within output
git_clean f008
100%
Passed
Tokens
72
Input
150
Total output
144
Reasoning within output
git_clean f009
100%
Passed
Tokens
67
Input
1,303
Total output
1,293
Reasoning within output
git_clean f010
100%
Passed
Tokens
63
Input
259
Total output
251
Reasoning within output
git_clean f011
100%
Passed
Tokens
60
Input
121
Total output
111
Reasoning within output
git_clean f012
100%
Passed
Tokens
63
Input
525
Total output
488
Reasoning within output
git_grep f001
100%
Passed
Tokens
52
Input
62
Total output
60
Reasoning within output
git_grep f002
100%
Passed
Tokens
63
Input
173
Total output
170
Reasoning within output
git_grep f003
100%
Passed
Tokens
84
Input
30
Total output
28
Reasoning within output
git_grep f004
100%
Passed
Tokens
72
Input
60
Total output
53
Reasoning within output
git_grep f005
100%
Passed
Tokens
107
Input
93
Total output
92
Reasoning within output
git_grep f006
100%
Passed
Tokens
37
Input
213
Total output
210
Reasoning within output
git_grep f007
100%
Passed
Tokens
156
Input
1,902
Total output
1,856
Reasoning within output
git_grep f008
100%
Passed
Tokens
57
Input
79
Total output
88
Reasoning within output
git_grep f009
100%
Passed
Tokens
50
Input
53
Total output
48
Reasoning within output
git_grep f010
100%
Passed
Tokens
60
Input
242
Total output
237
Reasoning within output
git_grep f011
100%
Passed
Tokens
114
Input
151
Total output
148
Reasoning within output
git_grep f012
100%
Passed
Tokens
64
Input
106
Total output
97
Reasoning within output
git_log_format f001
100%
Passed
Tokens
711
Input
66
Total output
55
Reasoning within output
git_log_format f002
100%
Passed
Tokens
700
Input
140
Total output
131
Reasoning within output
git_log_format f003
100%
Passed
Tokens
566
Input
54
Total output
47
Reasoning within output
git_log_format f004
100%
Passed
Tokens
699
Input
67
Total output
64
Reasoning within output
git_log_format f005
100%
Passed
Tokens
573
Input
415
Total output
408
Reasoning within output
git_log_format f006
100%
Passed
Tokens
703
Input
97
Total output
95
Reasoning within output
git_log_format f007
100%
Passed
Tokens
735
Input
64
Total output
59
Reasoning within output
git_log_format f008
100%
Passed
Tokens
964
Input
51
Total output
48
Reasoning within output
git_log_format f009
100%
Passed
Tokens
561
Input
37
Total output
34
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,067
Input
49
Total output
46
Reasoning within output
git_log_format f011
100%
Passed
Tokens
341
Input
67
Total output
62
Reasoning within output
git_log_format f012
100%
Passed
Tokens
319
Input
71
Total output
69
Reasoning within output
git_show f001
100%
Passed
Tokens
171
Input
55
Total output
48
Reasoning within output
git_show f002
100%
Passed
Tokens
168
Input
331
Total output
327
Reasoning within output
git_show f003
100%
Passed
Tokens
553
Input
91
Total output
83
Reasoning within output
git_show f004
100%
Passed
Tokens
382
Input
58
Total output
50
Reasoning within output
git_show f005
100%
Passed
Tokens
171
Input
182
Total output
178
Reasoning within output
git_show f006
100%
Passed
Tokens
178
Input
108
Total output
103
Reasoning within output
git_show f007
100%
Passed
Tokens
162
Input
72
Total output
66
Reasoning within output
git_show f008
100%
Passed
Tokens
180
Input
121
Total output
85
Reasoning within output
git_show f009
100%
Passed
Tokens
263
Input
88
Total output
81
Reasoning within output
git_show f010
100%
Passed
Tokens
168
Input
102
Total output
95
Reasoning within output
git_show f011
100%
Passed
Tokens
198
Input
47
Total output
49
Reasoning within output
git_show f012
100%
Passed
Tokens
296
Input
79
Total output
76
Reasoning within output
merge_conflicts f001
0%
Failed
Tokens
84
Input
502
Total output
542
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
109
Input
533
Total output
524
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
79
Input
450
Total output
491
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
134
Input
1,242
Total output
1,219
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
136
Input
170
Total output
152
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
123
Input
247
Total output
204
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
130
Input
251
Total output
241
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
106
Input
101
Total output
93
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
104
Input
249
Total output
273
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
178
Input
337
Total output
328
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
142
Input
185
Total output
162
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
231
Input
519
Total output
477
Reasoning within output
rebase f001
0%
Failed
Tokens
95
Input
536
Total output
526
Reasoning within output
rebase f002
100%
Passed
Tokens
130
Input
105
Total output
95
Reasoning within output
rebase f003
100%
Passed
Tokens
103
Input
96
Total output
91
Reasoning within output
rebase f004
100%
Passed
Tokens
145
Input
758
Total output
724
Reasoning within output
rebase f005
100%
Passed
Tokens
140
Input
151
Total output
132
Reasoning within output
rebase f006
100%
Passed
Tokens
135
Input
143
Total output
122
Reasoning within output
rebase f007
100%
Passed
Tokens
130
Input
155
Total output
159
Reasoning within output
rebase f008
100%
Passed
Tokens
117
Input
230
Total output
222
Reasoning within output
rebase f009
100%
Passed
Tokens
102
Input
134
Total output
127
Reasoning within output
rebase f010
100%
Passed
Tokens
201
Input
553
Total output
528
Reasoning within output
rebase f011
100%
Passed
Tokens
151
Input
208
Total output
185
Reasoning within output
rebase f012
0%
Failed
Tokens
260
Input
286
Total output
249
Reasoning within output
reflog f001
100%
Passed
Tokens
197
Input
380
Total output
357
Reasoning within output
reflog f002
100%
Passed
Tokens
196
Input
110
Total output
50
Reasoning within output
reflog f003
100%
Passed
Tokens
176
Input
161
Total output
92
Reasoning within output
reflog f004
100%
Passed
Tokens
277
Input
757
Total output
570
Reasoning within output
reflog f005
100%
Passed
Tokens
309
Input
507
Total output
450
Reasoning within output
reflog f006
100%
Passed
Tokens
207
Input
157
Total output
120
Reasoning within output
reflog f007
100%
Passed
Tokens
241
Input
158
Total output
72
Reasoning within output
reflog f008
100%
Passed
Tokens
301
Input
331
Total output
304
Reasoning within output
reflog f009
100%
Passed
Tokens
256
Input
536
Total output
450
Reasoning within output
reflog f010
100%
Passed
Tokens
242
Input
380
Total output
308
Reasoning within output
reflog f011
100%
Passed
Tokens
261
Input
1,284
Total output
1,119
Reasoning within output
reflog f012
100%
Passed
Tokens
268
Input
1,201
Total output
907
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
121
Input
70
Total output
65
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
269
Input
113
Total output
95
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
111
Input
91
Total output
79
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
110
Input
178
Total output
158
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
120
Input
151
Total output
132
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
167
Input
110
Total output
88
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
198
Input
119
Total output
105
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
163
Input
158
Total output
120
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
198
Input
123
Total output
102
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
118
Input
60
Total output
41
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
108
Input
198
Total output
152
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
127
Input
128
Total output
114
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
40
Input
63
Total output
52
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
90
Input
295
Total output
284
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
91
Input
1,209
Total output
1,122
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
81
Input
54
Total output
49
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
47
Input
365
Total output
343
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
81
Input
389
Total output
359
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
48
Input
89
Total output
69
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
83
Input
823
Total output
815
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
84
Input
75
Total output
64
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
89
Input
167
Total output
186
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
90
Input
36
Total output
30
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
46
Input
77
Total output
63
Reasoning within output
tag_management f001
100%
Passed
Tokens
51
Input
61
Total output
49
Reasoning within output
tag_management f002
100%
Passed
Tokens
50
Input
180
Total output
160
Reasoning within output
tag_management f003
100%
Passed
Tokens
59
Input
79
Total output
68
Reasoning within output
tag_management f004
100%
Passed
Tokens
61
Input
95
Total output
100
Reasoning within output
tag_management f005
100%
Passed
Tokens
72
Input
141
Total output
132
Reasoning within output
tag_management f006
100%
Passed
Tokens
59
Input
100
Total output
79
Reasoning within output
tag_management f007
100%
Passed
Tokens
60
Input
310
Total output
290
Reasoning within output
tag_management f008
100%
Passed
Tokens
65
Input
475
Total output
373
Reasoning within output
tag_management f009
100%
Passed
Tokens
66
Input
91
Total output
73
Reasoning within output
tag_management f010
100%
Passed
Tokens
45
Input
74
Total output
64
Reasoning within output
tag_management f011
100%
Passed
Tokens
45
Input
43
Total output
38
Reasoning within output
tag_management f012
100%
Passed
Tokens
77
Input
351
Total output
340
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
127
Input
109
Total output
98
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
132
Input
337
Total output
315
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
190
Input
80
Total output
72
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
192
Input
43
Total output
37
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
121
Input
425
Total output
405
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
117
Input
171
Total output
154
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
121
Input
389
Total output
368
Reasoning within output
worktree_usage f008
100%
Passed
Tokens
145
Input
530
Total output
485
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
220
Input
61
Total output
55
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
192
Input
177
Total output
159
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
187
Input
183
Total output
173
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
114
Input
199
Total output
186
Reasoning within output