Deepseek / deepseek-v4-flash-0731
high
95.6%
195 / 204 fixtures · 1 run(s)
43,697 input / 98,530 total output / 95,212 reasoning within output tokens $0.03284677
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-5.9%
Text: 95.6% →
JSON: 89.7%
+2
Gained
JSON pass / text fail
−14
Lost
Text pass / JSON fail
181
Unchanged Pass
Both pass
7
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| commit_squash | 75% | 50% | -25% |
| branch_cleanup | 100% | 83.3% | -16.7% |
| merge_conflicts | 91.7% | 75% | -16.7% |
| reflog | 100% | 83.3% | -16.7% |
| worktree_usage | 91.7% | 75% | -16.7% |
| submodule_usage | 100% | 91.7% | -8.3% |
| blame_forensics | 100% | 100% | + 0% |
| cherry_pick | 83.3% | 83.3% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_clean | 100% | 100% | + 0% |
| git_grep | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 100% | 100% | + 0% |
| rebase | 83.3% | 83.3% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
Changed Fixtures (16)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
301
Input
77
Total output
87
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
277
Input
367
Total output
362
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
308
Input
66
Total output
61
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
248
Input
268
Total output
262
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
231
Input
54
Total output
49
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
291
Input
442
Total output
438
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
264
Input
106
Total output
100
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
208
Input
394
Total output
387
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
247
Input
108
Total output
110
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
455
Input
327
Total output
322
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
285
Input
120
Total output
117
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
211
Input
213
Total output
220
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
106
Input
72
Total output
82
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
191
Input
341
Total output
324
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
168
Input
120
Total output
118
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
205
Input
218
Total output
207
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
100
Input
507
Total output
510
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
201
Input
93
Total output
91
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
180
Input
194
Total output
204
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
196
Input
235
Total output
210
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
164
Input
125
Total output
135
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
192
Input
175
Total output
157
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
147
Input
74
Total output
72
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
225
Input
203
Total output
190
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
93
Input
776
Total output
770
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
118
Input
904
Total output
881
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
166
Input
835
Total output
830
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
146
Input
1,526
Total output
1,714
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
148
Input
137
Total output
140
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
135
Input
414
Total output
412
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
129
Input
169
Total output
176
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
201
Input
87
Total output
99
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
186
Input
37
Total output
31
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
215
Input
195
Total output
190
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
239
Input
143
Total output
121
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
264
Input
406
Total output
365
Reasoning within output
commit_messages f001
96%
Passed
Tokens
179
Input
119
Total output
110
Reasoning within output
commit_messages f002
88.3%
Passed
Tokens
281
Input
107
Total output
102
Reasoning within output
commit_messages f003
95%
Passed
Tokens
160
Input
396
Total output
301
Reasoning within output
commit_messages f004
94.3%
Passed
Tokens
187
Input
37
Total output
33
Reasoning within output
commit_messages f005
91%
Passed
Tokens
175
Input
142
Total output
138
Reasoning within output
commit_messages f006
88.3%
Passed
Tokens
210
Input
120
Total output
114
Reasoning within output
commit_messages f007
93.3%
Passed
Tokens
180
Input
123
Total output
122
Reasoning within output
commit_messages f008
91.7%
Passed
Tokens
145
Input
144
Total output
141
Reasoning within output
commit_messages f009
85%
Passed
Tokens
198
Input
48
Total output
40
Reasoning within output
commit_messages f010
91%
Passed
Tokens
345
Input
320
Total output
321
Reasoning within output
commit_messages f011
63.3%
Passed
Tokens
137
Input
596
Total output
489
Reasoning within output
commit_messages f012
88.3%
Passed
Tokens
199
Input
99
Total output
92
Reasoning within output
commit_squash f001
100%
Passed
Tokens
213
Input
2,663
Total output
2,650
Reasoning within output
commit_squash f002
100%
Passed
Tokens
110
Input
258
Total output
259
Reasoning within output
commit_squash f003
100%
Passed
Tokens
120
Input
432
Total output
425
Reasoning within output
commit_squash f004
100%
Passed
Tokens
191
Input
8,315
Total output
8,455
Reasoning within output
commit_squash f005
0%
Failed
Tokens
106
Input
60
Total output
69
Reasoning within output
commit_squash f006
100%
Passed
Tokens
174
Input
152
Total output
139
Reasoning within output
commit_squash f007
0%
Failed
Tokens
100
Input
108
Total output
73
Reasoning within output
commit_squash f008
100%
Passed
Tokens
109
Input
134
Total output
109
Reasoning within output
commit_squash f009
100%
Passed
Tokens
179
Input
217
Total output
205
Reasoning within output
commit_squash f010
0%
Failed
Tokens
114
Input
72
Total output
55
Reasoning within output
commit_squash f011
100%
Passed
Tokens
205
Input
223
Total output
207
Reasoning within output
commit_squash f012
100%
Passed
Tokens
119
Input
471
Total output
395
Reasoning within output
git_bisect f001
100%
Passed
Tokens
166
Input
95
Total output
69
Reasoning within output
git_bisect f002
100%
Passed
Tokens
189
Input
167
Total output
153
Reasoning within output
git_bisect f003
100%
Passed
Tokens
193
Input
343
Total output
327
Reasoning within output
git_bisect f004
100%
Passed
Tokens
183
Input
434
Total output
438
Reasoning within output
git_bisect f005
100%
Passed
Tokens
183
Input
224
Total output
218
Reasoning within output
git_bisect f006
100%
Passed
Tokens
289
Input
62
Total output
53
Reasoning within output
git_bisect f007
100%
Passed
Tokens
183
Input
173
Total output
153
Reasoning within output
git_bisect f008
100%
Passed
Tokens
191
Input
175
Total output
153
Reasoning within output
git_bisect f009
100%
Passed
Tokens
183
Input
125
Total output
125
Reasoning within output
git_bisect f010
100%
Passed
Tokens
187
Input
140
Total output
132
Reasoning within output
git_bisect f011
100%
Passed
Tokens
274
Input
92
Total output
86
Reasoning within output
git_bisect f012
100%
Passed
Tokens
295
Input
81
Total output
84
Reasoning within output
git_clean f001
100%
Passed
Tokens
49
Input
158
Total output
141
Reasoning within output
git_clean f002
100%
Passed
Tokens
144
Input
302
Total output
321
Reasoning within output
git_clean f003
100%
Passed
Tokens
57
Input
131
Total output
130
Reasoning within output
git_clean f004
100%
Passed
Tokens
136
Input
372
Total output
377
Reasoning within output
git_clean f005
100%
Passed
Tokens
53
Input
356
Total output
348
Reasoning within output
git_clean f006
100%
Passed
Tokens
74
Input
204
Total output
207
Reasoning within output
git_clean f007
100%
Passed
Tokens
148
Input
211
Total output
206
Reasoning within output
git_clean f008
100%
Passed
Tokens
151
Input
43
Total output
38
Reasoning within output
git_clean f009
100%
Passed
Tokens
146
Input
4,689
Total output
4,680
Reasoning within output
git_clean f010
100%
Passed
Tokens
63
Input
347
Total output
336
Reasoning within output
git_clean f011
100%
Passed
Tokens
139
Input
420
Total output
414
Reasoning within output
git_clean f012
100%
Passed
Tokens
63
Input
317
Total output
312
Reasoning within output
git_grep f001
100%
Passed
Tokens
52
Input
107
Total output
108
Reasoning within output
git_grep f002
100%
Passed
Tokens
60
Input
122
Total output
123
Reasoning within output
git_grep f003
100%
Passed
Tokens
84
Input
45
Total output
47
Reasoning within output
git_grep f004
100%
Passed
Tokens
151
Input
28
Total output
22
Reasoning within output
git_grep f005
100%
Passed
Tokens
186
Input
71
Total output
69
Reasoning within output
git_grep f006
100%
Passed
Tokens
116
Input
135
Total output
133
Reasoning within output
git_grep f007
100%
Passed
Tokens
241
Input
2,488
Total output
2,451
Reasoning within output
git_grep f008
100%
Passed
Tokens
57
Input
118
Total output
128
Reasoning within output
git_grep f009
100%
Passed
Tokens
135
Input
44
Total output
38
Reasoning within output
git_grep f010
100%
Passed
Tokens
60
Input
105
Total output
106
Reasoning within output
git_grep f011
100%
Passed
Tokens
193
Input
148
Total output
135
Reasoning within output
git_grep f012
100%
Passed
Tokens
64
Input
81
Total output
64
Reasoning within output
git_log_format f001
100%
Passed
Tokens
779
Input
73
Total output
70
Reasoning within output
git_log_format f002
100%
Passed
Tokens
707
Input
49
Total output
47
Reasoning within output
git_log_format f003
100%
Passed
Tokens
575
Input
75
Total output
61
Reasoning within output
git_log_format f004
100%
Passed
Tokens
771
Input
63
Total output
51
Reasoning within output
git_log_format f005
100%
Passed
Tokens
652
Input
415
Total output
409
Reasoning within output
git_log_format f006
100%
Passed
Tokens
709
Input
93
Total output
90
Reasoning within output
git_log_format f007
100%
Passed
Tokens
794
Input
39
Total output
33
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,006
Input
42
Total output
43
Reasoning within output
git_log_format f009
100%
Passed
Tokens
572
Input
38
Total output
32
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,044
Input
31
Total output
26
Reasoning within output
git_log_format f011
100%
Passed
Tokens
353
Input
123
Total output
124
Reasoning within output
git_log_format f012
100%
Passed
Tokens
400
Input
47
Total output
45
Reasoning within output
git_show f001
100%
Passed
Tokens
164
Input
63
Total output
54
Reasoning within output
git_show f002
100%
Passed
Tokens
166
Input
813
Total output
810
Reasoning within output
git_show f003
100%
Passed
Tokens
557
Input
156
Total output
136
Reasoning within output
git_show f004
100%
Passed
Tokens
388
Input
59
Total output
51
Reasoning within output
git_show f005
100%
Passed
Tokens
248
Input
111
Total output
116
Reasoning within output
git_show f006
100%
Passed
Tokens
178
Input
26
Total output
23
Reasoning within output
git_show f007
100%
Passed
Tokens
162
Input
77
Total output
60
Reasoning within output
git_show f008
100%
Passed
Tokens
187
Input
101
Total output
73
Reasoning within output
git_show f009
100%
Passed
Tokens
262
Input
87
Total output
65
Reasoning within output
git_show f010
100%
Passed
Tokens
248
Input
113
Total output
113
Reasoning within output
git_show f011
100%
Passed
Tokens
198
Input
85
Total output
69
Reasoning within output
git_show f012
100%
Passed
Tokens
376
Input
90
Total output
91
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
84
Input
340
Total output
334
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
109
Input
497
Total output
487
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
158
Input
1,747
Total output
1,891
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
213
Input
15,862
Total output
15,839
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
215
Input
390
Total output
373
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
202
Input
503
Total output
435
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
130
Input
177
Total output
173
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
106
Input
142
Total output
151
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
189
Input
519
Total output
562
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
257
Input
758
Total output
805
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
221
Input
309
Total output
268
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
310
Input
690
Total output
658
Reasoning within output
rebase f001
100%
Passed
Tokens
173
Input
396
Total output
391
Reasoning within output
rebase f002
100%
Passed
Tokens
206
Input
49
Total output
40
Reasoning within output
rebase f003
100%
Passed
Tokens
101
Input
159
Total output
176
Reasoning within output
rebase f004
0%
Failed
Tokens
145
Input
1,418
Total output
1,458
Reasoning within output
rebase f005
100%
Passed
Tokens
141
Input
166
Total output
165
Reasoning within output
rebase f006
100%
Passed
Tokens
136
Input
349
Total output
320
Reasoning within output
rebase f007
100%
Passed
Tokens
132
Input
134
Total output
123
Reasoning within output
rebase f008
100%
Passed
Tokens
197
Input
106
Total output
114
Reasoning within output
rebase f009
100%
Passed
Tokens
180
Input
190
Total output
189
Reasoning within output
rebase f010
100%
Passed
Tokens
205
Input
360
Total output
364
Reasoning within output
rebase f011
100%
Passed
Tokens
229
Input
258
Total output
205
Reasoning within output
rebase f012
0%
Failed
Tokens
347
Input
456
Total output
424
Reasoning within output
reflog f001
100%
Passed
Tokens
276
Input
107
Total output
85
Reasoning within output
reflog f002
100%
Passed
Tokens
272
Input
206
Total output
117
Reasoning within output
reflog f003
100%
Passed
Tokens
174
Input
320
Total output
253
Reasoning within output
reflog f004
100%
Passed
Tokens
357
Input
3,548
Total output
3,115
Reasoning within output
reflog f005
100%
Passed
Tokens
326
Input
2,928
Total output
2,886
Reasoning within output
reflog f006
100%
Passed
Tokens
292
Input
833
Total output
493
Reasoning within output
reflog f007
100%
Passed
Tokens
244
Input
460
Total output
294
Reasoning within output
reflog f008
100%
Passed
Tokens
399
Input
1,377
Total output
1,173
Reasoning within output
reflog f009
100%
Passed
Tokens
270
Input
1,266
Total output
1,022
Reasoning within output
reflog f010
100%
Passed
Tokens
308
Input
545
Total output
436
Reasoning within output
reflog f011
100%
Passed
Tokens
352
Input
6,236
Total output
6,129
Reasoning within output
reflog f012
100%
Passed
Tokens
268
Input
1,167
Total output
1,039
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
201
Input
60
Total output
62
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
266
Input
329
Total output
247
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
111
Input
172
Total output
188
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
195
Input
66
Total output
63
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
198
Input
114
Total output
117
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
252
Input
115
Total output
79
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
277
Input
113
Total output
94
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
163
Input
268
Total output
268
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
277
Input
245
Total output
187
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
118
Input
106
Total output
93
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
187
Input
534
Total output
464
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
212
Input
187
Total output
147
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
40
Input
81
Total output
70
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
88
Input
313
Total output
332
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
173
Input
2,390
Total output
2,366
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
158
Input
31
Total output
28
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
126
Input
255
Total output
227
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
84
Input
435
Total output
429
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
127
Input
98
Total output
78
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
85
Input
1,402
Total output
1,522
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
81
Input
151
Total output
153
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
92
Input
153
Total output
168
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
171
Input
70
Total output
68
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
125
Input
69
Total output
56
Reasoning within output
tag_management f001
100%
Passed
Tokens
138
Input
43
Total output
32
Reasoning within output
tag_management f002
100%
Passed
Tokens
129
Input
68
Total output
50
Reasoning within output
tag_management f003
100%
Passed
Tokens
57
Input
154
Total output
122
Reasoning within output
tag_management f004
100%
Passed
Tokens
62
Input
97
Total output
97
Reasoning within output
tag_management f005
100%
Passed
Tokens
155
Input
70
Total output
56
Reasoning within output
tag_management f006
100%
Passed
Tokens
139
Input
188
Total output
148
Reasoning within output
tag_management f007
100%
Passed
Tokens
58
Input
147
Total output
129
Reasoning within output
tag_management f008
100%
Passed
Tokens
64
Input
290
Total output
212
Reasoning within output
tag_management f009
100%
Passed
Tokens
145
Input
75
Total output
58
Reasoning within output
tag_management f010
100%
Passed
Tokens
123
Input
40
Total output
28
Reasoning within output
tag_management f011
100%
Passed
Tokens
123
Input
71
Total output
67
Reasoning within output
tag_management f012
100%
Passed
Tokens
75
Input
125
Total output
122
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
125
Input
170
Total output
167
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
206
Input
572
Total output
585
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
274
Input
94
Total output
94
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
264
Input
75
Total output
70
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
195
Input
61
Total output
47
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
200
Input
149
Total output
133
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
120
Input
452
Total output
434
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
146
Input
477
Total output
413
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
220
Input
135
Total output
148
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
273
Input
188
Total output
172
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
267
Input
91
Total output
82
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
197
Input
67
Total output
48
Reasoning within output