Deepseek / deepseek-v4-pro
high
93.6%
191 / 204 fixtures · 1 run(s)
34,695 input / 66,523 total output / 62,525 reasoning within output tokens $0.18442750
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-11.8%
Text: 93.6% →
JSON: 81.9%
+5
Gained
JSON pass / text fail
−29
Lost
Text pass / JSON fail
162
Unchanged Pass
Both pass
8
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| blame_forensics | 100% | 58.3% | -41.7% |
| commit_squash | 91.7% | 58.3% | -33.3% |
| branch_cleanup | 91.7% | 66.7% | -25% |
| git_show | 100% | 75% | -25% |
| git_grep | 91.7% | 75% | -16.7% |
| worktree_usage | 91.7% | 83.3% | -8.3% |
| cherry_pick | 83.3% | 75% | -8.3% |
| git_bisect | 100% | 91.7% | -8.3% |
| git_clean | 100% | 91.7% | -8.3% |
| git_log_format | 91.7% | 100% | + 8.3% |
| merge_conflicts | 83.3% | 75% | -8.3% |
| rebase | 83.3% | 75% | -8.3% |
| submodule_usage | 83.3% | 75% | -8.3% |
| tag_management | 100% | 91.7% | -8.3% |
| commit_messages | 100% | 100% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
Changed Fixtures (34)
f002 -loss f005 -loss f008 -loss f010 -loss f012 -loss f001 -loss f009 -loss f011 -loss f001 -loss f001 -loss f002 -loss f003 -loss f007 -loss f008 -loss f011 +gain f003 -loss f003 -loss f006 -loss f012 -loss f006 +gain f001 -loss f005 -loss f009 -loss f004 +gain f006 -loss f010 -loss f010 -loss f003 +gain f008 -loss f010 -loss f008 -loss f001 -loss f007 -loss f008 +gain
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
214
Input
259
Total output
254
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
195
Input
466
Total output
460
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
226
Input
248
Total output
241
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
168
Input
241
Total output
234
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
234
Input
2,877
Total output
2,873
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
203
Input
416
Total output
412
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
186
Input
168
Total output
162
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
207
Input
254
Total output
248
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
176
Input
361
Total output
357
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
362
Input
705
Total output
701
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
202
Input
290
Total output
286
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
128
Input
270
Total output
264
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
100
Input
192
Total output
186
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
109
Input
432
Total output
425
Reasoning within output
branch_cleanup f003
0%
Failed
Tokens
92
Input
3
Total output
0
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
121
Input
418
Total output
427
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
98
Input
255
Total output
250
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
117
Input
184
Total output
175
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
103
Input
278
Total output
271
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
117
Input
420
Total output
409
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
81
Input
191
Total output
188
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
108
Input
261
Total output
230
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
69
Input
120
Total output
117
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
153
Input
311
Total output
297
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
93
Input
452
Total output
446
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
120
Input
865
Total output
855
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
88
Input
5
Total output
0
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
147
Input
1,662
Total output
1,640
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
149
Input
215
Total output
197
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
135
Input
768
Total output
747
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
129
Input
221
Total output
210
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
123
Input
122
Total output
114
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
107
Input
100
Total output
93
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
211
Input
394
Total output
368
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
161
Input
464
Total output
441
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
262
Input
1,080
Total output
1,038
Reasoning within output
commit_messages f001
92.7%
Passed
Tokens
100
Input
401
Total output
396
Reasoning within output
commit_messages f002
88.3%
Passed
Tokens
196
Input
371
Total output
365
Reasoning within output
commit_messages f003
93%
Passed
Tokens
81
Input
219
Total output
181
Reasoning within output
commit_messages f004
93.3%
Passed
Tokens
108
Input
153
Total output
148
Reasoning within output
commit_messages f005
87.7%
Passed
Tokens
96
Input
99
Total output
94
Reasoning within output
commit_messages f006
86%
Passed
Tokens
131
Input
201
Total output
194
Reasoning within output
commit_messages f007
93.3%
Passed
Tokens
180
Input
846
Total output
838
Reasoning within output
commit_messages f008
92.7%
Passed
Tokens
66
Input
105
Total output
99
Reasoning within output
commit_messages f009
83.3%
Passed
Tokens
119
Input
252
Total output
244
Reasoning within output
commit_messages f010
95.7%
Passed
Tokens
266
Input
327
Total output
320
Reasoning within output
commit_messages f011
86%
Passed
Tokens
137
Input
939
Total output
926
Reasoning within output
commit_messages f012
93.3%
Passed
Tokens
120
Input
46
Total output
39
Reasoning within output
commit_squash f001
100%
Passed
Tokens
135
Input
537
Total output
523
Reasoning within output
commit_squash f002
100%
Passed
Tokens
113
Input
224
Total output
213
Reasoning within output
commit_squash f003
100%
Passed
Tokens
120
Input
275
Total output
261
Reasoning within output
commit_squash f004
100%
Passed
Tokens
111
Input
519
Total output
506
Reasoning within output
commit_squash f005
100%
Passed
Tokens
106
Input
352
Total output
343
Reasoning within output
commit_squash f006
100%
Passed
Tokens
94
Input
215
Total output
201
Reasoning within output
commit_squash f007
100%
Passed
Tokens
97
Input
196
Total output
182
Reasoning within output
commit_squash f008
100%
Passed
Tokens
109
Input
263
Total output
249
Reasoning within output
commit_squash f009
100%
Passed
Tokens
96
Input
439
Total output
427
Reasoning within output
commit_squash f010
100%
Passed
Tokens
112
Input
180
Total output
163
Reasoning within output
commit_squash f011
0%
Failed
Tokens
125
Input
149
Total output
123
Reasoning within output
commit_squash f012
100%
Passed
Tokens
120
Input
273
Total output
251
Reasoning within output
git_bisect f001
100%
Passed
Tokens
168
Input
91
Total output
0
Reasoning within output
git_bisect f002
100%
Passed
Tokens
187
Input
149
Total output
145
Reasoning within output
git_bisect f003
100%
Passed
Tokens
187
Input
184
Total output
178
Reasoning within output
git_bisect f004
100%
Passed
Tokens
187
Input
245
Total output
240
Reasoning within output
git_bisect f005
100%
Passed
Tokens
189
Input
242
Total output
214
Reasoning within output
git_bisect f006
100%
Passed
Tokens
218
Input
193
Total output
182
Reasoning within output
git_bisect f007
100%
Passed
Tokens
187
Input
251
Total output
245
Reasoning within output
git_bisect f008
100%
Passed
Tokens
191
Input
325
Total output
319
Reasoning within output
git_bisect f009
100%
Passed
Tokens
183
Input
185
Total output
180
Reasoning within output
git_bisect f010
100%
Passed
Tokens
193
Input
277
Total output
271
Reasoning within output
git_bisect f011
100%
Passed
Tokens
185
Input
200
Total output
181
Reasoning within output
git_bisect f012
100%
Passed
Tokens
216
Input
239
Total output
234
Reasoning within output
git_clean f001
100%
Passed
Tokens
49
Input
394
Total output
384
Reasoning within output
git_clean f002
100%
Passed
Tokens
59
Input
5
Total output
0
Reasoning within output
git_clean f003
100%
Passed
Tokens
57
Input
5
Total output
0
Reasoning within output
git_clean f004
100%
Passed
Tokens
57
Input
299
Total output
292
Reasoning within output
git_clean f005
100%
Passed
Tokens
47
Input
266
Total output
258
Reasoning within output
git_clean f006
100%
Passed
Tokens
74
Input
375
Total output
373
Reasoning within output
git_clean f007
100%
Passed
Tokens
69
Input
317
Total output
306
Reasoning within output
git_clean f008
100%
Passed
Tokens
72
Input
148
Total output
142
Reasoning within output
git_clean f009
100%
Passed
Tokens
67
Input
369
Total output
383
Reasoning within output
git_clean f010
100%
Passed
Tokens
63
Input
5
Total output
0
Reasoning within output
git_clean f011
100%
Passed
Tokens
60
Input
303
Total output
296
Reasoning within output
git_clean f012
100%
Passed
Tokens
63
Input
287
Total output
277
Reasoning within output
git_grep f001
100%
Passed
Tokens
52
Input
104
Total output
99
Reasoning within output
git_grep f002
100%
Passed
Tokens
62
Input
96
Total output
93
Reasoning within output
git_grep f003
100%
Passed
Tokens
84
Input
108
Total output
105
Reasoning within output
git_grep f004
100%
Passed
Tokens
72
Input
6
Total output
0
Reasoning within output
git_grep f005
100%
Passed
Tokens
107
Input
157
Total output
161
Reasoning within output
git_grep f006
100%
Passed
Tokens
37
Input
279
Total output
276
Reasoning within output
git_grep f007
0%
Failed
Tokens
156
Input
2
Total output
0
Reasoning within output
git_grep f008
100%
Passed
Tokens
57
Input
135
Total output
152
Reasoning within output
git_grep f009
100%
Passed
Tokens
50
Input
106
Total output
101
Reasoning within output
git_grep f010
100%
Passed
Tokens
60
Input
64
Total output
62
Reasoning within output
git_grep f011
100%
Passed
Tokens
114
Input
52
Total output
49
Reasoning within output
git_grep f012
100%
Passed
Tokens
64
Input
80
Total output
69
Reasoning within output
git_log_format f001
100%
Passed
Tokens
718
Input
141
Total output
138
Reasoning within output
git_log_format f002
100%
Passed
Tokens
695
Input
130
Total output
121
Reasoning within output
git_log_format f003
100%
Passed
Tokens
592
Input
238
Total output
228
Reasoning within output
git_log_format f004
100%
Passed
Tokens
706
Input
61
Total output
58
Reasoning within output
git_log_format f005
100%
Passed
Tokens
573
Input
573
Total output
566
Reasoning within output
git_log_format f006
0%
Failed
Tokens
703
Input
2
Total output
0
Reasoning within output
git_log_format f007
100%
Passed
Tokens
722
Input
46
Total output
39
Reasoning within output
git_log_format f008
100%
Passed
Tokens
938
Input
52
Total output
49
Reasoning within output
git_log_format f009
100%
Passed
Tokens
569
Input
100
Total output
97
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,088
Input
88
Total output
85
Reasoning within output
git_log_format f011
100%
Passed
Tokens
362
Input
145
Total output
141
Reasoning within output
git_log_format f012
100%
Passed
Tokens
323
Input
103
Total output
100
Reasoning within output
git_show f001
100%
Passed
Tokens
167
Input
113
Total output
107
Reasoning within output
git_show f002
100%
Passed
Tokens
163
Input
506
Total output
502
Reasoning within output
git_show f003
100%
Passed
Tokens
557
Input
115
Total output
107
Reasoning within output
git_show f004
100%
Passed
Tokens
386
Input
72
Total output
64
Reasoning within output
git_show f005
100%
Passed
Tokens
169
Input
192
Total output
188
Reasoning within output
git_show f006
100%
Passed
Tokens
181
Input
114
Total output
109
Reasoning within output
git_show f007
100%
Passed
Tokens
162
Input
82
Total output
76
Reasoning within output
git_show f008
100%
Passed
Tokens
179
Input
165
Total output
139
Reasoning within output
git_show f009
100%
Passed
Tokens
257
Input
141
Total output
138
Reasoning within output
git_show f010
100%
Passed
Tokens
164
Input
123
Total output
120
Reasoning within output
git_show f011
100%
Passed
Tokens
206
Input
118
Total output
126
Reasoning within output
git_show f012
100%
Passed
Tokens
291
Input
85
Total output
82
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
84
Input
380
Total output
373
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
109
Input
679
Total output
669
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
79
Input
775
Total output
769
Reasoning within output
merge_conflicts f004
0%
Failed
Tokens
134
Input
1,375
Total output
1,347
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
136
Input
178
Total output
160
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
123
Input
703
Total output
678
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
130
Input
217
Total output
206
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
106
Input
121
Total output
113
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
104
Input
293
Total output
286
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
178
Input
551
Total output
525
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
142
Input
411
Total output
388
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
231
Input
888
Total output
846
Reasoning within output
rebase f001
100%
Passed
Tokens
94
Input
2,460
Total output
2,454
Reasoning within output
rebase f002
100%
Passed
Tokens
129
Input
216
Total output
206
Reasoning within output
rebase f003
100%
Passed
Tokens
103
Input
240
Total output
235
Reasoning within output
rebase f004
0%
Failed
Tokens
146
Input
35
Total output
0
Reasoning within output
rebase f005
100%
Passed
Tokens
139
Input
196
Total output
181
Reasoning within output
rebase f006
100%
Passed
Tokens
135
Input
26
Total output
0
Reasoning within output
rebase f007
100%
Passed
Tokens
132
Input
523
Total output
512
Reasoning within output
rebase f008
100%
Passed
Tokens
117
Input
133
Total output
125
Reasoning within output
rebase f009
100%
Passed
Tokens
101
Input
120
Total output
113
Reasoning within output
rebase f010
100%
Passed
Tokens
201
Input
534
Total output
569
Reasoning within output
rebase f011
100%
Passed
Tokens
152
Input
343
Total output
320
Reasoning within output
rebase f012
0%
Failed
Tokens
264
Input
1,867
Total output
1,826
Reasoning within output
reflog f001
100%
Passed
Tokens
203
Input
166
Total output
142
Reasoning within output
reflog f002
100%
Passed
Tokens
200
Input
580
Total output
490
Reasoning within output
reflog f003
100%
Passed
Tokens
173
Input
390
Total output
292
Reasoning within output
reflog f004
100%
Passed
Tokens
260
Input
681
Total output
562
Reasoning within output
reflog f005
100%
Passed
Tokens
306
Input
2,436
Total output
2,396
Reasoning within output
reflog f006
100%
Passed
Tokens
214
Input
419
Total output
254
Reasoning within output
reflog f007
100%
Passed
Tokens
233
Input
577
Total output
531
Reasoning within output
reflog f008
100%
Passed
Tokens
292
Input
717
Total output
640
Reasoning within output
reflog f009
100%
Passed
Tokens
266
Input
580
Total output
374
Reasoning within output
reflog f010
100%
Passed
Tokens
229
Input
599
Total output
483
Reasoning within output
reflog f011
100%
Passed
Tokens
279
Input
551
Total output
360
Reasoning within output
reflog f012
100%
Passed
Tokens
273
Input
1,859
Total output
1,267
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
123
Input
99
Total output
56
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
272
Input
76
Total output
0
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
111
Input
87
Total output
68
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
110
Input
79
Total output
72
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
119
Input
154
Total output
147
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
167
Input
161
Total output
125
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
192
Input
170
Total output
153
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
163
Input
151
Total output
135
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
198
Input
232
Total output
213
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
118
Input
72
Total output
65
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
109
Input
244
Total output
200
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
127
Input
99
Total output
83
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
40
Input
113
Total output
102
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
88
Input
888
Total output
875
Reasoning within output
submodule_usage f003
75%
Failed
Tokens
91
Input
564
Total output
548
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
81
Input
88
Total output
82
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
47
Input
448
Total output
419
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
76
Input
374
Total output
369
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
48
Input
216
Total output
195
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
85
Input
166
Total output
157
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
78
Input
101
Total output
95
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
92
Input
423
Total output
414
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
96
Input
127
Total output
121
Reasoning within output
submodule_usage f012
0%
Failed
Tokens
46
Input
118
Total output
105
Reasoning within output
tag_management f001
100%
Passed
Tokens
50
Input
51
Total output
43
Reasoning within output
tag_management f002
100%
Passed
Tokens
52
Input
91
Total output
73
Reasoning within output
tag_management f003
100%
Passed
Tokens
57
Input
96
Total output
86
Reasoning within output
tag_management f004
100%
Passed
Tokens
63
Input
146
Total output
142
Reasoning within output
tag_management f005
100%
Passed
Tokens
72
Input
68
Total output
59
Reasoning within output
tag_management f006
100%
Passed
Tokens
59
Input
20
Total output
0
Reasoning within output
tag_management f007
100%
Passed
Tokens
61
Input
32
Total output
0
Reasoning within output
tag_management f008
100%
Passed
Tokens
63
Input
21
Total output
0
Reasoning within output
tag_management f009
100%
Passed
Tokens
66
Input
146
Total output
128
Reasoning within output
tag_management f010
100%
Passed
Tokens
44
Input
85
Total output
76
Reasoning within output
tag_management f011
100%
Passed
Tokens
43
Input
133
Total output
126
Reasoning within output
tag_management f012
100%
Passed
Tokens
78
Input
408
Total output
397
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
128
Input
118
Total output
107
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
132
Input
532
Total output
508
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
192
Input
295
Total output
285
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
195
Input
83
Total output
77
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
119
Input
198
Total output
183
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
125
Input
279
Total output
263
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
121
Input
443
Total output
422
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
142
Input
793
Total output
751
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
216
Input
63
Total output
57
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
191
Input
476
Total output
459
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
187
Input
161
Total output
139
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
119
Input
119
Total output
104
Reasoning within output