Deepseek / deepseek-v4-pro
medium
93.6%
191 / 204 fixtures · 1 run(s)
34,710 input / 76,546 total output / 72,687 reasoning within output tokens $0.22833374
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-11.3%
Text: 93.6% →
JSON: 82.4%
+9
Gained
JSON pass / text fail
−32
Lost
Text pass / JSON fail
159
Unchanged Pass
Both pass
4
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| blame_forensics | 91.7% | 50% | -41.7% |
| commit_squash | 91.7% | 50% | -41.7% |
| worktree_usage | 58.3% | 100% | + 41.7% |
| branch_cleanup | 100% | 66.7% | -33.3% |
| git_show | 100% | 66.7% | -33.3% |
| git_grep | 100% | 75% | -25% |
| git_clean | 100% | 83.3% | -16.7% |
| tag_management | 100% | 83.3% | -16.7% |
| merge_conflicts | 83.3% | 66.7% | -16.7% |
| cherry_pick | 83.3% | 91.7% | + 8.3% |
| rebase | 83.3% | 91.7% | + 8.3% |
| git_log_format | 100% | 91.7% | -8.3% |
| reflog | 100% | 91.7% | -8.3% |
| submodule_usage | 100% | 91.7% | -8.3% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
Changed Fixtures (41)
f001 -loss f002 -loss f005 +gain f006 -loss f008 -loss f010 -loss f012 -loss f003 -loss f009 -loss f010 -loss f011 -loss f004 +gain f003 -loss f006 -loss f007 -loss f011 -loss f012 -loss f004 -loss f006 -loss f002 -loss f006 -loss f007 -loss f009 -loss f002 -loss f003 -loss f005 -loss f011 -loss f001 -loss f002 -loss f004 +gain f010 -loss f004 +gain f001 -loss f003 -loss f007 -loss f008 -loss f005 +gain f007 +gain f008 +gain f011 +gain f012 +gain
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
220
Input
1,209
Total output
1,396
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
195
Input
580
Total output
549
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
225
Input
312
Total output
305
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
164
Input
6
Total output
0
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
224
Input
4,986
Total output
4,978
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
202
Input
643
Total output
638
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
187
Input
317
Total output
310
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
212
Input
273
Total output
289
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
172
Input
217
Total output
212
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
359
Input
4
Total output
0
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
202
Input
358
Total output
353
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
127
Input
304
Total output
298
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
102
Input
291
Total output
285
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
107
Input
549
Total output
542
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
89
Input
216
Total output
238
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
122
Input
7
Total output
0
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
100
Input
246
Total output
241
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
117
Input
240
Total output
231
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
103
Input
161
Total output
154
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
117
Input
298
Total output
287
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
76
Input
119
Total output
116
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
111
Input
134
Total output
121
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
68
Input
121
Total output
118
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
150
Input
318
Total output
304
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
92
Input
577
Total output
571
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
121
Input
251
Total output
241
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
89
Input
380
Total output
374
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
146
Input
1,124
Total output
1,103
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
149
Input
244
Total output
226
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
135
Input
280
Total output
259
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
129
Input
321
Total output
310
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
121
Input
160
Total output
152
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
107
Input
188
Total output
181
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
211
Input
380
Total output
354
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
160
Input
269
Total output
246
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
264
Input
1,438
Total output
1,391
Reasoning within output
commit_messages f001
80.7%
Passed
Tokens
100
Input
319
Total output
304
Reasoning within output
commit_messages f002
84.3%
Passed
Tokens
196
Input
301
Total output
289
Reasoning within output
commit_messages f003
96.7%
Passed
Tokens
81
Input
212
Total output
201
Reasoning within output
commit_messages f004
93.7%
Passed
Tokens
108
Input
117
Total output
113
Reasoning within output
commit_messages f005
90%
Passed
Tokens
96
Input
185
Total output
189
Reasoning within output
commit_messages f006
91.7%
Passed
Tokens
131
Input
483
Total output
475
Reasoning within output
commit_messages f007
91.7%
Passed
Tokens
180
Input
292
Total output
283
Reasoning within output
commit_messages f008
89.3%
Passed
Tokens
66
Input
190
Total output
185
Reasoning within output
commit_messages f009
80%
Passed
Tokens
119
Input
332
Total output
322
Reasoning within output
commit_messages f010
92.7%
Passed
Tokens
266
Input
269
Total output
269
Reasoning within output
commit_messages f011
80%
Passed
Tokens
137
Input
765
Total output
752
Reasoning within output
commit_messages f012
87.7%
Passed
Tokens
120
Input
315
Total output
310
Reasoning within output
commit_squash f001
100%
Passed
Tokens
128
Input
780
Total output
766
Reasoning within output
commit_squash f002
100%
Passed
Tokens
112
Input
220
Total output
209
Reasoning within output
commit_squash f003
100%
Passed
Tokens
121
Input
255
Total output
241
Reasoning within output
commit_squash f004
100%
Passed
Tokens
110
Input
111
Total output
98
Reasoning within output
commit_squash f005
100%
Passed
Tokens
103
Input
361
Total output
352
Reasoning within output
commit_squash f006
100%
Passed
Tokens
93
Input
13
Total output
0
Reasoning within output
commit_squash f007
100%
Passed
Tokens
95
Input
252
Total output
238
Reasoning within output
commit_squash f008
100%
Passed
Tokens
107
Input
204
Total output
190
Reasoning within output
commit_squash f009
100%
Passed
Tokens
100
Input
206
Total output
193
Reasoning within output
commit_squash f010
0%
Failed
Tokens
115
Input
26
Total output
0
Reasoning within output
commit_squash f011
100%
Passed
Tokens
124
Input
223
Total output
184
Reasoning within output
commit_squash f012
100%
Passed
Tokens
118
Input
212
Total output
190
Reasoning within output
git_bisect f001
100%
Passed
Tokens
164
Input
97
Total output
0
Reasoning within output
git_bisect f002
100%
Passed
Tokens
191
Input
279
Total output
270
Reasoning within output
git_bisect f003
100%
Passed
Tokens
183
Input
142
Total output
142
Reasoning within output
git_bisect f004
100%
Passed
Tokens
193
Input
201
Total output
195
Reasoning within output
git_bisect f005
100%
Passed
Tokens
189
Input
281
Total output
273
Reasoning within output
git_bisect f006
100%
Passed
Tokens
218
Input
168
Total output
153
Reasoning within output
git_bisect f007
100%
Passed
Tokens
189
Input
145
Total output
139
Reasoning within output
git_bisect f008
100%
Passed
Tokens
191
Input
193
Total output
160
Reasoning within output
git_bisect f009
100%
Passed
Tokens
187
Input
246
Total output
239
Reasoning within output
git_bisect f010
100%
Passed
Tokens
183
Input
231
Total output
226
Reasoning within output
git_bisect f011
100%
Passed
Tokens
193
Input
236
Total output
228
Reasoning within output
git_bisect f012
100%
Passed
Tokens
210
Input
283
Total output
276
Reasoning within output
git_clean f001
100%
Passed
Tokens
49
Input
330
Total output
320
Reasoning within output
git_clean f002
100%
Passed
Tokens
59
Input
163
Total output
166
Reasoning within output
git_clean f003
100%
Passed
Tokens
57
Input
176
Total output
170
Reasoning within output
git_clean f004
100%
Passed
Tokens
57
Input
385
Total output
378
Reasoning within output
git_clean f005
100%
Passed
Tokens
47
Input
335
Total output
329
Reasoning within output
git_clean f006
100%
Passed
Tokens
74
Input
386
Total output
379
Reasoning within output
git_clean f007
100%
Passed
Tokens
69
Input
239
Total output
229
Reasoning within output
git_clean f008
100%
Passed
Tokens
72
Input
221
Total output
216
Reasoning within output
git_clean f009
100%
Passed
Tokens
67
Input
626
Total output
617
Reasoning within output
git_clean f010
100%
Passed
Tokens
63
Input
214
Total output
206
Reasoning within output
git_clean f011
100%
Passed
Tokens
60
Input
309
Total output
302
Reasoning within output
git_clean f012
100%
Passed
Tokens
63
Input
394
Total output
381
Reasoning within output
git_grep f001
100%
Passed
Tokens
52
Input
89
Total output
84
Reasoning within output
git_grep f002
100%
Passed
Tokens
60
Input
86
Total output
86
Reasoning within output
git_grep f003
100%
Passed
Tokens
84
Input
54
Total output
51
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
145
Total output
142
Reasoning within output
git_grep f006
100%
Passed
Tokens
37
Input
141
Total output
138
Reasoning within output
git_grep f007
100%
Passed
Tokens
156
Input
413
Total output
410
Reasoning within output
git_grep f008
100%
Passed
Tokens
57
Input
104
Total output
101
Reasoning within output
git_grep f009
100%
Passed
Tokens
50
Input
80
Total output
75
Reasoning within output
git_grep f010
100%
Passed
Tokens
60
Input
112
Total output
109
Reasoning within output
git_grep f011
100%
Passed
Tokens
114
Input
119
Total output
116
Reasoning within output
git_grep f012
100%
Passed
Tokens
64
Input
124
Total output
113
Reasoning within output
git_log_format f001
100%
Passed
Tokens
716
Input
96
Total output
93
Reasoning within output
git_log_format f002
100%
Passed
Tokens
689
Input
8
Total output
0
Reasoning within output
git_log_format f003
100%
Passed
Tokens
586
Input
300
Total output
289
Reasoning within output
git_log_format f004
100%
Passed
Tokens
698
Input
161
Total output
154
Reasoning within output
git_log_format f005
100%
Passed
Tokens
573
Input
133
Total output
125
Reasoning within output
git_log_format f006
100%
Passed
Tokens
703
Input
211
Total output
208
Reasoning within output
git_log_format f007
100%
Passed
Tokens
727
Input
86
Total output
79
Reasoning within output
git_log_format f008
100%
Passed
Tokens
966
Input
63
Total output
60
Reasoning within output
git_log_format f009
100%
Passed
Tokens
580
Input
81
Total output
79
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,057
Input
99
Total output
96
Reasoning within output
git_log_format f011
100%
Passed
Tokens
353
Input
102
Total output
98
Reasoning within output
git_log_format f012
100%
Passed
Tokens
320
Input
124
Total output
114
Reasoning within output
git_show f001
100%
Passed
Tokens
174
Input
107
Total output
100
Reasoning within output
git_show f002
100%
Passed
Tokens
169
Input
399
Total output
395
Reasoning within output
git_show f003
100%
Passed
Tokens
565
Input
7
Total output
0
Reasoning within output
git_show f004
100%
Passed
Tokens
394
Input
146
Total output
138
Reasoning within output
git_show f005
100%
Passed
Tokens
174
Input
134
Total output
130
Reasoning within output
git_show f006
100%
Passed
Tokens
177
Input
74
Total output
71
Reasoning within output
git_show f007
100%
Passed
Tokens
162
Input
94
Total output
88
Reasoning within output
git_show f008
100%
Passed
Tokens
178
Input
157
Total output
132
Reasoning within output
git_show f009
100%
Passed
Tokens
258
Input
260
Total output
254
Reasoning within output
git_show f010
100%
Passed
Tokens
171
Input
174
Total output
171
Reasoning within output
git_show f011
100%
Passed
Tokens
200
Input
58
Total output
54
Reasoning within output
git_show f012
100%
Passed
Tokens
291
Input
183
Total output
184
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
84
Input
435
Total output
429
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
109
Input
462
Total output
412
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
79
Input
613
Total output
678
Reasoning within output
merge_conflicts f004
0%
Failed
Tokens
134
Input
1,516
Total output
1,487
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
136
Input
351
Total output
333
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
123
Input
366
Total output
346
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
130
Input
231
Total output
220
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
106
Input
7
Total output
0
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
104
Input
349
Total output
342
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
178
Input
861
Total output
835
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
142
Input
332
Total output
309
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
231
Input
941
Total output
900
Reasoning within output
rebase f001
100%
Passed
Tokens
96
Input
5,123
Total output
5,117
Reasoning within output
rebase f002
100%
Passed
Tokens
128
Input
9
Total output
0
Reasoning within output
rebase f003
100%
Passed
Tokens
102
Input
175
Total output
170
Reasoning within output
rebase f004
0%
Failed
Tokens
144
Input
2,638
Total output
2,617
Reasoning within output
rebase f005
100%
Passed
Tokens
141
Input
343
Total output
362
Reasoning within output
rebase f006
100%
Passed
Tokens
135
Input
372
Total output
351
Reasoning within output
rebase f007
100%
Passed
Tokens
130
Input
239
Total output
228
Reasoning within output
rebase f008
100%
Passed
Tokens
119
Input
759
Total output
751
Reasoning within output
rebase f009
100%
Passed
Tokens
101
Input
220
Total output
213
Reasoning within output
rebase f010
100%
Passed
Tokens
201
Input
1,053
Total output
1,027
Reasoning within output
rebase f011
100%
Passed
Tokens
152
Input
1,267
Total output
1,245
Reasoning within output
rebase f012
0%
Failed
Tokens
262
Input
1,240
Total output
1,319
Reasoning within output
reflog f001
100%
Passed
Tokens
196
Input
338
Total output
314
Reasoning within output
reflog f002
100%
Passed
Tokens
187
Input
387
Total output
259
Reasoning within output
reflog f003
100%
Passed
Tokens
174
Input
341
Total output
220
Reasoning within output
reflog f004
100%
Passed
Tokens
273
Input
1,394
Total output
1,091
Reasoning within output
reflog f005
100%
Passed
Tokens
319
Input
454
Total output
411
Reasoning within output
reflog f006
100%
Passed
Tokens
211
Input
207
Total output
143
Reasoning within output
reflog f007
100%
Passed
Tokens
241
Input
612
Total output
576
Reasoning within output
reflog f008
100%
Passed
Tokens
318
Input
741
Total output
621
Reasoning within output
reflog f009
100%
Passed
Tokens
278
Input
1,129
Total output
999
Reasoning within output
reflog f010
100%
Passed
Tokens
236
Input
156
Total output
0
Reasoning within output
reflog f011
100%
Passed
Tokens
270
Input
936
Total output
775
Reasoning within output
reflog f012
100%
Passed
Tokens
266
Input
1,519
Total output
964
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
123
Input
135
Total output
128
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
269
Input
185
Total output
86
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
111
Input
99
Total output
81
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
110
Input
121
Total output
103
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
121
Input
187
Total output
145
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
167
Input
150
Total output
116
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
196
Input
213
Total output
206
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
163
Input
123
Total output
110
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
198
Input
182
Total output
161
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
118
Input
49
Total output
0
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
109
Input
160
Total output
153
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
127
Input
139
Total output
126
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
40
Input
113
Total output
102
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
90
Input
507
Total output
549
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
92
Input
1,544
Total output
1,519
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
82
Input
5
Total output
0
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
47
Input
265
Total output
231
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
81
Input
411
Total output
406
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
48
Input
277
Total output
256
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
82
Input
372
Total output
365
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
83
Input
143
Total output
137
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
90
Input
385
Total output
376
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
92
Input
81
Total output
75
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
46
Input
197
Total output
183
Reasoning within output
tag_management f001
100%
Passed
Tokens
53
Input
81
Total output
76
Reasoning within output
tag_management f002
100%
Passed
Tokens
52
Input
128
Total output
109
Reasoning within output
tag_management f003
100%
Passed
Tokens
57
Input
138
Total output
127
Reasoning within output
tag_management f004
100%
Passed
Tokens
63
Input
3
Total output
0
Reasoning within output
tag_management f005
100%
Passed
Tokens
76
Input
9
Total output
0
Reasoning within output
tag_management f006
100%
Passed
Tokens
57
Input
17
Total output
0
Reasoning within output
tag_management f007
100%
Passed
Tokens
58
Input
542
Total output
528
Reasoning within output
tag_management f008
100%
Passed
Tokens
66
Input
519
Total output
421
Reasoning within output
tag_management f009
100%
Passed
Tokens
66
Input
136
Total output
118
Reasoning within output
tag_management f010
100%
Passed
Tokens
45
Input
113
Total output
105
Reasoning within output
tag_management f011
100%
Passed
Tokens
44
Input
246
Total output
239
Reasoning within output
tag_management f012
100%
Passed
Tokens
77
Input
817
Total output
807
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
127
Input
332
Total output
322
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
129
Input
473
Total output
451
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
188
Input
357
Total output
343
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
192
Input
116
Total output
110
Reasoning within output
worktree_usage f005
33.3%
Failed
Tokens
118
Input
229
Total output
226
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
118
Input
216
Total output
199
Reasoning within output
worktree_usage f007
0%
Failed
Tokens
126
Input
715
Total output
690
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
144
Input
879
Total output
801
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
217
Input
135
Total output
144
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
192
Input
384
Total output
367
Reasoning within output
worktree_usage f011
0%
Failed
Tokens
185
Input
110
Total output
105
Reasoning within output
worktree_usage f012
0%
Failed
Tokens
116
Input
518
Total output
464
Reasoning within output