Deepseek / deepseek-v4-pro
xhigh
90.7%
185 / 204 fixtures · 1 run(s)
46,330 input / 148,856 total output / 144,873 reasoning within output tokens $0.42033928
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-4.4%
Text: 90.7% →
JSON: 86.3%
+9
Gained
JSON pass / text fail
−18
Lost
Text pass / JSON fail
167
Unchanged Pass
Both pass
10
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| branch_cleanup | 100% | 66.7% | -33.3% |
| commit_squash | 66.7% | 41.7% | -25% |
| git_show | 100% | 83.3% | -16.7% |
| tag_management | 75% | 91.7% | + 16.7% |
| merge_conflicts | 83.3% | 91.7% | + 8.3% |
| commit_messages | 100% | 91.7% | -8.3% |
| git_clean | 100% | 91.7% | -8.3% |
| git_log_format | 100% | 91.7% | -8.3% |
| blame_forensics | 83.3% | 83.3% | + 0% |
| cherry_pick | 75% | 75% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_grep | 91.7% | 91.7% | + 0% |
| rebase | 75% | 75% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 100% | 100% | + 0% |
| worktree_usage | 91.7% | 91.7% | + 0% |
Changed Fixtures (27)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
222
Input
504
Total output
564
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
282
Input
1,019
Total output
1,014
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
305
Input
125
Total output
117
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
166
Input
1,034
Total output
1,090
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
314
Input
13,487
Total output
13,479
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
286
Input
2,566
Total output
2,561
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
261
Input
421
Total output
414
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
283
Input
308
Total output
302
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
251
Input
489
Total output
484
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
373
Input
473
Total output
470
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
283
Input
1,209
Total output
1,150
Reasoning within output
blame_forensics f012
0%
Failed
Tokens
128
Input
356
Total output
375
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
184
Input
553
Total output
547
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
192
Input
202
Total output
195
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
87
Input
469
Total output
466
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
201
Input
929
Total output
921
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
99
Input
504
Total output
552
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
120
Input
249
Total output
255
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
103
Input
312
Total output
305
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
202
Input
317
Total output
305
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
157
Input
703
Total output
700
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
116
Input
336
Total output
329
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
67
Input
99
Total output
109
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
146
Input
13
Total output
0
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
170
Input
682
Total output
676
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
199
Input
1,504
Total output
1,495
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
88
Input
5
Total output
0
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
225
Input
2,965
Total output
2,944
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
228
Input
325
Total output
307
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
215
Input
714
Total output
693
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
208
Input
381
Total output
370
Reasoning within output
cherry_pick f008
0%
Failed
Tokens
123
Input
173
Total output
182
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
186
Input
297
Total output
290
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
290
Input
1,250
Total output
1,224
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
240
Input
772
Total output
749
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
341
Input
4,295
Total output
4,253
Reasoning within output
commit_messages f001
93.3%
Passed
Tokens
179
Input
513
Total output
508
Reasoning within output
commit_messages f002
80.7%
Passed
Tokens
196
Input
318
Total output
331
Reasoning within output
commit_messages f003
94.7%
Passed
Tokens
160
Input
309
Total output
298
Reasoning within output
commit_messages f004
92.7%
Passed
Tokens
187
Input
379
Total output
374
Reasoning within output
commit_messages f005
61.7%
Passed
Tokens
175
Input
994
Total output
1,098
Reasoning within output
commit_messages f006
91%
Passed
Tokens
131
Input
269
Total output
262
Reasoning within output
commit_messages f007
81.7%
Passed
Tokens
259
Input
396
Total output
452
Reasoning within output
commit_messages f008
90%
Passed
Tokens
145
Input
240
Total output
235
Reasoning within output
commit_messages f009
91.7%
Passed
Tokens
119
Input
7
Total output
0
Reasoning within output
commit_messages f010
89%
Passed
Tokens
266
Input
8
Total output
0
Reasoning within output
commit_messages f011
81.3%
Passed
Tokens
216
Input
818
Total output
803
Reasoning within output
commit_messages f012
89.7%
Passed
Tokens
120
Input
534
Total output
354
Reasoning within output
commit_squash f001
0%
Failed
Tokens
211
Input
2,744
Total output
2,721
Reasoning within output
commit_squash f002
0%
Failed
Tokens
112
Input
194
Total output
197
Reasoning within output
commit_squash f003
0%
Failed
Tokens
125
Input
468
Total output
448
Reasoning within output
commit_squash f004
100%
Passed
Tokens
190
Input
3,767
Total output
3,754
Reasoning within output
commit_squash f005
100%
Passed
Tokens
105
Input
285
Total output
276
Reasoning within output
commit_squash f006
100%
Passed
Tokens
173
Input
854
Total output
840
Reasoning within output
commit_squash f007
100%
Passed
Tokens
176
Input
884
Total output
869
Reasoning within output
commit_squash f008
0%
Failed
Tokens
107
Input
358
Total output
337
Reasoning within output
commit_squash f009
100%
Passed
Tokens
99
Input
12
Total output
0
Reasoning within output
commit_squash f010
100%
Passed
Tokens
196
Input
368
Total output
352
Reasoning within output
commit_squash f011
100%
Passed
Tokens
200
Input
493
Total output
476
Reasoning within output
commit_squash f012
100%
Passed
Tokens
200
Input
768
Total output
746
Reasoning within output
git_bisect f001
100%
Passed
Tokens
245
Input
227
Total output
222
Reasoning within output
git_bisect f002
100%
Passed
Tokens
268
Input
365
Total output
309
Reasoning within output
git_bisect f003
100%
Passed
Tokens
266
Input
207
Total output
200
Reasoning within output
git_bisect f004
100%
Passed
Tokens
276
Input
273
Total output
266
Reasoning within output
git_bisect f005
100%
Passed
Tokens
272
Input
397
Total output
389
Reasoning within output
git_bisect f006
100%
Passed
Tokens
295
Input
337
Total output
332
Reasoning within output
git_bisect f007
100%
Passed
Tokens
191
Input
181
Total output
174
Reasoning within output
git_bisect f008
100%
Passed
Tokens
268
Input
317
Total output
310
Reasoning within output
git_bisect f009
100%
Passed
Tokens
264
Input
289
Total output
283
Reasoning within output
git_bisect f010
100%
Passed
Tokens
268
Input
303
Total output
298
Reasoning within output
git_bisect f011
100%
Passed
Tokens
280
Input
364
Total output
358
Reasoning within output
git_bisect f012
100%
Passed
Tokens
297
Input
219
Total output
212
Reasoning within output
git_clean f001
100%
Passed
Tokens
128
Input
378
Total output
368
Reasoning within output
git_clean f002
100%
Passed
Tokens
59
Input
5
Total output
0
Reasoning within output
git_clean f003
100%
Passed
Tokens
136
Input
249
Total output
243
Reasoning within output
git_clean f004
100%
Passed
Tokens
57
Input
413
Total output
406
Reasoning within output
git_clean f005
100%
Passed
Tokens
126
Input
1,228
Total output
1,223
Reasoning within output
git_clean f006
100%
Passed
Tokens
153
Input
880
Total output
873
Reasoning within output
git_clean f007
100%
Passed
Tokens
148
Input
651
Total output
641
Reasoning within output
git_clean f008
100%
Passed
Tokens
151
Input
255
Total output
249
Reasoning within output
git_clean f009
100%
Passed
Tokens
146
Input
1,861
Total output
1,851
Reasoning within output
git_clean f010
100%
Passed
Tokens
142
Input
262
Total output
254
Reasoning within output
git_clean f011
100%
Passed
Tokens
139
Input
418
Total output
411
Reasoning within output
git_clean f012
100%
Passed
Tokens
142
Input
1,234
Total output
1,225
Reasoning within output
git_grep f001
100%
Passed
Tokens
52
Input
86
Total output
90
Reasoning within output
git_grep f002
100%
Passed
Tokens
142
Input
103
Total output
100
Reasoning within output
git_grep f003
100%
Passed
Tokens
163
Input
158
Total output
155
Reasoning within output
git_grep f004
100%
Passed
Tokens
72
Input
6
Total output
0
Reasoning within output
git_grep f005
100%
Passed
Tokens
186
Input
111
Total output
109
Reasoning within output
git_grep f006
100%
Passed
Tokens
116
Input
281
Total output
279
Reasoning within output
git_grep f007
0%
Failed
Tokens
156
Input
2
Total output
0
Reasoning within output
git_grep f008
100%
Passed
Tokens
136
Input
111
Total output
108
Reasoning within output
git_grep f009
100%
Passed
Tokens
50
Input
91
Total output
86
Reasoning within output
git_grep f010
100%
Passed
Tokens
139
Input
104
Total output
101
Reasoning within output
git_grep f011
100%
Passed
Tokens
193
Input
167
Total output
164
Reasoning within output
git_grep f012
100%
Passed
Tokens
143
Input
146
Total output
135
Reasoning within output
git_log_format f001
100%
Passed
Tokens
735
Input
2
Total output
0
Reasoning within output
git_log_format f002
100%
Passed
Tokens
776
Input
231
Total output
222
Reasoning within output
git_log_format f003
100%
Passed
Tokens
632
Input
93
Total output
82
Reasoning within output
git_log_format f004
100%
Passed
Tokens
773
Input
226
Total output
223
Reasoning within output
git_log_format f005
100%
Passed
Tokens
652
Input
943
Total output
937
Reasoning within output
git_log_format f006
100%
Passed
Tokens
703
Input
2
Total output
0
Reasoning within output
git_log_format f007
100%
Passed
Tokens
802
Input
144
Total output
137
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,033
Input
182
Total output
179
Reasoning within output
git_log_format f009
100%
Passed
Tokens
642
Input
98
Total output
95
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,126
Input
110
Total output
108
Reasoning within output
git_log_format f011
100%
Passed
Tokens
439
Input
144
Total output
141
Reasoning within output
git_log_format f012
100%
Passed
Tokens
403
Input
109
Total output
106
Reasoning within output
git_show f001
100%
Passed
Tokens
249
Input
174
Total output
167
Reasoning within output
git_show f002
100%
Passed
Tokens
165
Input
478
Total output
523
Reasoning within output
git_show f003
100%
Passed
Tokens
646
Input
203
Total output
195
Reasoning within output
git_show f004
100%
Passed
Tokens
388
Input
83
Total output
68
Reasoning within output
git_show f005
100%
Passed
Tokens
171
Input
87
Total output
83
Reasoning within output
git_show f006
100%
Passed
Tokens
254
Input
205
Total output
203
Reasoning within output
git_show f007
100%
Passed
Tokens
241
Input
182
Total output
176
Reasoning within output
git_show f008
100%
Passed
Tokens
255
Input
147
Total output
124
Reasoning within output
git_show f009
100%
Passed
Tokens
339
Input
223
Total output
220
Reasoning within output
git_show f010
100%
Passed
Tokens
170
Input
132
Total output
138
Reasoning within output
git_show f011
100%
Passed
Tokens
282
Input
128
Total output
124
Reasoning within output
git_show f012
100%
Passed
Tokens
379
Input
125
Total output
122
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
163
Input
1,077
Total output
1,071
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
188
Input
1,659
Total output
1,649
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
79
Input
538
Total output
589
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
213
Input
9,635
Total output
9,611
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
215
Input
400
Total output
382
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
202
Input
803
Total output
782
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
209
Input
381
Total output
370
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
185
Input
605
Total output
597
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
183
Input
174
Total output
167
Reasoning within output
merge_conflicts f010
50%
Failed
Tokens
178
Input
25
Total output
0
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
221
Input
601
Total output
578
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
310
Input
2,587
Total output
2,545
Reasoning within output
rebase f001
100%
Passed
Tokens
174
Input
944
Total output
938
Reasoning within output
rebase f002
100%
Passed
Tokens
127
Input
194
Total output
173
Reasoning within output
rebase f003
100%
Passed
Tokens
101
Input
4
Total output
0
Reasoning within output
rebase f004
0%
Failed
Tokens
224
Input
14,481
Total output
14,461
Reasoning within output
rebase f005
100%
Passed
Tokens
219
Input
474
Total output
454
Reasoning within output
rebase f006
100%
Passed
Tokens
213
Input
1,389
Total output
1,368
Reasoning within output
rebase f007
100%
Passed
Tokens
210
Input
669
Total output
658
Reasoning within output
rebase f008
100%
Passed
Tokens
197
Input
1,557
Total output
1,549
Reasoning within output
rebase f009
100%
Passed
Tokens
103
Input
6
Total output
0
Reasoning within output
rebase f010
0%
Failed
Tokens
203
Input
32
Total output
0
Reasoning within output
rebase f011
100%
Passed
Tokens
229
Input
309
Total output
286
Reasoning within output
rebase f012
0%
Failed
Tokens
341
Input
4,732
Total output
4,685
Reasoning within output
reflog f001
100%
Passed
Tokens
281
Input
374
Total output
347
Reasoning within output
reflog f002
100%
Passed
Tokens
279
Input
468
Total output
379
Reasoning within output
reflog f003
100%
Passed
Tokens
250
Input
359
Total output
270
Reasoning within output
reflog f004
100%
Passed
Tokens
351
Input
1,766
Total output
1,543
Reasoning within output
reflog f005
100%
Passed
Tokens
323
Input
681
Total output
590
Reasoning within output
reflog f006
100%
Passed
Tokens
293
Input
406
Total output
304
Reasoning within output
reflog f007
100%
Passed
Tokens
240
Input
845
Total output
790
Reasoning within output
reflog f008
100%
Passed
Tokens
378
Input
1,099
Total output
998
Reasoning within output
reflog f009
100%
Passed
Tokens
345
Input
2,478
Total output
2,298
Reasoning within output
reflog f010
100%
Passed
Tokens
308
Input
1,069
Total output
728
Reasoning within output
reflog f011
100%
Passed
Tokens
347
Input
3,270
Total output
3,098
Reasoning within output
reflog f012
100%
Passed
Tokens
259
Input
409
Total output
0
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
201
Input
128
Total output
122
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
345
Input
326
Total output
211
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
190
Input
191
Total output
166
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
110
Input
137
Total output
117
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
200
Input
338
Total output
290
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
246
Input
184
Total output
156
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
192
Input
130
Total output
126
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
163
Input
96
Total output
0
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
277
Input
1,263
Total output
1,200
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
118
Input
163
Total output
148
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
186
Input
116
Total output
109
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
206
Input
238
Total output
231
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
119
Input
324
Total output
313
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
172
Input
636
Total output
623
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
93
Input
24
Total output
0
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
160
Input
348
Total output
343
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
126
Input
562
Total output
540
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
159
Input
630
Total output
624
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
48
Input
119
Total output
98
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
87
Input
7
Total output
0
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
164
Input
355
Total output
349
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
165
Input
408
Total output
400
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
172
Input
171
Total output
165
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
125
Input
302
Total output
288
Reasoning within output
tag_management f001
0%
Failed
Tokens
52
Input
113
Total output
92
Reasoning within output
tag_management f002
100%
Passed
Tokens
133
Input
227
Total output
208
Reasoning within output
tag_management f003
100%
Passed
Tokens
137
Input
471
Total output
460
Reasoning within output
tag_management f004
100%
Passed
Tokens
142
Input
401
Total output
398
Reasoning within output
tag_management f005
100%
Passed
Tokens
157
Input
334
Total output
324
Reasoning within output
tag_management f006
100%
Passed
Tokens
135
Input
491
Total output
480
Reasoning within output
tag_management f007
66.7%
Failed
Tokens
137
Input
1,075
Total output
1,059
Reasoning within output
tag_management f008
100%
Passed
Tokens
142
Input
1,091
Total output
1,065
Reasoning within output
tag_management f009
100%
Passed
Tokens
145
Input
194
Total output
176
Reasoning within output
tag_management f010
0%
Failed
Tokens
43
Input
48
Total output
34
Reasoning within output
tag_management f011
100%
Passed
Tokens
120
Input
62
Total output
56
Reasoning within output
tag_management f012
100%
Passed
Tokens
156
Input
944
Total output
933
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
199
Input
115
Total output
104
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
210
Input
1,121
Total output
1,105
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
266
Input
588
Total output
578
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
188
Input
47
Total output
45
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
199
Input
345
Total output
330
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
195
Input
793
Total output
776
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
203
Input
860
Total output
839
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
143
Input
1,072
Total output
1,019
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
302
Input
501
Total output
495
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
267
Input
524
Total output
506
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
268
Input
340
Total output
301
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
118
Input
253
Total output
198
Reasoning within output