Deepseek / deepseek-v4-flash-0731
max
96.1%
196 / 204 fixtures · 1 run(s)
52,129 input / 225,121 total output / 221,042 reasoning within output tokens $0.06378496
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-5.4%
Text: 96.1% →
JSON: 90.7%
+0
Gained
JSON pass / text fail
−12
Lost
Text pass / JSON fail
184
Unchanged Pass
Both pass
8
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| branch_cleanup | 100% | 83.3% | -16.7% |
| git_clean | 100% | 83.3% | -16.7% |
| git_show | 91.7% | 75% | -16.7% |
| submodule_usage | 100% | 83.3% | -16.7% |
| rebase | 91.7% | 83.3% | -8.3% |
| git_grep | 100% | 91.7% | -8.3% |
| tag_management | 100% | 91.7% | -8.3% |
| blame_forensics | 100% | 100% | + 0% |
| cherry_pick | 83.3% | 83.3% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| commit_squash | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| merge_conflicts | 91.7% | 91.7% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| worktree_usage | 75% | 75% | + 0% |
Changed Fixtures (12)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
323
Input
909
Total output
919
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
272
Input
789
Total output
795
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
311
Input
64
Total output
57
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
256
Input
1,924
Total output
1,918
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
306
Input
65
Total output
74
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
292
Input
662
Total output
658
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
279
Input
224
Total output
225
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
303
Input
892
Total output
884
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
250
Input
177
Total output
194
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
474
Input
427
Total output
432
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
279
Input
77
Total output
73
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
206
Input
111
Total output
105
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
183
Input
245
Total output
232
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
205
Input
373
Total output
367
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
182
Input
109
Total output
107
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
198
Input
169
Total output
171
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
182
Input
164
Total output
160
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
198
Input
155
Total output
144
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
193
Input
146
Total output
140
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
193
Input
350
Total output
327
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
157
Input
85
Total output
83
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
188
Input
113
Total output
115
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
147
Input
71
Total output
75
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
228
Input
184
Total output
181
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
173
Input
546
Total output
628
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
212
Input
4,351
Total output
3,995
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
186
Input
4,859
Total output
5,450
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
238
Input
807
Total output
787
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
243
Input
384
Total output
367
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
215
Input
255
Total output
210
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
219
Input
845
Total output
835
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
200
Input
68
Total output
77
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
205
Input
277
Total output
287
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
292
Input
306
Total output
321
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
251
Input
227
Total output
194
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
343
Input
1,105
Total output
1,090
Reasoning within output
commit_messages f001
93.7%
Passed
Tokens
192
Input
62
Total output
58
Reasoning within output
commit_messages f002
84.3%
Passed
Tokens
288
Input
419
Total output
409
Reasoning within output
commit_messages f003
91.7%
Passed
Tokens
173
Input
152
Total output
108
Reasoning within output
commit_messages f004
93.3%
Passed
Tokens
187
Input
65
Total output
68
Reasoning within output
commit_messages f005
87.7%
Passed
Tokens
175
Input
89
Total output
84
Reasoning within output
commit_messages f006
92%
Passed
Tokens
210
Input
233
Total output
194
Reasoning within output
commit_messages f007
86%
Passed
Tokens
272
Input
251
Total output
244
Reasoning within output
commit_messages f008
92.7%
Passed
Tokens
158
Input
195
Total output
161
Reasoning within output
commit_messages f009
91.7%
Passed
Tokens
211
Input
322
Total output
285
Reasoning within output
commit_messages f010
91.7%
Passed
Tokens
345
Input
59
Total output
50
Reasoning within output
commit_messages f011
57.7%
Passed
Tokens
229
Input
892
Total output
881
Reasoning within output
commit_messages f012
91%
Passed
Tokens
212
Input
261
Total output
189
Reasoning within output
commit_squash f001
100%
Passed
Tokens
221
Input
6,194
Total output
6,362
Reasoning within output
commit_squash f002
100%
Passed
Tokens
203
Input
254
Total output
244
Reasoning within output
commit_squash f003
100%
Passed
Tokens
202
Input
6,030
Total output
5,919
Reasoning within output
commit_squash f004
100%
Passed
Tokens
186
Input
2,096
Total output
2,083
Reasoning within output
commit_squash f005
100%
Passed
Tokens
197
Input
371
Total output
363
Reasoning within output
commit_squash f006
100%
Passed
Tokens
185
Input
161
Total output
154
Reasoning within output
commit_squash f007
100%
Passed
Tokens
193
Input
230
Total output
236
Reasoning within output
commit_squash f008
100%
Passed
Tokens
190
Input
172
Total output
159
Reasoning within output
commit_squash f009
100%
Passed
Tokens
178
Input
2,672
Total output
2,693
Reasoning within output
commit_squash f010
100%
Passed
Tokens
206
Input
245
Total output
229
Reasoning within output
commit_squash f011
100%
Passed
Tokens
216
Input
6,250
Total output
6,234
Reasoning within output
commit_squash f012
100%
Passed
Tokens
210
Input
10,350
Total output
10,139
Reasoning within output
git_bisect f001
100%
Passed
Tokens
260
Input
96
Total output
90
Reasoning within output
git_bisect f002
100%
Passed
Tokens
279
Input
267
Total output
262
Reasoning within output
git_bisect f003
100%
Passed
Tokens
272
Input
225
Total output
194
Reasoning within output
git_bisect f004
100%
Passed
Tokens
275
Input
189
Total output
185
Reasoning within output
git_bisect f005
100%
Passed
Tokens
266
Input
110
Total output
103
Reasoning within output
git_bisect f006
100%
Passed
Tokens
310
Input
306
Total output
300
Reasoning within output
git_bisect f007
100%
Passed
Tokens
279
Input
247
Total output
242
Reasoning within output
git_bisect f008
100%
Passed
Tokens
279
Input
160
Total output
155
Reasoning within output
git_bisect f009
100%
Passed
Tokens
262
Input
84
Total output
79
Reasoning within output
git_bisect f010
100%
Passed
Tokens
287
Input
145
Total output
139
Reasoning within output
git_bisect f011
100%
Passed
Tokens
268
Input
122
Total output
92
Reasoning within output
git_bisect f012
100%
Passed
Tokens
293
Input
73
Total output
69
Reasoning within output
git_clean f001
100%
Passed
Tokens
128
Input
70
Total output
68
Reasoning within output
git_clean f002
100%
Passed
Tokens
151
Input
239
Total output
234
Reasoning within output
git_clean f003
100%
Passed
Tokens
149
Input
111
Total output
106
Reasoning within output
git_clean f004
100%
Passed
Tokens
155
Input
185
Total output
177
Reasoning within output
git_clean f005
100%
Passed
Tokens
126
Input
1,568
Total output
1,623
Reasoning within output
git_clean f006
100%
Passed
Tokens
153
Input
149
Total output
144
Reasoning within output
git_clean f007
100%
Passed
Tokens
161
Input
4,235
Total output
4,198
Reasoning within output
git_clean f008
100%
Passed
Tokens
151
Input
77
Total output
72
Reasoning within output
git_clean f009
100%
Passed
Tokens
146
Input
9,734
Total output
9,837
Reasoning within output
git_clean f010
100%
Passed
Tokens
142
Input
138
Total output
131
Reasoning within output
git_clean f011
100%
Passed
Tokens
152
Input
686
Total output
683
Reasoning within output
git_clean f012
100%
Passed
Tokens
155
Input
301
Total output
288
Reasoning within output
git_grep f001
100%
Passed
Tokens
144
Input
47
Total output
43
Reasoning within output
git_grep f002
100%
Passed
Tokens
139
Input
74
Total output
75
Reasoning within output
git_grep f003
100%
Passed
Tokens
163
Input
33
Total output
34
Reasoning within output
git_grep f004
100%
Passed
Tokens
164
Input
143
Total output
137
Reasoning within output
git_grep f005
100%
Passed
Tokens
186
Input
84
Total output
82
Reasoning within output
git_grep f006
100%
Passed
Tokens
116
Input
193
Total output
207
Reasoning within output
git_grep f007
100%
Passed
Tokens
235
Input
4,376
Total output
4,052
Reasoning within output
git_grep f008
100%
Passed
Tokens
149
Input
60
Total output
58
Reasoning within output
git_grep f009
100%
Passed
Tokens
142
Input
54
Total output
49
Reasoning within output
git_grep f010
100%
Passed
Tokens
139
Input
133
Total output
131
Reasoning within output
git_grep f011
100%
Passed
Tokens
206
Input
177
Total output
169
Reasoning within output
git_grep f012
100%
Passed
Tokens
143
Input
40
Total output
31
Reasoning within output
git_log_format f001
100%
Passed
Tokens
797
Input
68
Total output
63
Reasoning within output
git_log_format f002
100%
Passed
Tokens
792
Input
141
Total output
158
Reasoning within output
git_log_format f003
100%
Passed
Tokens
654
Input
108
Total output
101
Reasoning within output
git_log_format f004
100%
Passed
Tokens
799
Input
48
Total output
46
Reasoning within output
git_log_format f005
100%
Passed
Tokens
652
Input
2,973
Total output
2,969
Reasoning within output
git_log_format f006
100%
Passed
Tokens
782
Input
124
Total output
94
Reasoning within output
git_log_format f007
100%
Passed
Tokens
800
Input
22
Total output
16
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,046
Input
36
Total output
32
Reasoning within output
git_log_format f009
100%
Passed
Tokens
652
Input
59
Total output
54
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,144
Input
37
Total output
34
Reasoning within output
git_log_format f011
100%
Passed
Tokens
437
Input
100
Total output
98
Reasoning within output
git_log_format f012
100%
Passed
Tokens
411
Input
73
Total output
71
Reasoning within output
git_show f001
100%
Passed
Tokens
259
Input
101
Total output
109
Reasoning within output
git_show f002
0%
Failed
Tokens
245
Input
2,044
Total output
2,096
Reasoning within output
git_show f003
100%
Passed
Tokens
663
Input
136
Total output
127
Reasoning within output
git_show f004
100%
Passed
Tokens
471
Input
75
Total output
63
Reasoning within output
git_show f005
100%
Passed
Tokens
248
Input
177
Total output
194
Reasoning within output
git_show f006
100%
Passed
Tokens
280
Input
54
Total output
54
Reasoning within output
git_show f007
100%
Passed
Tokens
241
Input
37
Total output
36
Reasoning within output
git_show f008
100%
Passed
Tokens
278
Input
95
Total output
63
Reasoning within output
git_show f009
100%
Passed
Tokens
351
Input
181
Total output
177
Reasoning within output
git_show f010
100%
Passed
Tokens
256
Input
103
Total output
100
Reasoning within output
git_show f011
100%
Passed
Tokens
275
Input
38
Total output
37
Reasoning within output
git_show f012
100%
Passed
Tokens
392
Input
63
Total output
63
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
176
Input
4,484
Total output
4,479
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
188
Input
1,259
Total output
1,250
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
158
Input
562
Total output
628
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
213
Input
1,335
Total output
1,309
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
215
Input
128
Total output
110
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
202
Input
273
Total output
240
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
222
Input
235
Total output
225
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
198
Input
169
Total output
162
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
183
Input
572
Total output
566
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
257
Input
569
Total output
542
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
234
Input
294
Total output
272
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
310
Input
12,215
Total output
12,632
Reasoning within output
rebase f001
100%
Passed
Tokens
175
Input
5,448
Total output
5,443
Reasoning within output
rebase f002
100%
Passed
Tokens
220
Input
168
Total output
144
Reasoning within output
rebase f003
100%
Passed
Tokens
181
Input
226
Total output
221
Reasoning within output
rebase f004
100%
Passed
Tokens
224
Input
10,145
Total output
10,122
Reasoning within output
rebase f005
100%
Passed
Tokens
219
Input
121
Total output
107
Reasoning within output
rebase f006
100%
Passed
Tokens
232
Input
594
Total output
532
Reasoning within output
rebase f007
100%
Passed
Tokens
224
Input
316
Total output
306
Reasoning within output
rebase f008
100%
Passed
Tokens
209
Input
587
Total output
623
Reasoning within output
rebase f009
100%
Passed
Tokens
193
Input
319
Total output
313
Reasoning within output
rebase f010
100%
Passed
Tokens
282
Input
1,519
Total output
1,598
Reasoning within output
rebase f011
100%
Passed
Tokens
230
Input
180
Total output
140
Reasoning within output
rebase f012
0%
Failed
Tokens
339
Input
345
Total output
311
Reasoning within output
reflog f001
100%
Passed
Tokens
280
Input
255
Total output
233
Reasoning within output
reflog f002
100%
Passed
Tokens
272
Input
220
Total output
117
Reasoning within output
reflog f003
100%
Passed
Tokens
255
Input
385
Total output
285
Reasoning within output
reflog f004
100%
Passed
Tokens
355
Input
6,854
Total output
6,389
Reasoning within output
reflog f005
100%
Passed
Tokens
417
Input
2,216
Total output
1,892
Reasoning within output
reflog f006
100%
Passed
Tokens
298
Input
2,458
Total output
2,101
Reasoning within output
reflog f007
100%
Passed
Tokens
330
Input
1,300
Total output
1,236
Reasoning within output
reflog f008
100%
Passed
Tokens
382
Input
3,614
Total output
3,503
Reasoning within output
reflog f009
100%
Passed
Tokens
372
Input
4,259
Total output
4,126
Reasoning within output
reflog f010
100%
Passed
Tokens
303
Input
972
Total output
696
Reasoning within output
reflog f011
100%
Passed
Tokens
346
Input
4,970
Total output
4,674
Reasoning within output
reflog f012
100%
Passed
Tokens
365
Input
7,155
Total output
6,885
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
221
Input
108
Total output
103
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
364
Input
292
Total output
227
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
209
Input
93
Total output
72
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
189
Input
140
Total output
92
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
216
Input
186
Total output
164
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
246
Input
163
Total output
138
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
277
Input
103
Total output
89
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
242
Input
703
Total output
650
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
277
Input
312
Total output
275
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
210
Input
284
Total output
226
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
199
Input
2,124
Total output
2,067
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
219
Input
159
Total output
150
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
119
Input
74
Total output
61
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
171
Input
158
Total output
162
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
174
Input
601
Total output
608
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
169
Input
97
Total output
102
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
126
Input
173
Total output
147
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
158
Input
1,351
Total output
1,421
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
140
Input
168
Total output
151
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
168
Input
2,401
Total output
2,394
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
174
Input
357
Total output
352
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
171
Input
111
Total output
120
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
169
Input
70
Total output
67
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
125
Input
65
Total output
56
Reasoning within output
tag_management f001
100%
Passed
Tokens
134
Input
39
Total output
30
Reasoning within output
tag_management f002
100%
Passed
Tokens
131
Input
90
Total output
66
Reasoning within output
tag_management f003
100%
Passed
Tokens
136
Input
48
Total output
33
Reasoning within output
tag_management f004
100%
Passed
Tokens
141
Input
152
Total output
150
Reasoning within output
tag_management f005
100%
Passed
Tokens
153
Input
43
Total output
34
Reasoning within output
tag_management f006
100%
Passed
Tokens
140
Input
86
Total output
64
Reasoning within output
tag_management f007
100%
Passed
Tokens
137
Input
218
Total output
167
Reasoning within output
tag_management f008
100%
Passed
Tokens
156
Input
8,133
Total output
8,110
Reasoning within output
tag_management f009
100%
Passed
Tokens
158
Input
242
Total output
199
Reasoning within output
tag_management f010
100%
Passed
Tokens
124
Input
41
Total output
33
Reasoning within output
tag_management f011
100%
Passed
Tokens
136
Input
262
Total output
256
Reasoning within output
tag_management f012
100%
Passed
Tokens
157
Input
1,754
Total output
1,495
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
205
Input
177
Total output
178
Reasoning within output
worktree_usage f002
0%
Failed
Tokens
209
Input
2,355
Total output
2,330
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
272
Input
1,894
Total output
1,915
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
270
Input
36
Total output
31
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
200
Input
138
Total output
124
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
215
Input
371
Total output
355
Reasoning within output
worktree_usage f007
0%
Failed
Tokens
212
Input
14,386
Total output
14,362
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
233
Input
14,603
Total output
14,551
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
309
Input
256
Total output
251
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
275
Input
265
Total output
252
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
263
Input
74
Total output
70
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
200
Input
80
Total output
63
Reasoning within output