Deepseek / deepseek-v4-flash-0731
xhigh
95.1%
194 / 204 fixtures · 1 run(s)
43,586 input / 131,277 total output / 125,642 reasoning within output tokens $0.04385501
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-7.4%
Text: 95.1% →
JSON: 87.8%
+2
Gained
JSON pass / text fail
−17
Lost
Text pass / JSON fail
177
Unchanged Pass
Both pass
8
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| commit_squash | 91.7% | 41.7% | -50% |
| branch_cleanup | 100% | 75% | -25% |
| git_bisect | 100% | 83.3% | -16.7% |
| merge_conflicts | 91.7% | 75% | -16.7% |
| tag_management | 100% | 83.3% | -16.7% |
| git_show | 91.7% | 83.3% | -8.3% |
| rebase | 83.3% | 91.7% | + 8.3% |
| cherry_pick | 83.3% | 75% | -8.3% |
| git_clean | 91.7% | 100% | + 8.3% |
| blame_forensics | 100% | 100% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| git_grep | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 91.7% | 91.7% | + 0% |
| worktree_usage | 91.7% | 91.7% | + 0% |
Changed Fixtures (19)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
300
Input
928
Total output
1,026
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
283
Input
284
Total output
279
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
229
Input
333
Total output
283
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
244
Input
131
Total output
125
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
302
Input
3,147
Total output
3,143
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
277
Input
588
Total output
584
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
267
Input
90
Total output
84
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
288
Input
370
Total output
373
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
178
Input
164
Total output
174
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
375
Input
65
Total output
82
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
201
Input
124
Total output
119
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
217
Input
126
Total output
122
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
104
Input
156
Total output
196
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
185
Input
714
Total output
708
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
169
Input
117
Total output
115
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
123
Input
70
Total output
97
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
98
Input
70
Total output
89
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
198
Input
181
Total output
173
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
101
Input
54
Total output
78
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
119
Input
259
Total output
232
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
77
Input
152
Total output
217
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
190
Input
132
Total output
122
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
67
Input
177
Total output
179
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
224
Input
213
Total output
182
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
94
Input
891
Total output
1,024
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
200
Input
7,066
Total output
6,453
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
168
Input
1,524
Total output
1,519
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
224
Input
3,849
Total output
3,829
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
150
Input
271
Total output
286
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
137
Input
345
Total output
302
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
209
Input
106
Total output
96
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
123
Input
249
Total output
266
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
186
Input
80
Total output
74
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
288
Input
667
Total output
642
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
161
Input
130
Total output
89
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
343
Input
4,270
Total output
4,416
Reasoning within output
commit_messages f001
90%
Passed
Tokens
185
Input
93
Total output
82
Reasoning within output
commit_messages f002
87.7%
Passed
Tokens
196
Input
125
Total output
112
Reasoning within output
commit_messages f003
63.3%
Passed
Tokens
160
Input
257
Total output
181
Reasoning within output
commit_messages f004
91.7%
Passed
Tokens
108
Input
145
Total output
153
Reasoning within output
commit_messages f005
89.3%
Passed
Tokens
96
Input
196
Total output
181
Reasoning within output
commit_messages f006
91.7%
Passed
Tokens
131
Input
583
Total output
576
Reasoning within output
commit_messages f007
90%
Passed
Tokens
180
Input
308
Total output
261
Reasoning within output
commit_messages f008
93.3%
Passed
Tokens
66
Input
275
Total output
269
Reasoning within output
commit_messages f009
83.3%
Passed
Tokens
198
Input
193
Total output
187
Reasoning within output
commit_messages f010
91%
Passed
Tokens
266
Input
356
Total output
290
Reasoning within output
commit_messages f011
76%
Passed
Tokens
137
Input
1,094
Total output
695
Reasoning within output
commit_messages f012
91%
Passed
Tokens
199
Input
81
Total output
78
Reasoning within output
commit_squash f001
100%
Passed
Tokens
211
Input
3,318
Total output
3,341
Reasoning within output
commit_squash f002
100%
Passed
Tokens
191
Input
214
Total output
219
Reasoning within output
commit_squash f003
100%
Passed
Tokens
203
Input
7,758
Total output
7,745
Reasoning within output
commit_squash f004
100%
Passed
Tokens
189
Input
505
Total output
493
Reasoning within output
commit_squash f005
100%
Passed
Tokens
189
Input
119
Total output
133
Reasoning within output
commit_squash f006
0%
Failed
Tokens
93
Input
303
Total output
283
Reasoning within output
commit_squash f007
100%
Passed
Tokens
96
Input
524
Total output
516
Reasoning within output
commit_squash f008
100%
Passed
Tokens
194
Input
138
Total output
122
Reasoning within output
commit_squash f009
100%
Passed
Tokens
99
Input
283
Total output
250
Reasoning within output
commit_squash f010
100%
Passed
Tokens
194
Input
238
Total output
222
Reasoning within output
commit_squash f011
100%
Passed
Tokens
123
Input
46
Total output
29
Reasoning within output
commit_squash f012
100%
Passed
Tokens
202
Input
190
Total output
169
Reasoning within output
git_bisect f001
100%
Passed
Tokens
243
Input
78
Total output
73
Reasoning within output
git_bisect f002
100%
Passed
Tokens
266
Input
159
Total output
153
Reasoning within output
git_bisect f003
100%
Passed
Tokens
268
Input
251
Total output
246
Reasoning within output
git_bisect f004
100%
Passed
Tokens
266
Input
125
Total output
121
Reasoning within output
git_bisect f005
100%
Passed
Tokens
268
Input
94
Total output
89
Reasoning within output
git_bisect f006
100%
Passed
Tokens
208
Input
159
Total output
146
Reasoning within output
git_bisect f007
100%
Passed
Tokens
187
Input
294
Total output
264
Reasoning within output
git_bisect f008
100%
Passed
Tokens
185
Input
260
Total output
234
Reasoning within output
git_bisect f009
100%
Passed
Tokens
187
Input
205
Total output
200
Reasoning within output
git_bisect f010
100%
Passed
Tokens
258
Input
106
Total output
106
Reasoning within output
git_bisect f011
100%
Passed
Tokens
268
Input
153
Total output
147
Reasoning within output
git_bisect f012
100%
Passed
Tokens
297
Input
207
Total output
202
Reasoning within output
git_clean f001
100%
Passed
Tokens
128
Input
102
Total output
98
Reasoning within output
git_clean f002
100%
Passed
Tokens
138
Input
67
Total output
62
Reasoning within output
git_clean f003
100%
Passed
Tokens
57
Input
204
Total output
200
Reasoning within output
git_clean f004
100%
Passed
Tokens
136
Input
141
Total output
147
Reasoning within output
git_clean f005
100%
Passed
Tokens
47
Input
374
Total output
403
Reasoning within output
git_clean f006
100%
Passed
Tokens
153
Input
2,377
Total output
2,370
Reasoning within output
git_clean f007
100%
Passed
Tokens
69
Input
389
Total output
380
Reasoning within output
git_clean f008
100%
Passed
Tokens
72
Input
162
Total output
161
Reasoning within output
git_clean f009
100%
Passed
Tokens
146
Input
10,301
Total output
10,293
Reasoning within output
git_clean f010
100%
Passed
Tokens
142
Input
94
Total output
89
Reasoning within output
git_clean f011
60%
Failed
Tokens
60
Input
85
Total output
86
Reasoning within output
git_clean f012
100%
Passed
Tokens
63
Input
324
Total output
307
Reasoning within output
git_grep f001
100%
Passed
Tokens
52
Input
47
Total output
45
Reasoning within output
git_grep f002
100%
Passed
Tokens
144
Input
44
Total output
39
Reasoning within output
git_grep f003
100%
Passed
Tokens
163
Input
36
Total output
34
Reasoning within output
git_grep f004
100%
Passed
Tokens
72
Input
27
Total output
22
Reasoning within output
git_grep f005
100%
Passed
Tokens
107
Input
166
Total output
159
Reasoning within output
git_grep f006
100%
Passed
Tokens
37
Input
248
Total output
270
Reasoning within output
git_grep f007
100%
Passed
Tokens
235
Input
4,145
Total output
3,903
Reasoning within output
git_grep f008
100%
Passed
Tokens
57
Input
53
Total output
55
Reasoning within output
git_grep f009
100%
Passed
Tokens
50
Input
143
Total output
131
Reasoning within output
git_grep f010
100%
Passed
Tokens
60
Input
369
Total output
382
Reasoning within output
git_grep f011
100%
Passed
Tokens
193
Input
173
Total output
161
Reasoning within output
git_grep f012
100%
Passed
Tokens
64
Input
50
Total output
29
Reasoning within output
git_log_format f001
100%
Passed
Tokens
716
Input
99
Total output
87
Reasoning within output
git_log_format f002
100%
Passed
Tokens
699
Input
142
Total output
152
Reasoning within output
git_log_format f003
100%
Passed
Tokens
656
Input
47
Total output
37
Reasoning within output
git_log_format f004
100%
Passed
Tokens
796
Input
53
Total output
40
Reasoning within output
git_log_format f005
100%
Passed
Tokens
573
Input
83
Total output
67
Reasoning within output
git_log_format f006
100%
Passed
Tokens
703
Input
107
Total output
77
Reasoning within output
git_log_format f007
100%
Passed
Tokens
819
Input
38
Total output
31
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,030
Input
37
Total output
35
Reasoning within output
git_log_format f009
100%
Passed
Tokens
664
Input
43
Total output
42
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,152
Input
40
Total output
33
Reasoning within output
git_log_format f011
100%
Passed
Tokens
432
Input
44
Total output
41
Reasoning within output
git_log_format f012
100%
Passed
Tokens
405
Input
32
Total output
30
Reasoning within output
git_show f001
100%
Passed
Tokens
171
Input
53
Total output
44
Reasoning within output
git_show f002
0%
Failed
Tokens
165
Input
1,429
Total output
1,578
Reasoning within output
git_show f003
100%
Passed
Tokens
642
Input
58
Total output
48
Reasoning within output
git_show f004
100%
Passed
Tokens
465
Input
81
Total output
74
Reasoning within output
git_show f005
100%
Passed
Tokens
173
Input
110
Total output
112
Reasoning within output
git_show f006
100%
Passed
Tokens
265
Input
26
Total output
25
Reasoning within output
git_show f007
100%
Passed
Tokens
247
Input
193
Total output
191
Reasoning within output
git_show f008
100%
Passed
Tokens
258
Input
80
Total output
47
Reasoning within output
git_show f009
100%
Passed
Tokens
260
Input
166
Total output
233
Reasoning within output
git_show f010
100%
Passed
Tokens
171
Input
93
Total output
91
Reasoning within output
git_show f011
100%
Passed
Tokens
278
Input
67
Total output
64
Reasoning within output
git_show f012
100%
Passed
Tokens
372
Input
85
Total output
80
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
169
Input
735
Total output
771
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
109
Input
588
Total output
558
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
79
Input
500
Total output
551
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
219
Input
326
Total output
307
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
215
Input
243
Total output
226
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
202
Input
185
Total output
148
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
209
Input
181
Total output
180
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
106
Input
225
Total output
261
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
104
Input
199
Total output
214
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
257
Input
487
Total output
462
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
221
Input
170
Total output
148
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
231
Input
125
Total output
107
Reasoning within output
rebase f001
100%
Passed
Tokens
174
Input
3,273
Total output
3,268
Reasoning within output
rebase f002
100%
Passed
Tokens
208
Input
147
Total output
138
Reasoning within output
rebase f003
100%
Passed
Tokens
180
Input
168
Total output
186
Reasoning within output
rebase f004
0%
Failed
Tokens
150
Input
1,702
Total output
1,681
Reasoning within output
rebase f005
100%
Passed
Tokens
140
Input
202
Total output
188
Reasoning within output
rebase f006
100%
Passed
Tokens
213
Input
2,191
Total output
2,171
Reasoning within output
rebase f007
100%
Passed
Tokens
131
Input
202
Total output
195
Reasoning within output
rebase f008
100%
Passed
Tokens
198
Input
158
Total output
166
Reasoning within output
rebase f009
100%
Passed
Tokens
182
Input
1,009
Total output
1,046
Reasoning within output
rebase f010
100%
Passed
Tokens
284
Input
378
Total output
353
Reasoning within output
rebase f011
100%
Passed
Tokens
152
Input
160
Total output
108
Reasoning within output
rebase f012
0%
Failed
Tokens
351
Input
17,251
Total output
17,410
Reasoning within output
reflog f001
100%
Passed
Tokens
285
Input
115
Total output
72
Reasoning within output
reflog f002
100%
Passed
Tokens
276
Input
348
Total output
221
Reasoning within output
reflog f003
100%
Passed
Tokens
258
Input
183
Total output
89
Reasoning within output
reflog f004
100%
Passed
Tokens
264
Input
1,071
Total output
898
Reasoning within output
reflog f005
100%
Passed
Tokens
412
Input
1,488
Total output
1,107
Reasoning within output
reflog f006
100%
Passed
Tokens
215
Input
529
Total output
364
Reasoning within output
reflog f007
100%
Passed
Tokens
328
Input
673
Total output
530
Reasoning within output
reflog f008
100%
Passed
Tokens
385
Input
171
Total output
109
Reasoning within output
reflog f009
100%
Passed
Tokens
266
Input
1,045
Total output
856
Reasoning within output
reflog f010
100%
Passed
Tokens
233
Input
676
Total output
427
Reasoning within output
reflog f011
100%
Passed
Tokens
352
Input
1,718
Total output
1,409
Reasoning within output
reflog f012
100%
Passed
Tokens
276
Input
2,039
Total output
1,591
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
122
Input
175
Total output
180
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
351
Input
249
Total output
190
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
111
Input
134
Total output
138
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
110
Input
210
Total output
191
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
198
Input
354
Total output
317
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
167
Input
90
Total output
92
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
194
Input
206
Total output
177
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
242
Input
176
Total output
132
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
277
Input
247
Total output
198
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
118
Input
251
Total output
250
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
107
Input
360
Total output
323
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
127
Input
511
Total output
374
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
119
Input
83
Total output
71
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
89
Input
442
Total output
449
Reasoning within output
submodule_usage f003
75%
Failed
Tokens
96
Input
767
Total output
728
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
161
Input
57
Total output
58
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
126
Input
325
Total output
312
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
76
Input
356
Total output
398
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
127
Input
196
Total output
191
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
162
Input
3,494
Total output
3,487
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
163
Input
110
Total output
105
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
169
Input
229
Total output
257
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
94
Input
61
Total output
59
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
46
Input
144
Total output
131
Reasoning within output
tag_management f001
100%
Passed
Tokens
54
Input
60
Total output
52
Reasoning within output
tag_management f002
100%
Passed
Tokens
51
Input
83
Total output
59
Reasoning within output
tag_management f003
100%
Passed
Tokens
61
Input
84
Total output
74
Reasoning within output
tag_management f004
100%
Passed
Tokens
138
Input
50
Total output
50
Reasoning within output
tag_management f005
100%
Passed
Tokens
71
Input
38
Total output
32
Reasoning within output
tag_management f006
100%
Passed
Tokens
136
Input
93
Total output
68
Reasoning within output
tag_management f007
100%
Passed
Tokens
59
Input
86
Total output
73
Reasoning within output
tag_management f008
100%
Passed
Tokens
143
Input
6,192
Total output
5,044
Reasoning within output
tag_management f009
100%
Passed
Tokens
67
Input
82
Total output
59
Reasoning within output
tag_management f010
100%
Passed
Tokens
44
Input
83
Total output
71
Reasoning within output
tag_management f011
100%
Passed
Tokens
42
Input
99
Total output
92
Reasoning within output
tag_management f012
100%
Passed
Tokens
160
Input
705
Total output
695
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
122
Input
194
Total output
194
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
216
Input
1,060
Total output
1,037
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
270
Input
142
Total output
133
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
266
Input
57
Total output
59
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
197
Input
61
Total output
48
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
196
Input
159
Total output
143
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
124
Input
288
Total output
273
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
230
Input
263
Total output
206
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
221
Input
138
Total output
143
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
274
Input
122
Total output
107
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
276
Input
111
Total output
108
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
119
Input
86
Total output
67
Reasoning within output