Deepseek / deepseek-v4.1-flash
high
97.1%
198 / 204 fixtures · 1 run(s)
40,039 input / 115,150 total output / 111,333 reasoning within output tokens $0.07416989
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-3.4%
Text: 97.1% →
JSON: 93.6%
+1
Gained
JSON pass / text fail
−8
Lost
Text pass / JSON fail
190
Unchanged Pass
Both pass
5
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| branch_cleanup | 100% | 83.3% | -16.7% |
| merge_conflicts | 91.7% | 83.3% | -8.3% |
| blame_forensics | 100% | 91.7% | -8.3% |
| commit_squash | 100% | 91.7% | -8.3% |
| git_show | 91.7% | 100% | + 8.3% |
| reflog | 100% | 91.7% | -8.3% |
| stash_recovery | 100% | 91.7% | -8.3% |
| tag_management | 100% | 91.7% | -8.3% |
| cherry_pick | 83.3% | 83.3% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_clean | 100% | 100% | + 0% |
| git_grep | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| rebase | 91.7% | 91.7% | + 0% |
| submodule_usage | 100% | 100% | + 0% |
| worktree_usage | 91.7% | 91.7% | + 0% |
Changed Fixtures (9)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
243
Input
231
Total output
225
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
227
Input
802
Total output
796
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
251
Input
60
Total output
52
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
188
Input
155
Total output
168
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
264
Input
1,014
Total output
1,009
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
233
Input
866
Total output
861
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
212
Input
79
Total output
72
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
240
Input
249
Total output
243
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
201
Input
110
Total output
105
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
393
Input
102
Total output
109
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
230
Input
70
Total output
65
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
153
Input
282
Total output
277
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
129
Input
163
Total output
150
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
134
Input
246
Total output
230
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
117
Input
145
Total output
143
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
146
Input
263
Total output
255
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
127
Input
210
Total output
205
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
146
Input
219
Total output
210
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
127
Input
104
Total output
97
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
139
Input
268
Total output
256
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
104
Input
196
Total output
193
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
140
Input
198
Total output
172
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
94
Input
89
Total output
93
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
172
Input
201
Total output
171
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
119
Input
255
Total output
249
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
147
Input
225
Total output
215
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
114
Input
986
Total output
980
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
172
Input
1,434
Total output
1,413
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
173
Input
160
Total output
142
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
161
Input
217
Total output
196
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
155
Input
94
Total output
83
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
149
Input
60
Total output
52
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
134
Input
60
Total output
53
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
237
Input
294
Total output
268
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
187
Input
133
Total output
110
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
290
Input
3,295
Total output
3,253
Reasoning within output
commit_messages f001
79%
Passed
Tokens
126
Input
296
Total output
287
Reasoning within output
commit_messages f002
85%
Passed
Tokens
222
Input
224
Total output
214
Reasoning within output
commit_messages f003
92.5%
Passed
Tokens
107
Input
110
Total output
100
Reasoning within output
commit_messages f004
92.5%
Passed
Tokens
134
Input
47
Total output
42
Reasoning within output
commit_messages f005
92.5%
Passed
Tokens
122
Input
95
Total output
89
Reasoning within output
commit_messages f006
90%
Passed
Tokens
157
Input
243
Total output
190
Reasoning within output
commit_messages f007
91.5%
Passed
Tokens
206
Input
273
Total output
264
Reasoning within output
commit_messages f008
91.5%
Passed
Tokens
92
Input
125
Total output
120
Reasoning within output
commit_messages f009
86.5%
Passed
Tokens
145
Input
241
Total output
232
Reasoning within output
commit_messages f010
92.5%
Passed
Tokens
292
Input
386
Total output
377
Reasoning within output
commit_messages f011
87.5%
Passed
Tokens
163
Input
244
Total output
234
Reasoning within output
commit_messages f012
96%
Passed
Tokens
146
Input
239
Total output
161
Reasoning within output
commit_squash f001
100%
Passed
Tokens
162
Input
1,628
Total output
1,684
Reasoning within output
commit_squash f002
100%
Passed
Tokens
139
Input
174
Total output
163
Reasoning within output
commit_squash f003
100%
Passed
Tokens
149
Input
2,195
Total output
2,181
Reasoning within output
commit_squash f004
100%
Passed
Tokens
136
Input
745
Total output
732
Reasoning within output
commit_squash f005
100%
Passed
Tokens
129
Input
2,848
Total output
2,839
Reasoning within output
commit_squash f006
100%
Passed
Tokens
119
Input
164
Total output
150
Reasoning within output
commit_squash f007
100%
Passed
Tokens
122
Input
167
Total output
153
Reasoning within output
commit_squash f008
100%
Passed
Tokens
137
Input
1,118
Total output
1,104
Reasoning within output
commit_squash f009
100%
Passed
Tokens
127
Input
127
Total output
114
Reasoning within output
commit_squash f010
100%
Passed
Tokens
141
Input
207
Total output
179
Reasoning within output
commit_squash f011
100%
Passed
Tokens
151
Input
270
Total output
253
Reasoning within output
commit_squash f012
100%
Passed
Tokens
148
Input
1,299
Total output
1,277
Reasoning within output
git_bisect f001
100%
Passed
Tokens
190
Input
69
Total output
63
Reasoning within output
git_bisect f002
100%
Passed
Tokens
217
Input
184
Total output
177
Reasoning within output
git_bisect f003
100%
Passed
Tokens
207
Input
107
Total output
102
Reasoning within output
git_bisect f004
100%
Passed
Tokens
217
Input
171
Total output
164
Reasoning within output
git_bisect f005
100%
Passed
Tokens
211
Input
110
Total output
103
Reasoning within output
git_bisect f006
100%
Passed
Tokens
236
Input
103
Total output
98
Reasoning within output
git_bisect f007
100%
Passed
Tokens
215
Input
79
Total output
81
Reasoning within output
git_bisect f008
100%
Passed
Tokens
213
Input
58
Total output
49
Reasoning within output
git_bisect f009
100%
Passed
Tokens
211
Input
94
Total output
87
Reasoning within output
git_bisect f010
100%
Passed
Tokens
219
Input
132
Total output
124
Reasoning within output
git_bisect f011
100%
Passed
Tokens
219
Input
105
Total output
87
Reasoning within output
git_bisect f012
100%
Passed
Tokens
244
Input
161
Total output
154
Reasoning within output
git_clean f001
100%
Passed
Tokens
75
Input
139
Total output
129
Reasoning within output
git_clean f002
100%
Passed
Tokens
85
Input
101
Total output
95
Reasoning within output
git_clean f003
100%
Passed
Tokens
83
Input
113
Total output
107
Reasoning within output
git_clean f004
100%
Passed
Tokens
83
Input
162
Total output
155
Reasoning within output
git_clean f005
100%
Passed
Tokens
73
Input
930
Total output
924
Reasoning within output
git_clean f006
100%
Passed
Tokens
100
Input
643
Total output
636
Reasoning within output
git_clean f007
100%
Passed
Tokens
95
Input
832
Total output
821
Reasoning within output
git_clean f008
100%
Passed
Tokens
98
Input
141
Total output
135
Reasoning within output
git_clean f009
100%
Passed
Tokens
93
Input
2,478
Total output
2,469
Reasoning within output
git_clean f010
100%
Passed
Tokens
89
Input
140
Total output
135
Reasoning within output
git_clean f011
100%
Passed
Tokens
86
Input
144
Total output
148
Reasoning within output
git_clean f012
100%
Passed
Tokens
89
Input
237
Total output
228
Reasoning within output
git_grep f001
100%
Passed
Tokens
78
Input
106
Total output
101
Reasoning within output
git_grep f002
100%
Passed
Tokens
87
Input
35
Total output
32
Reasoning within output
git_grep f003
100%
Passed
Tokens
110
Input
54
Total output
51
Reasoning within output
git_grep f004
100%
Passed
Tokens
98
Input
139
Total output
132
Reasoning within output
git_grep f005
100%
Passed
Tokens
133
Input
42
Total output
39
Reasoning within output
git_grep f006
100%
Passed
Tokens
63
Input
161
Total output
158
Reasoning within output
git_grep f007
100%
Passed
Tokens
182
Input
209
Total output
206
Reasoning within output
git_grep f008
100%
Passed
Tokens
83
Input
47
Total output
44
Reasoning within output
git_grep f009
100%
Passed
Tokens
76
Input
60
Total output
55
Reasoning within output
git_grep f010
100%
Passed
Tokens
86
Input
123
Total output
120
Reasoning within output
git_grep f011
100%
Passed
Tokens
140
Input
48
Total output
45
Reasoning within output
git_grep f012
100%
Passed
Tokens
90
Input
61
Total output
50
Reasoning within output
git_log_format f001
100%
Passed
Tokens
734
Input
54
Total output
51
Reasoning within output
git_log_format f002
100%
Passed
Tokens
745
Input
94
Total output
85
Reasoning within output
git_log_format f003
100%
Passed
Tokens
605
Input
66
Total output
56
Reasoning within output
git_log_format f004
100%
Passed
Tokens
723
Input
53
Total output
50
Reasoning within output
git_log_format f005
100%
Passed
Tokens
599
Input
394
Total output
387
Reasoning within output
git_log_format f006
100%
Passed
Tokens
729
Input
69
Total output
67
Reasoning within output
git_log_format f007
100%
Passed
Tokens
752
Input
39
Total output
33
Reasoning within output
git_log_format f008
100%
Passed
Tokens
972
Input
31
Total output
29
Reasoning within output
git_log_format f009
100%
Passed
Tokens
604
Input
53
Total output
50
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,107
Input
44
Total output
41
Reasoning within output
git_log_format f011
100%
Passed
Tokens
387
Input
71
Total output
67
Reasoning within output
git_log_format f012
100%
Passed
Tokens
359
Input
54
Total output
51
Reasoning within output
git_show f001
100%
Passed
Tokens
196
Input
141
Total output
134
Reasoning within output
git_show f002
0%
Failed
Tokens
197
Input
2,181
Total output
2,177
Reasoning within output
git_show f003
100%
Passed
Tokens
595
Input
100
Total output
93
Reasoning within output
git_show f004
100%
Passed
Tokens
414
Input
76
Total output
68
Reasoning within output
git_show f005
100%
Passed
Tokens
199
Input
121
Total output
117
Reasoning within output
git_show f006
100%
Passed
Tokens
209
Input
45
Total output
42
Reasoning within output
git_show f007
100%
Passed
Tokens
188
Input
76
Total output
70
Reasoning within output
git_show f008
100%
Passed
Tokens
208
Input
80
Total output
52
Reasoning within output
git_show f009
100%
Passed
Tokens
286
Input
111
Total output
108
Reasoning within output
git_show f010
100%
Passed
Tokens
192
Input
113
Total output
111
Reasoning within output
git_show f011
100%
Passed
Tokens
225
Input
22
Total output
18
Reasoning within output
git_show f012
100%
Passed
Tokens
319
Input
75
Total output
72
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
110
Input
987
Total output
981
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
135
Input
531
Total output
521
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
105
Input
1,464
Total output
1,458
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
160
Input
476
Total output
452
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
162
Input
164
Total output
146
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
149
Input
423
Total output
402
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
156
Input
129
Total output
118
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
132
Input
97
Total output
89
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
130
Input
137
Total output
130
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
204
Input
769
Total output
816
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
168
Input
166
Total output
143
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
257
Input
4,861
Total output
4,819
Reasoning within output
rebase f001
100%
Passed
Tokens
118
Input
1,416
Total output
1,410
Reasoning within output
rebase f002
100%
Passed
Tokens
154
Input
192
Total output
182
Reasoning within output
rebase f003
100%
Passed
Tokens
128
Input
135
Total output
130
Reasoning within output
rebase f004
100%
Passed
Tokens
170
Input
9,399
Total output
9,375
Reasoning within output
rebase f005
100%
Passed
Tokens
166
Input
443
Total output
502
Reasoning within output
rebase f006
100%
Passed
Tokens
160
Input
713
Total output
645
Reasoning within output
rebase f007
100%
Passed
Tokens
157
Input
617
Total output
608
Reasoning within output
rebase f008
100%
Passed
Tokens
145
Input
327
Total output
319
Reasoning within output
rebase f009
100%
Passed
Tokens
127
Input
205
Total output
214
Reasoning within output
rebase f010
100%
Passed
Tokens
231
Input
461
Total output
482
Reasoning within output
rebase f011
100%
Passed
Tokens
179
Input
501
Total output
478
Reasoning within output
rebase f012
0%
Failed
Tokens
292
Input
2,739
Total output
2,697
Reasoning within output
reflog f001
100%
Passed
Tokens
226
Input
160
Total output
138
Reasoning within output
reflog f002
100%
Passed
Tokens
211
Input
208
Total output
141
Reasoning within output
reflog f003
100%
Passed
Tokens
198
Input
262
Total output
129
Reasoning within output
reflog f004
100%
Passed
Tokens
291
Input
6,072
Total output
5,896
Reasoning within output
reflog f005
100%
Passed
Tokens
343
Input
2,449
Total output
2,311
Reasoning within output
reflog f006
100%
Passed
Tokens
249
Input
1,621
Total output
1,289
Reasoning within output
reflog f007
100%
Passed
Tokens
262
Input
456
Total output
371
Reasoning within output
reflog f008
100%
Passed
Tokens
328
Input
2,121
Total output
1,963
Reasoning within output
reflog f009
100%
Passed
Tokens
282
Input
752
Total output
671
Reasoning within output
reflog f010
100%
Passed
Tokens
252
Input
2,013
Total output
1,842
Reasoning within output
reflog f011
100%
Passed
Tokens
279
Input
3,674
Total output
3,386
Reasoning within output
reflog f012
100%
Passed
Tokens
299
Input
4,758
Total output
4,527
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
147
Input
66
Total output
66
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
292
Input
154
Total output
142
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
137
Input
71
Total output
63
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
136
Input
144
Total output
137
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
147
Input
157
Total output
150
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
193
Input
70
Total output
63
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
218
Input
108
Total output
88
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
189
Input
116
Total output
109
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
224
Input
211
Total output
173
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
144
Input
61
Total output
55
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
135
Input
151
Total output
129
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
153
Input
120
Total output
113
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
66
Input
77
Total output
70
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
120
Input
381
Total output
370
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
119
Input
3,334
Total output
3,309
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
108
Input
249
Total output
243
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
73
Input
389
Total output
355
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
106
Input
1,151
Total output
1,145
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
74
Input
261
Total output
240
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
112
Input
7,379
Total output
7,372
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
105
Input
168
Total output
162
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
118
Input
211
Total output
202
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
117
Input
137
Total output
131
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
72
Input
115
Total output
101
Reasoning within output
tag_management f001
100%
Passed
Tokens
80
Input
43
Total output
38
Reasoning within output
tag_management f002
100%
Passed
Tokens
76
Input
85
Total output
65
Reasoning within output
tag_management f003
100%
Passed
Tokens
82
Input
87
Total output
76
Reasoning within output
tag_management f004
100%
Passed
Tokens
87
Input
124
Total output
106
Reasoning within output
tag_management f005
100%
Passed
Tokens
99
Input
125
Total output
110
Reasoning within output
tag_management f006
100%
Passed
Tokens
83
Input
188
Total output
166
Reasoning within output
tag_management f007
100%
Passed
Tokens
86
Input
133
Total output
89
Reasoning within output
tag_management f008
100%
Passed
Tokens
90
Input
2,886
Total output
2,861
Reasoning within output
tag_management f009
100%
Passed
Tokens
92
Input
124
Total output
105
Reasoning within output
tag_management f010
100%
Passed
Tokens
69
Input
59
Total output
50
Reasoning within output
tag_management f011
100%
Passed
Tokens
68
Input
48
Total output
48
Reasoning within output
tag_management f012
100%
Passed
Tokens
104
Input
126
Total output
116
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
153
Input
235
Total output
224
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
158
Input
422
Total output
398
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
215
Input
153
Total output
143
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
213
Input
63
Total output
62
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
140
Input
78
Total output
63
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
144
Input
190
Total output
173
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
153
Input
584
Total output
563
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
168
Input
2,029
Total output
1,976
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
242
Input
146
Total output
161
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
223
Input
154
Total output
137
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
217
Input
108
Total output
106
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
139
Input
100
Total output
85
Reasoning within output