Google / gemini-3.8-flash
medium
96.6%
197 / 204 fixtures · 1 run(s)
40,357 input / 96,390 total output / 92,701 reasoning within output tokens $0.39173025
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-2.4%
Text: 96.6% →
JSON: 94.1%
+1
Gained
JSON pass / text fail
−6
Lost
Text pass / JSON fail
191
Unchanged Pass
Both pass
6
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| branch_cleanup | 100% | 75% | -25% |
| rebase | 91.7% | 75% | -16.7% |
| reflog | 91.7% | 100% | + 8.3% |
| worktree_usage | 100% | 91.7% | -8.3% |
| blame_forensics | 91.7% | 91.7% | + 0% |
| cherry_pick | 83.3% | 83.3% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| commit_squash | 91.7% | 91.7% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_clean | 100% | 100% | + 0% |
| git_grep | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 100% | 100% | + 0% |
| merge_conflicts | 91.7% | 91.7% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
Changed Fixtures (7)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
260
Input
521
Total output
517
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
255
Input
220
Total output
216
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
297
Input
170
Total output
164
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
210
Input
111
Total output
106
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
267
Input
1,783
Total output
1,778
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
239
Input
196
Total output
193
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
221
Input
156
Total output
152
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
263
Input
257
Total output
254
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
210
Input
151
Total output
148
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
460
Input
163
Total output
160
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
262
Input
162
Total output
159
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
154
Input
198
Total output
194
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
102
Input
132
Total output
128
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
120
Input
184
Total output
177
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
92
Input
158
Total output
157
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
132
Input
106
Total output
99
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
104
Input
219
Total output
215
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
125
Input
129
Total output
119
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
104
Input
149
Total output
142
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
115
Input
142
Total output
133
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
78
Input
133
Total output
132
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
111
Input
213
Total output
208
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
65
Input
190
Total output
189
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
155
Input
145
Total output
133
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
94
Input
201
Total output
197
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
113
Input
423
Total output
416
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
86
Input
649
Total output
646
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
166
Input
1,030
Total output
1,006
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
154
Input
363
Total output
343
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
140
Input
501
Total output
480
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
133
Input
246
Total output
236
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
124
Input
188
Total output
182
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
106
Input
87
Total output
82
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
229
Input
428
Total output
398
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
165
Input
370
Total output
347
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
284
Input
1,790
Total output
1,743
Reasoning within output
commit_messages f001
84%
Passed
Tokens
112
Input
435
Total output
427
Reasoning within output
commit_messages f002
95%
Passed
Tokens
245
Input
362
Total output
354
Reasoning within output
commit_messages f003
94%
Passed
Tokens
83
Input
258
Total output
248
Reasoning within output
commit_messages f004
91.5%
Passed
Tokens
118
Input
227
Total output
223
Reasoning within output
commit_messages f005
95%
Passed
Tokens
109
Input
256
Total output
250
Reasoning within output
commit_messages f006
92%
Passed
Tokens
151
Input
261
Total output
255
Reasoning within output
commit_messages f007
92.5%
Passed
Tokens
209
Input
230
Total output
224
Reasoning within output
commit_messages f008
90%
Passed
Tokens
76
Input
295
Total output
290
Reasoning within output
commit_messages f009
89%
Passed
Tokens
133
Input
445
Total output
439
Reasoning within output
commit_messages f010
92.5%
Passed
Tokens
332
Input
314
Total output
307
Reasoning within output
commit_messages f011
84%
Passed
Tokens
153
Input
750
Total output
740
Reasoning within output
commit_messages f012
92.5%
Passed
Tokens
130
Input
203
Total output
198
Reasoning within output
commit_squash f001
100%
Passed
Tokens
134
Input
3,418
Total output
3,405
Reasoning within output
commit_squash f002
100%
Passed
Tokens
114
Input
342
Total output
333
Reasoning within output
commit_squash f003
0%
Failed
Tokens
0
Input
0
Total output
0
Reasoning within output
commit_squash f004
100%
Passed
Tokens
113
Input
598
Total output
587
Reasoning within output
commit_squash f005
100%
Passed
Tokens
110
Input
3,802
Total output
3,795
Reasoning within output
commit_squash f006
100%
Passed
Tokens
95
Input
277
Total output
266
Reasoning within output
commit_squash f007
100%
Passed
Tokens
97
Input
374
Total output
362
Reasoning within output
commit_squash f008
100%
Passed
Tokens
110
Input
433
Total output
421
Reasoning within output
commit_squash f009
100%
Passed
Tokens
101
Input
444
Total output
433
Reasoning within output
commit_squash f010
100%
Passed
Tokens
119
Input
326
Total output
311
Reasoning within output
commit_squash f011
100%
Passed
Tokens
120
Input
1,192
Total output
1,177
Reasoning within output
commit_squash f012
100%
Passed
Tokens
123
Input
410
Total output
390
Reasoning within output
git_bisect f001
100%
Passed
Tokens
185
Input
93
Total output
86
Reasoning within output
git_bisect f002
100%
Passed
Tokens
205
Input
118
Total output
114
Reasoning within output
git_bisect f003
100%
Passed
Tokens
209
Input
93
Total output
86
Reasoning within output
git_bisect f004
100%
Passed
Tokens
217
Input
137
Total output
130
Reasoning within output
git_bisect f005
100%
Passed
Tokens
213
Input
104
Total output
98
Reasoning within output
git_bisect f006
100%
Passed
Tokens
245
Input
133
Total output
126
Reasoning within output
git_bisect f007
100%
Passed
Tokens
205
Input
109
Total output
103
Reasoning within output
git_bisect f008
100%
Passed
Tokens
215
Input
79
Total output
72
Reasoning within output
git_bisect f009
100%
Passed
Tokens
205
Input
79
Total output
74
Reasoning within output
git_bisect f010
100%
Passed
Tokens
215
Input
137
Total output
130
Reasoning within output
git_bisect f011
100%
Passed
Tokens
213
Input
81
Total output
75
Reasoning within output
git_bisect f012
100%
Passed
Tokens
230
Input
90
Total output
86
Reasoning within output
git_clean f001
100%
Passed
Tokens
50
Input
209
Total output
205
Reasoning within output
git_clean f002
100%
Passed
Tokens
62
Input
224
Total output
220
Reasoning within output
git_clean f003
100%
Passed
Tokens
62
Input
224
Total output
220
Reasoning within output
git_clean f004
100%
Passed
Tokens
62
Input
411
Total output
406
Reasoning within output
git_clean f005
100%
Passed
Tokens
49
Input
326
Total output
322
Reasoning within output
git_clean f006
100%
Passed
Tokens
80
Input
334
Total output
328
Reasoning within output
git_clean f007
100%
Passed
Tokens
69
Input
253
Total output
244
Reasoning within output
git_clean f008
100%
Passed
Tokens
78
Input
231
Total output
227
Reasoning within output
git_clean f009
100%
Passed
Tokens
73
Input
2,607
Total output
2,600
Reasoning within output
git_clean f010
100%
Passed
Tokens
64
Input
337
Total output
333
Reasoning within output
git_clean f011
100%
Passed
Tokens
64
Input
508
Total output
503
Reasoning within output
git_clean f012
100%
Passed
Tokens
69
Input
270
Total output
263
Reasoning within output
git_grep f001
100%
Passed
Tokens
48
Input
144
Total output
139
Reasoning within output
git_grep f002
100%
Passed
Tokens
58
Input
190
Total output
189
Reasoning within output
git_grep f003
100%
Passed
Tokens
100
Input
182
Total output
181
Reasoning within output
git_grep f004
100%
Passed
Tokens
76
Input
231
Total output
226
Reasoning within output
git_grep f005
100%
Passed
Tokens
114
Input
241
Total output
240
Reasoning within output
git_grep f006
100%
Passed
Tokens
33
Input
212
Total output
211
Reasoning within output
git_grep f007
100%
Passed
Tokens
176
Input
981
Total output
979
Reasoning within output
git_grep f008
100%
Passed
Tokens
56
Input
99
Total output
98
Reasoning within output
git_grep f009
100%
Passed
Tokens
49
Input
127
Total output
124
Reasoning within output
git_grep f010
100%
Passed
Tokens
63
Input
92
Total output
91
Reasoning within output
git_grep f011
100%
Passed
Tokens
126
Input
229
Total output
228
Reasoning within output
git_grep f012
100%
Passed
Tokens
64
Input
219
Total output
206
Reasoning within output
git_log_format f001
100%
Passed
Tokens
953
Input
133
Total output
132
Reasoning within output
git_log_format f002
100%
Passed
Tokens
919
Input
180
Total output
173
Reasoning within output
git_log_format f003
100%
Passed
Tokens
745
Input
188
Total output
179
Reasoning within output
git_log_format f004
100%
Passed
Tokens
914
Input
170
Total output
169
Reasoning within output
git_log_format f005
100%
Passed
Tokens
746
Input
206
Total output
201
Reasoning within output
git_log_format f006
100%
Passed
Tokens
934
Input
235
Total output
234
Reasoning within output
git_log_format f007
100%
Passed
Tokens
934
Input
68
Total output
61
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,251
Input
132
Total output
131
Reasoning within output
git_log_format f009
100%
Passed
Tokens
750
Input
74
Total output
73
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,446
Input
90
Total output
89
Reasoning within output
git_log_format f011
100%
Passed
Tokens
442
Input
131
Total output
128
Reasoning within output
git_log_format f012
100%
Passed
Tokens
398
Input
101
Total output
100
Reasoning within output
git_show f001
100%
Passed
Tokens
195
Input
72
Total output
67
Reasoning within output
git_show f002
100%
Passed
Tokens
205
Input
429
Total output
426
Reasoning within output
git_show f003
100%
Passed
Tokens
731
Input
155
Total output
149
Reasoning within output
git_show f004
100%
Passed
Tokens
484
Input
94
Total output
87
Reasoning within output
git_show f005
100%
Passed
Tokens
206
Input
197
Total output
195
Reasoning within output
git_show f006
100%
Passed
Tokens
218
Input
78
Total output
77
Reasoning within output
git_show f007
100%
Passed
Tokens
203
Input
121
Total output
116
Reasoning within output
git_show f008
100%
Passed
Tokens
210
Input
203
Total output
166
Reasoning within output
git_show f009
100%
Passed
Tokens
320
Input
195
Total output
194
Reasoning within output
git_show f010
100%
Passed
Tokens
206
Input
158
Total output
157
Reasoning within output
git_show f011
100%
Passed
Tokens
229
Input
72
Total output
69
Reasoning within output
git_show f012
100%
Passed
Tokens
362
Input
91
Total output
90
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
82
Input
360
Total output
356
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
100
Input
284
Total output
277
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
73
Input
989
Total output
986
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
150
Input
1,006
Total output
980
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
140
Input
356
Total output
336
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
126
Input
307
Total output
285
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
136
Input
117
Total output
107
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
107
Input
138
Total output
132
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
99
Input
252
Total output
247
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
190
Input
777
Total output
747
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
143
Input
179
Total output
156
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
247
Input
10,014
Total output
9,967
Reasoning within output
rebase f001
100%
Passed
Tokens
95
Input
506
Total output
502
Reasoning within output
rebase f002
100%
Passed
Tokens
120
Input
132
Total output
125
Reasoning within output
rebase f003
100%
Passed
Tokens
98
Input
173
Total output
170
Reasoning within output
rebase f004
100%
Passed
Tokens
162
Input
3,079
Total output
3,053
Reasoning within output
rebase f005
100%
Passed
Tokens
144
Input
411
Total output
395
Reasoning within output
rebase f006
100%
Passed
Tokens
139
Input
362
Total output
340
Reasoning within output
rebase f007
100%
Passed
Tokens
137
Input
132
Total output
122
Reasoning within output
rebase f008
100%
Passed
Tokens
120
Input
76
Total output
70
Reasoning within output
rebase f009
100%
Passed
Tokens
99
Input
132
Total output
127
Reasoning within output
rebase f010
100%
Passed
Tokens
215
Input
752
Total output
722
Reasoning within output
rebase f011
100%
Passed
Tokens
155
Input
294
Total output
271
Reasoning within output
rebase f012
0%
Failed
Tokens
282
Input
4,879
Total output
4,832
Reasoning within output
reflog f001
100%
Passed
Tokens
249
Input
381
Total output
348
Reasoning within output
reflog f002
0%
Failed
Tokens
0
Input
0
Total output
0
Reasoning within output
reflog f003
100%
Passed
Tokens
208
Input
387
Total output
286
Reasoning within output
reflog f004
100%
Passed
Tokens
329
Input
932
Total output
669
Reasoning within output
reflog f005
100%
Passed
Tokens
397
Input
282
Total output
148
Reasoning within output
reflog f006
100%
Passed
Tokens
242
Input
610
Total output
460
Reasoning within output
reflog f007
100%
Passed
Tokens
296
Input
505
Total output
352
Reasoning within output
reflog f008
100%
Passed
Tokens
390
Input
270
Total output
124
Reasoning within output
reflog f009
100%
Passed
Tokens
333
Input
614
Total output
402
Reasoning within output
reflog f010
100%
Passed
Tokens
290
Input
420
Total output
288
Reasoning within output
reflog f011
100%
Passed
Tokens
350
Input
1,339
Total output
1,036
Reasoning within output
reflog f012
100%
Passed
Tokens
330
Input
650
Total output
416
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
137
Input
107
Total output
102
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
313
Input
122
Total output
117
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
127
Input
77
Total output
70
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
120
Input
108
Total output
97
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
130
Input
168
Total output
123
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
196
Input
120
Total output
104
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
220
Input
103
Total output
88
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
192
Input
84
Total output
70
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
222
Input
102
Total output
65
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
128
Input
155
Total output
150
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
123
Input
183
Total output
178
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
143
Input
102
Total output
88
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
36
Input
187
Total output
179
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
101
Input
1,134
Total output
1,127
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
104
Input
2,311
Total output
2,283
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
94
Input
191
Total output
188
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
43
Input
2,243
Total output
2,221
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
95
Input
724
Total output
721
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
43
Input
229
Total output
212
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
101
Input
543
Total output
538
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
95
Input
170
Total output
167
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
102
Input
601
Total output
595
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
107
Input
57
Total output
53
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
41
Input
199
Total output
188
Reasoning within output
tag_management f001
100%
Passed
Tokens
56
Input
161
Total output
155
Reasoning within output
tag_management f002
100%
Passed
Tokens
52
Input
445
Total output
428
Reasoning within output
tag_management f003
100%
Passed
Tokens
59
Input
178
Total output
168
Reasoning within output
tag_management f004
100%
Passed
Tokens
66
Input
155
Total output
153
Reasoning within output
tag_management f005
100%
Passed
Tokens
77
Input
210
Total output
203
Reasoning within output
tag_management f006
100%
Passed
Tokens
65
Input
216
Total output
202
Reasoning within output
tag_management f007
100%
Passed
Tokens
58
Input
500
Total output
489
Reasoning within output
tag_management f008
100%
Passed
Tokens
64
Input
265
Total output
242
Reasoning within output
tag_management f009
100%
Passed
Tokens
68
Input
340
Total output
324
Reasoning within output
tag_management f010
100%
Passed
Tokens
44
Input
121
Total output
114
Reasoning within output
tag_management f011
100%
Passed
Tokens
47
Input
154
Total output
149
Reasoning within output
tag_management f012
100%
Passed
Tokens
86
Input
175
Total output
166
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
150
Input
212
Total output
203
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
156
Input
686
Total output
663
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
229
Input
117
Total output
109
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
232
Input
2,090
Total output
2,086
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
142
Input
283
Total output
270
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
143
Input
118
Total output
105
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
151
Input
673
Total output
650
Reasoning within output
worktree_usage f008
100%
Passed
Tokens
162
Input
5,109
Total output
5,052
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
265
Input
84
Total output
80
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
240
Input
119
Total output
104
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
235
Input
113
Total output
105
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
139
Input
126
Total output
113
Reasoning within output