Google / gemini-3.5-flash
low
97.6%
199 / 204 fixtures · 1 run(s)
40,633 input / 59,225 total output / 54,937 reasoning within output tokens $0.59397450
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-2.5%
Text: 97.6% →
JSON: 95.1%
+1
Gained
JSON pass / text fail
−6
Lost
Text pass / JSON fail
193
Unchanged Pass
Both pass
4
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| branch_cleanup | 100% | 75% | -25% |
| cherry_pick | 91.7% | 83.3% | -8.3% |
| worktree_usage | 83.3% | 91.7% | + 8.3% |
| commit_squash | 100% | 91.7% | -8.3% |
| submodule_usage | 100% | 91.7% | -8.3% |
| blame_forensics | 100% | 100% | + 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% |
| git_show | 100% | 100% | + 0% |
| merge_conflicts | 91.7% | 91.7% | + 0% |
| rebase | 91.7% | 91.7% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
Changed Fixtures (7)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
260
Input
358
Total output
354
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
256
Input
341
Total output
337
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
293
Input
179
Total output
173
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
210
Input
160
Total output
155
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
267
Input
282
Total output
279
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
248
Input
276
Total output
273
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
216
Input
134
Total output
130
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
257
Input
264
Total output
261
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
214
Input
211
Total output
208
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
466
Input
173
Total output
170
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
268
Input
175
Total output
172
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
154
Input
388
Total output
384
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
99
Input
251
Total output
247
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
118
Input
268
Total output
261
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
91
Input
119
Total output
118
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
129
Input
323
Total output
316
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
106
Input
308
Total output
304
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
128
Input
149
Total output
139
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
105
Input
292
Total output
285
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
120
Input
309
Total output
300
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
77
Input
283
Total output
282
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
112
Input
224
Total output
219
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
65
Input
64
Total output
63
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
158
Input
365
Total output
353
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
94
Input
369
Total output
365
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
114
Input
482
Total output
475
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
86
Input
379
Total output
376
Reasoning within output
cherry_pick f004
100%
Passed
Tokens
165
Input
798
Total output
772
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
153
Input
234
Total output
214
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
142
Input
263
Total output
241
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
132
Input
196
Total output
186
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
124
Input
207
Total output
201
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
104
Input
170
Total output
165
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
227
Input
428
Total output
398
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
163
Input
239
Total output
216
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
286
Input
1,002
Total output
955
Reasoning within output
commit_messages f001
91%
Passed
Tokens
112
Input
298
Total output
294
Reasoning within output
commit_messages f002
87.7%
Passed
Tokens
245
Input
169
Total output
165
Reasoning within output
commit_messages f003
95%
Passed
Tokens
83
Input
289
Total output
279
Reasoning within output
commit_messages f004
92.7%
Passed
Tokens
118
Input
183
Total output
179
Reasoning within output
commit_messages f005
88.3%
Passed
Tokens
109
Input
289
Total output
284
Reasoning within output
commit_messages f006
91%
Passed
Tokens
151
Input
110
Total output
104
Reasoning within output
commit_messages f007
91.7%
Passed
Tokens
209
Input
142
Total output
136
Reasoning within output
commit_messages f008
92%
Passed
Tokens
76
Input
208
Total output
203
Reasoning within output
commit_messages f009
86.7%
Passed
Tokens
133
Input
296
Total output
289
Reasoning within output
commit_messages f010
92%
Passed
Tokens
332
Input
161
Total output
154
Reasoning within output
commit_messages f011
58.3%
Passed
Tokens
153
Input
340
Total output
333
Reasoning within output
commit_messages f012
90%
Passed
Tokens
130
Input
213
Total output
208
Reasoning within output
commit_squash f001
100%
Passed
Tokens
132
Input
745
Total output
732
Reasoning within output
commit_squash f002
100%
Passed
Tokens
114
Input
258
Total output
249
Reasoning within output
commit_squash f003
100%
Passed
Tokens
125
Input
432
Total output
419
Reasoning within output
commit_squash f004
100%
Passed
Tokens
113
Input
431
Total output
420
Reasoning within output
commit_squash f005
100%
Passed
Tokens
110
Input
334
Total output
327
Reasoning within output
commit_squash f006
100%
Passed
Tokens
97
Input
143
Total output
132
Reasoning within output
commit_squash f007
100%
Passed
Tokens
96
Input
322
Total output
310
Reasoning within output
commit_squash f008
100%
Passed
Tokens
112
Input
403
Total output
391
Reasoning within output
commit_squash f009
100%
Passed
Tokens
103
Input
523
Total output
512
Reasoning within output
commit_squash f010
100%
Passed
Tokens
117
Input
264
Total output
249
Reasoning within output
commit_squash f011
100%
Passed
Tokens
126
Input
325
Total output
310
Reasoning within output
commit_squash f012
100%
Passed
Tokens
121
Input
290
Total output
270
Reasoning within output
git_bisect f001
100%
Passed
Tokens
185
Input
143
Total output
120
Reasoning within output
git_bisect f002
100%
Passed
Tokens
213
Input
80
Total output
73
Reasoning within output
git_bisect f003
100%
Passed
Tokens
213
Input
167
Total output
147
Reasoning within output
git_bisect f004
100%
Passed
Tokens
213
Input
199
Total output
184
Reasoning within output
git_bisect f005
100%
Passed
Tokens
211
Input
162
Total output
118
Reasoning within output
git_bisect f006
100%
Passed
Tokens
239
Input
132
Total output
127
Reasoning within output
git_bisect f007
100%
Passed
Tokens
209
Input
182
Total output
176
Reasoning within output
git_bisect f008
100%
Passed
Tokens
203
Input
127
Total output
121
Reasoning within output
git_bisect f009
100%
Passed
Tokens
211
Input
158
Total output
152
Reasoning within output
git_bisect f010
100%
Passed
Tokens
217
Input
86
Total output
79
Reasoning within output
git_bisect f011
100%
Passed
Tokens
211
Input
123
Total output
101
Reasoning within output
git_bisect f012
100%
Passed
Tokens
241
Input
119
Total output
112
Reasoning within output
git_clean f001
100%
Passed
Tokens
50
Input
346
Total output
342
Reasoning within output
git_clean f002
100%
Passed
Tokens
62
Input
244
Total output
240
Reasoning within output
git_clean f003
100%
Passed
Tokens
62
Input
258
Total output
254
Reasoning within output
git_clean f004
100%
Passed
Tokens
62
Input
459
Total output
454
Reasoning within output
git_clean f005
100%
Passed
Tokens
49
Input
348
Total output
344
Reasoning within output
git_clean f006
100%
Passed
Tokens
80
Input
552
Total output
546
Reasoning within output
git_clean f007
100%
Passed
Tokens
69
Input
259
Total output
250
Reasoning within output
git_clean f008
100%
Passed
Tokens
77
Input
251
Total output
247
Reasoning within output
git_clean f009
100%
Passed
Tokens
73
Input
371
Total output
363
Reasoning within output
git_clean f010
100%
Passed
Tokens
64
Input
326
Total output
322
Reasoning within output
git_clean f011
100%
Passed
Tokens
64
Input
374
Total output
369
Reasoning within output
git_clean f012
100%
Passed
Tokens
69
Input
474
Total output
467
Reasoning within output
git_grep f001
100%
Passed
Tokens
48
Input
204
Total output
199
Reasoning within output
git_grep f002
100%
Passed
Tokens
60
Input
105
Total output
104
Reasoning within output
git_grep f003
100%
Passed
Tokens
100
Input
105
Total output
104
Reasoning within output
git_grep f004
100%
Passed
Tokens
76
Input
250
Total output
245
Reasoning within output
git_grep f005
100%
Passed
Tokens
114
Input
185
Total output
184
Reasoning within output
git_grep f006
100%
Passed
Tokens
33
Input
203
Total output
202
Reasoning within output
git_grep f007
100%
Passed
Tokens
176
Input
423
Total output
421
Reasoning within output
git_grep f008
100%
Passed
Tokens
56
Input
194
Total output
193
Reasoning within output
git_grep f009
100%
Passed
Tokens
49
Input
174
Total output
171
Reasoning within output
git_grep f010
100%
Passed
Tokens
63
Input
165
Total output
164
Reasoning within output
git_grep f011
100%
Passed
Tokens
126
Input
167
Total output
166
Reasoning within output
git_grep f012
100%
Passed
Tokens
64
Input
237
Total output
224
Reasoning within output
git_log_format f001
100%
Passed
Tokens
908
Input
137
Total output
136
Reasoning within output
git_log_format f002
100%
Passed
Tokens
892
Input
194
Total output
187
Reasoning within output
git_log_format f003
100%
Passed
Tokens
740
Input
144
Total output
135
Reasoning within output
git_log_format f004
100%
Passed
Tokens
905
Input
90
Total output
89
Reasoning within output
git_log_format f005
100%
Passed
Tokens
746
Input
177
Total output
172
Reasoning within output
git_log_format f006
100%
Passed
Tokens
934
Input
359
Total output
358
Reasoning within output
git_log_format f007
100%
Passed
Tokens
935
Input
217
Total output
210
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,224
Input
123
Total output
122
Reasoning within output
git_log_format f009
100%
Passed
Tokens
762
Input
69
Total output
68
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,424
Input
313
Total output
312
Reasoning within output
git_log_format f011
100%
Passed
Tokens
443
Input
168
Total output
165
Reasoning within output
git_log_format f012
100%
Passed
Tokens
399
Input
138
Total output
137
Reasoning within output
git_show f001
100%
Passed
Tokens
190
Input
100
Total output
95
Reasoning within output
git_show f002
100%
Passed
Tokens
208
Input
237
Total output
234
Reasoning within output
git_show f003
100%
Passed
Tokens
723
Input
120
Total output
114
Reasoning within output
git_show f004
100%
Passed
Tokens
480
Input
83
Total output
76
Reasoning within output
git_show f005
100%
Passed
Tokens
208
Input
106
Total output
104
Reasoning within output
git_show f006
100%
Passed
Tokens
217
Input
225
Total output
224
Reasoning within output
git_show f007
100%
Passed
Tokens
203
Input
68
Total output
63
Reasoning within output
git_show f008
100%
Passed
Tokens
208
Input
119
Total output
84
Reasoning within output
git_show f009
100%
Passed
Tokens
325
Input
145
Total output
144
Reasoning within output
git_show f010
100%
Passed
Tokens
203
Input
104
Total output
103
Reasoning within output
git_show f011
100%
Passed
Tokens
231
Input
80
Total output
77
Reasoning within output
git_show f012
100%
Passed
Tokens
361
Input
118
Total output
117
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
82
Input
263
Total output
259
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
100
Input
246
Total output
239
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
73
Input
359
Total output
356
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
150
Input
799
Total output
773
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
140
Input
340
Total output
320
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
126
Input
412
Total output
390
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
136
Input
130
Total output
120
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
107
Input
244
Total output
238
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
99
Input
236
Total output
231
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
190
Input
409
Total output
377
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
143
Input
198
Total output
175
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
247
Input
1,515
Total output
1,466
Reasoning within output
rebase f001
100%
Passed
Tokens
94
Input
367
Total output
363
Reasoning within output
rebase f002
100%
Passed
Tokens
118
Input
233
Total output
226
Reasoning within output
rebase f003
100%
Passed
Tokens
99
Input
335
Total output
332
Reasoning within output
rebase f004
100%
Passed
Tokens
164
Input
1,200
Total output
1,174
Reasoning within output
rebase f005
100%
Passed
Tokens
146
Input
500
Total output
484
Reasoning within output
rebase f006
100%
Passed
Tokens
141
Input
509
Total output
487
Reasoning within output
rebase f007
100%
Passed
Tokens
137
Input
384
Total output
374
Reasoning within output
rebase f008
100%
Passed
Tokens
120
Input
467
Total output
461
Reasoning within output
rebase f009
100%
Passed
Tokens
99
Input
250
Total output
245
Reasoning within output
rebase f010
100%
Passed
Tokens
219
Input
622
Total output
592
Reasoning within output
rebase f011
100%
Passed
Tokens
154
Input
563
Total output
535
Reasoning within output
rebase f012
0%
Failed
Tokens
284
Input
939
Total output
892
Reasoning within output
reflog f001
100%
Passed
Tokens
248
Input
371
Total output
333
Reasoning within output
reflog f002
100%
Passed
Tokens
242
Input
326
Total output
208
Reasoning within output
reflog f003
100%
Passed
Tokens
206
Input
413
Total output
276
Reasoning within output
reflog f004
100%
Passed
Tokens
345
Input
1,226
Total output
948
Reasoning within output
reflog f005
100%
Passed
Tokens
383
Input
200
Total output
118
Reasoning within output
reflog f006
100%
Passed
Tokens
252
Input
627
Total output
360
Reasoning within output
reflog f007
100%
Passed
Tokens
294
Input
413
Total output
291
Reasoning within output
reflog f008
100%
Passed
Tokens
384
Input
374
Total output
214
Reasoning within output
reflog f009
100%
Passed
Tokens
323
Input
760
Total output
483
Reasoning within output
reflog f010
100%
Passed
Tokens
289
Input
436
Total output
246
Reasoning within output
reflog f011
100%
Passed
Tokens
350
Input
638
Total output
417
Reasoning within output
reflog f012
100%
Passed
Tokens
341
Input
936
Total output
592
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
136
Input
123
Total output
101
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
310
Input
221
Total output
148
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
127
Input
151
Total output
132
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
120
Input
163
Total output
142
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
129
Input
177
Total output
157
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
196
Input
114
Total output
98
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
216
Input
89
Total output
73
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
192
Input
78
Total output
63
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
222
Input
188
Total output
135
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
128
Input
181
Total output
166
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
123
Input
232
Total output
203
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
143
Input
178
Total output
164
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
36
Input
131
Total output
123
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
103
Input
409
Total output
402
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
104
Input
271
Total output
248
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
96
Input
121
Total output
118
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
43
Input
220
Total output
195
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
92
Input
184
Total output
181
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
43
Input
161
Total output
144
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
98
Input
236
Total output
231
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
95
Input
90
Total output
87
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
101
Input
332
Total output
327
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
106
Input
155
Total output
151
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
41
Input
219
Total output
208
Reasoning within output
tag_management f001
100%
Passed
Tokens
55
Input
117
Total output
111
Reasoning within output
tag_management f002
100%
Passed
Tokens
53
Input
344
Total output
327
Reasoning within output
tag_management f003
100%
Passed
Tokens
60
Input
263
Total output
253
Reasoning within output
tag_management f004
100%
Passed
Tokens
65
Input
111
Total output
109
Reasoning within output
tag_management f005
100%
Passed
Tokens
79
Input
208
Total output
201
Reasoning within output
tag_management f006
100%
Passed
Tokens
64
Input
246
Total output
233
Reasoning within output
tag_management f007
100%
Passed
Tokens
59
Input
284
Total output
273
Reasoning within output
tag_management f008
100%
Passed
Tokens
64
Input
391
Total output
368
Reasoning within output
tag_management f009
100%
Passed
Tokens
67
Input
259
Total output
243
Reasoning within output
tag_management f010
100%
Passed
Tokens
44
Input
220
Total output
213
Reasoning within output
tag_management f011
100%
Passed
Tokens
47
Input
324
Total output
319
Reasoning within output
tag_management f012
100%
Passed
Tokens
86
Input
514
Total output
505
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
149
Input
215
Total output
206
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
156
Input
278
Total output
255
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
236
Input
155
Total output
147
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
234
Input
151
Total output
147
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
140
Input
245
Total output
232
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
140
Input
270
Total output
257
Reasoning within output
worktree_usage f007
0%
Failed
Tokens
148
Input
466
Total output
439
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
170
Input
941
Total output
898
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
271
Input
177
Total output
173
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
240
Input
104
Total output
89
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
236
Input
79
Total output
71
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
140
Input
382
Total output
369
Reasoning within output