Google / gemini-3-flash-preview
medium
97.1%
198 / 204 fixtures · 1 run(s)
40,601 input / 91,929 total output / 87,442 reasoning within output tokens $0.29608750
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-2.9%
Text: 97.1% →
JSON: 94.1%
+0
Gained
JSON pass / text fail
−6
Lost
Text pass / JSON fail
192
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% |
| merge_conflicts | 91.7% | 83.3% | -8.3% |
| rebase | 91.7% | 83.3% | -8.3% |
| cherry_pick | 83.3% | 75% | -8.3% |
| blame_forensics | 100% | 100% | + 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% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
| worktree_usage | 91.7% | 91.7% | + 0% |
Changed Fixtures (6)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
262
Input
1,205
Total output
1,201
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
256
Input
408
Total output
404
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
291
Input
309
Total output
303
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
205
Input
544
Total output
539
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
273
Input
1,355
Total output
1,352
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
249
Input
797
Total output
794
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
220
Input
369
Total output
365
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
261
Input
869
Total output
866
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
214
Input
359
Total output
356
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
460
Input
495
Total output
492
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
264
Input
201
Total output
198
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
156
Input
647
Total output
643
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
102
Input
270
Total output
266
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
118
Input
284
Total output
277
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
89
Input
325
Total output
324
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
125
Input
273
Total output
266
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
103
Input
290
Total output
286
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
130
Input
260
Total output
250
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
98
Input
250
Total output
243
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
118
Input
414
Total output
405
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
77
Input
239
Total output
238
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
111
Input
236
Total output
231
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
65
Input
183
Total output
182
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
155
Input
383
Total output
371
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
94
Input
240
Total output
236
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
114
Input
442
Total output
435
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
84
Input
387
Total output
384
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
165
Input
1,752
Total output
1,728
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
152
Input
377
Total output
357
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
141
Input
203
Total output
181
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
134
Input
269
Total output
259
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
125
Input
231
Total output
225
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
106
Input
219
Total output
214
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
227
Input
950
Total output
920
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
165
Input
258
Total output
235
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
284
Input
2,946
Total output
2,899
Reasoning within output
commit_messages f001
92.7%
Passed
Tokens
112
Input
303
Total output
299
Reasoning within output
commit_messages f002
81%
Passed
Tokens
245
Input
460
Total output
447
Reasoning within output
commit_messages f003
96.7%
Passed
Tokens
83
Input
223
Total output
213
Reasoning within output
commit_messages f004
94.3%
Passed
Tokens
118
Input
265
Total output
261
Reasoning within output
commit_messages f005
91%
Passed
Tokens
109
Input
344
Total output
339
Reasoning within output
commit_messages f006
92.7%
Passed
Tokens
151
Input
295
Total output
288
Reasoning within output
commit_messages f007
92.7%
Passed
Tokens
209
Input
200
Total output
194
Reasoning within output
commit_messages f008
92%
Passed
Tokens
76
Input
215
Total output
210
Reasoning within output
commit_messages f009
81.7%
Passed
Tokens
133
Input
462
Total output
455
Reasoning within output
commit_messages f010
93.3%
Passed
Tokens
332
Input
511
Total output
504
Reasoning within output
commit_messages f011
71.3%
Passed
Tokens
153
Input
593
Total output
584
Reasoning within output
commit_messages f012
92.7%
Passed
Tokens
130
Input
193
Total output
188
Reasoning within output
commit_squash f001
100%
Passed
Tokens
132
Input
1,361
Total output
1,348
Reasoning within output
commit_squash f002
100%
Passed
Tokens
114
Input
223
Total output
214
Reasoning within output
commit_squash f003
100%
Passed
Tokens
124
Input
493
Total output
480
Reasoning within output
commit_squash f004
100%
Passed
Tokens
112
Input
333
Total output
322
Reasoning within output
commit_squash f005
100%
Passed
Tokens
111
Input
368
Total output
361
Reasoning within output
commit_squash f006
100%
Passed
Tokens
97
Input
243
Total output
232
Reasoning within output
commit_squash f007
100%
Passed
Tokens
99
Input
388
Total output
376
Reasoning within output
commit_squash f008
100%
Passed
Tokens
112
Input
368
Total output
356
Reasoning within output
commit_squash f009
100%
Failed
Tokens
101
Input
478
Total output
464
Reasoning within output
commit_squash f010
100%
Passed
Tokens
118
Input
342
Total output
327
Reasoning within output
commit_squash f011
100%
Passed
Tokens
121
Input
300
Total output
285
Reasoning within output
commit_squash f012
100%
Passed
Tokens
122
Input
346
Total output
326
Reasoning within output
git_bisect f001
100%
Passed
Tokens
187
Input
314
Total output
307
Reasoning within output
git_bisect f002
100%
Passed
Tokens
215
Input
340
Total output
333
Reasoning within output
git_bisect f003
100%
Passed
Tokens
205
Input
464
Total output
459
Reasoning within output
git_bisect f004
100%
Passed
Tokens
205
Input
292
Total output
286
Reasoning within output
git_bisect f005
100%
Passed
Tokens
213
Input
336
Total output
231
Reasoning within output
git_bisect f006
100%
Passed
Tokens
239
Input
183
Total output
171
Reasoning within output
git_bisect f007
100%
Passed
Tokens
211
Input
225
Total output
218
Reasoning within output
git_bisect f008
100%
Passed
Tokens
211
Input
152
Total output
145
Reasoning within output
git_bisect f009
100%
Passed
Tokens
211
Input
214
Total output
208
Reasoning within output
git_bisect f010
100%
Passed
Tokens
207
Input
273
Total output
268
Reasoning within output
git_bisect f011
100%
Passed
Tokens
215
Input
318
Total output
298
Reasoning within output
git_bisect f012
100%
Passed
Tokens
237
Input
364
Total output
359
Reasoning within output
git_clean f001
100%
Passed
Tokens
50
Input
428
Total output
424
Reasoning within output
git_clean f002
100%
Passed
Tokens
62
Input
173
Total output
169
Reasoning within output
git_clean f003
100%
Passed
Tokens
62
Input
208
Total output
204
Reasoning within output
git_clean f004
100%
Passed
Tokens
62
Input
235
Total output
230
Reasoning within output
git_clean f005
100%
Passed
Tokens
49
Input
228
Total output
224
Reasoning within output
git_clean f006
100%
Passed
Tokens
80
Input
474
Total output
468
Reasoning within output
git_clean f007
100%
Passed
Tokens
69
Input
232
Total output
223
Reasoning within output
git_clean f008
100%
Passed
Tokens
77
Input
250
Total output
246
Reasoning within output
git_clean f009
100%
Passed
Tokens
73
Input
287
Total output
279
Reasoning within output
git_clean f010
100%
Passed
Tokens
64
Input
171
Total output
167
Reasoning within output
git_clean f011
100%
Passed
Tokens
64
Input
289
Total output
284
Reasoning within output
git_clean f012
100%
Passed
Tokens
69
Input
218
Total output
211
Reasoning within output
git_grep f001
100%
Passed
Tokens
48
Input
147
Total output
142
Reasoning within output
git_grep f002
100%
Passed
Tokens
59
Input
125
Total output
124
Reasoning within output
git_grep f003
100%
Passed
Tokens
100
Input
232
Total output
231
Reasoning within output
git_grep f004
100%
Passed
Tokens
76
Input
281
Total output
276
Reasoning within output
git_grep f005
100%
Passed
Tokens
114
Input
234
Total output
233
Reasoning within output
git_grep f006
100%
Passed
Tokens
33
Input
603
Total output
602
Reasoning within output
git_grep f007
100%
Passed
Tokens
176
Input
497
Total output
495
Reasoning within output
git_grep f008
100%
Passed
Tokens
56
Input
169
Total output
168
Reasoning within output
git_grep f009
100%
Passed
Tokens
49
Input
149
Total output
146
Reasoning within output
git_grep f010
100%
Passed
Tokens
63
Input
177
Total output
176
Reasoning within output
git_grep f011
100%
Passed
Tokens
126
Input
200
Total output
199
Reasoning within output
git_grep f012
100%
Passed
Tokens
64
Input
187
Total output
174
Reasoning within output
git_log_format f001
100%
Passed
Tokens
916
Input
201
Total output
200
Reasoning within output
git_log_format f002
100%
Passed
Tokens
923
Input
333
Total output
326
Reasoning within output
git_log_format f003
100%
Passed
Tokens
723
Input
355
Total output
346
Reasoning within output
git_log_format f004
100%
Passed
Tokens
887
Input
523
Total output
522
Reasoning within output
git_log_format f005
100%
Passed
Tokens
746
Input
355
Total output
350
Reasoning within output
git_log_format f006
100%
Passed
Tokens
934
Input
622
Total output
621
Reasoning within output
git_log_format f007
100%
Passed
Tokens
929
Input
252
Total output
245
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,235
Input
289
Total output
288
Reasoning within output
git_log_format f009
100%
Passed
Tokens
755
Input
141
Total output
140
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,434
Input
411
Total output
410
Reasoning within output
git_log_format f011
100%
Passed
Tokens
438
Input
249
Total output
246
Reasoning within output
git_log_format f012
100%
Passed
Tokens
393
Input
208
Total output
207
Reasoning within output
git_show f001
100%
Passed
Tokens
196
Input
218
Total output
213
Reasoning within output
git_show f002
100%
Passed
Tokens
205
Input
5,292
Total output
5,289
Reasoning within output
git_show f003
100%
Passed
Tokens
725
Input
336
Total output
330
Reasoning within output
git_show f004
100%
Passed
Tokens
482
Input
184
Total output
177
Reasoning within output
git_show f005
100%
Passed
Tokens
206
Input
288
Total output
286
Reasoning within output
git_show f006
100%
Passed
Tokens
213
Input
144
Total output
143
Reasoning within output
git_show f007
100%
Passed
Tokens
203
Input
237
Total output
232
Reasoning within output
git_show f008
100%
Passed
Tokens
209
Input
306
Total output
270
Reasoning within output
git_show f009
100%
Passed
Tokens
320
Input
402
Total output
401
Reasoning within output
git_show f010
100%
Passed
Tokens
201
Input
207
Total output
206
Reasoning within output
git_show f011
100%
Passed
Tokens
225
Input
354
Total output
351
Reasoning within output
git_show f012
100%
Passed
Tokens
359
Input
182
Total output
181
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
82
Input
1,120
Total output
1,116
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
100
Input
775
Total output
768
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
73
Input
658
Total output
655
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
150
Input
1,425
Total output
1,399
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
140
Input
452
Total output
432
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
126
Input
551
Total output
529
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
136
Input
316
Total output
306
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
107
Input
162
Total output
156
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
99
Input
247
Total output
242
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
190
Input
735
Total output
705
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
143
Input
294
Total output
271
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
247
Input
5,131
Total output
5,084
Reasoning within output
rebase f001
100%
Passed
Tokens
95
Input
675
Total output
671
Reasoning within output
rebase f002
100%
Passed
Tokens
120
Input
248
Total output
241
Reasoning within output
rebase f003
100%
Passed
Tokens
100
Input
247
Total output
244
Reasoning within output
rebase f004
100%
Passed
Tokens
165
Input
1,962
Total output
1,936
Reasoning within output
rebase f005
100%
Passed
Tokens
147
Input
388
Total output
372
Reasoning within output
rebase f006
100%
Passed
Tokens
140
Input
416
Total output
394
Reasoning within output
rebase f007
100%
Passed
Tokens
137
Input
323
Total output
313
Reasoning within output
rebase f008
100%
Passed
Tokens
120
Input
250
Total output
244
Reasoning within output
rebase f009
100%
Passed
Tokens
101
Input
277
Total output
272
Reasoning within output
rebase f010
100%
Passed
Tokens
217
Input
932
Total output
902
Reasoning within output
rebase f011
100%
Passed
Tokens
153
Input
347
Total output
324
Reasoning within output
rebase f012
0%
Failed
Tokens
280
Input
2,423
Total output
2,376
Reasoning within output
reflog f001
100%
Passed
Tokens
249
Input
477
Total output
445
Reasoning within output
reflog f002
100%
Passed
Tokens
231
Input
579
Total output
416
Reasoning within output
reflog f003
100%
Passed
Tokens
211
Input
514
Total output
369
Reasoning within output
reflog f004
100%
Passed
Tokens
345
Input
1,021
Total output
743
Reasoning within output
reflog f005
100%
Passed
Tokens
385
Input
466
Total output
337
Reasoning within output
reflog f006
100%
Passed
Tokens
258
Input
535
Total output
296
Reasoning within output
reflog f007
100%
Passed
Tokens
287
Input
487
Total output
353
Reasoning within output
reflog f008
100%
Passed
Tokens
374
Input
620
Total output
395
Reasoning within output
reflog f009
100%
Passed
Tokens
343
Input
781
Total output
568
Reasoning within output
reflog f010
100%
Passed
Tokens
285
Input
494
Total output
320
Reasoning within output
reflog f011
100%
Passed
Tokens
337
Input
832
Total output
631
Reasoning within output
reflog f012
100%
Passed
Tokens
342
Input
868
Total output
642
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
137
Input
155
Total output
135
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
313
Input
422
Total output
223
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
127
Input
143
Total output
110
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
120
Input
127
Total output
116
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
129
Input
405
Total output
255
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
196
Input
125
Total output
112
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
220
Input
221
Total output
203
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
192
Input
274
Total output
257
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
222
Input
210
Total output
160
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
128
Input
200
Total output
187
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
123
Input
258
Total output
245
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
143
Input
191
Total output
177
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
36
Input
131
Total output
123
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
102
Input
473
Total output
466
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
110
Input
542
Total output
519
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
94
Input
175
Total output
172
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
43
Input
877
Total output
853
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
91
Input
607
Total output
604
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
43
Input
164
Total output
147
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
103
Input
166
Total output
161
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
100
Input
103
Total output
100
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
103
Input
221
Total output
214
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
111
Input
64
Total output
60
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
41
Input
138
Total output
127
Reasoning within output
tag_management f001
100%
Passed
Tokens
57
Input
187
Total output
181
Reasoning within output
tag_management f002
100%
Passed
Tokens
51
Input
215
Total output
198
Reasoning within output
tag_management f003
100%
Passed
Tokens
62
Input
296
Total output
286
Reasoning within output
tag_management f004
100%
Passed
Tokens
65
Input
154
Total output
152
Reasoning within output
tag_management f005
100%
Passed
Tokens
80
Input
151
Total output
144
Reasoning within output
tag_management f006
100%
Passed
Tokens
64
Input
251
Total output
237
Reasoning within output
tag_management f007
100%
Passed
Tokens
60
Input
236
Total output
225
Reasoning within output
tag_management f008
100%
Passed
Tokens
63
Input
803
Total output
780
Reasoning within output
tag_management f009
100%
Passed
Tokens
68
Input
276
Total output
260
Reasoning within output
tag_management f010
100%
Passed
Tokens
45
Input
134
Total output
127
Reasoning within output
tag_management f011
100%
Passed
Tokens
46
Input
186
Total output
181
Reasoning within output
tag_management f012
100%
Passed
Tokens
85
Input
665
Total output
656
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
151
Input
155
Total output
146
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
154
Input
412
Total output
391
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
226
Input
189
Total output
181
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
233
Input
98
Total output
94
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
140
Input
246
Total output
233
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
143
Input
300
Total output
287
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
147
Input
216
Total output
193
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
169
Input
1,544
Total output
1,490
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
260
Input
128
Total output
124
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
240
Input
132
Total output
117
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
240
Input
94
Total output
86
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
145
Input
137
Total output
124
Reasoning within output