Google / gemini-3.6-flash
high
96.6%
197 / 204 fixtures · 1 run(s)
40,903 input / 119,676 total output / 115,139 reasoning within output tokens $0.95892450
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-2.4%
Text: 96.6% →
JSON: 94.1%
+0
Gained
JSON pass / text fail
−5
Lost
Text pass / JSON fail
192
Unchanged Pass
Both pass
7
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% | 83.3% | -8.3% |
| commit_squash | 100% | 91.7% | -8.3% |
| blame_forensics | 91.7% | 91.7% | + 0% |
| 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% |
| git_show | 100% | 100% | + 0% |
| merge_conflicts | 91.7% | 91.7% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 91.7% | 91.7% | + 0% |
| tag_management | 100% | 100% | + 0% |
| worktree_usage | 91.7% | 91.7% | + 0% |
Changed Fixtures (5)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
256
Input
609
Total output
605
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
255
Input
607
Total output
603
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
298
Input
339
Total output
333
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
208
Input
388
Total output
383
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
268
Input
1,375
Total output
1,370
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
247
Input
754
Total output
751
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
220
Input
529
Total output
525
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
261
Input
434
Total output
431
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
213
Input
363
Total output
360
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
458
Input
316
Total output
313
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
269
Input
504
Total output
501
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
156
Input
664
Total output
660
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
103
Input
348
Total output
344
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
118
Input
398
Total output
391
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
93
Input
335
Total output
334
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
130
Input
526
Total output
519
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
106
Input
311
Total output
307
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
131
Input
479
Total output
469
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
106
Input
411
Total output
404
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
116
Input
451
Total output
442
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
78
Input
282
Total output
281
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
112
Input
282
Total output
277
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
66
Input
205
Total output
204
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
158
Input
415
Total output
403
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
94
Input
363
Total output
359
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
112
Input
534
Total output
527
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
86
Input
507
Total output
504
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
164
Input
1,102
Total output
1,078
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
155
Input
506
Total output
486
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
141
Input
518
Total output
496
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
133
Input
468
Total output
458
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
126
Input
315
Total output
309
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
105
Input
311
Total output
306
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
227
Input
1,681
Total output
1,651
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
166
Input
533
Total output
510
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
289
Input
1,192
Total output
1,135
Reasoning within output
commit_messages f001
95%
Passed
Tokens
112
Input
416
Total output
412
Reasoning within output
commit_messages f002
85%
Passed
Tokens
245
Input
388
Total output
375
Reasoning within output
commit_messages f003
93.3%
Passed
Tokens
84
Input
277
Total output
267
Reasoning within output
commit_messages f004
95.3%
Passed
Tokens
118
Input
314
Total output
310
Reasoning within output
commit_messages f005
90%
Passed
Tokens
109
Input
214
Total output
208
Reasoning within output
commit_messages f006
93.3%
Passed
Tokens
152
Input
402
Total output
395
Reasoning within output
commit_messages f007
94%
Passed
Tokens
209
Input
274
Total output
268
Reasoning within output
commit_messages f008
92.7%
Passed
Tokens
77
Input
332
Total output
327
Reasoning within output
commit_messages f009
86.7%
Passed
Tokens
133
Input
738
Total output
731
Reasoning within output
commit_messages f010
91%
Passed
Tokens
332
Input
532
Total output
521
Reasoning within output
commit_messages f011
77.7%
Passed
Tokens
154
Input
1,298
Total output
1,286
Reasoning within output
commit_messages f012
90%
Passed
Tokens
131
Input
331
Total output
326
Reasoning within output
commit_squash f001
100%
Passed
Tokens
134
Input
1,306
Total output
1,293
Reasoning within output
commit_squash f002
100%
Passed
Tokens
114
Input
377
Total output
368
Reasoning within output
commit_squash f003
100%
Passed
Tokens
126
Input
3,111
Total output
3,098
Reasoning within output
commit_squash f004
100%
Passed
Tokens
111
Input
1,288
Total output
1,277
Reasoning within output
commit_squash f005
100%
Passed
Tokens
113
Input
1,986
Total output
1,979
Reasoning within output
commit_squash f006
100%
Passed
Tokens
96
Input
476
Total output
465
Reasoning within output
commit_squash f007
100%
Passed
Tokens
99
Input
622
Total output
610
Reasoning within output
commit_squash f008
100%
Passed
Tokens
110
Input
855
Total output
843
Reasoning within output
commit_squash f009
100%
Passed
Tokens
104
Input
1,425
Total output
1,414
Reasoning within output
commit_squash f010
100%
Passed
Tokens
120
Input
480
Total output
465
Reasoning within output
commit_squash f011
100%
Passed
Tokens
123
Input
707
Total output
692
Reasoning within output
commit_squash f012
100%
Passed
Tokens
123
Input
378
Total output
358
Reasoning within output
git_bisect f001
100%
Passed
Tokens
186
Input
262
Total output
248
Reasoning within output
git_bisect f002
100%
Passed
Tokens
216
Input
284
Total output
277
Reasoning within output
git_bisect f003
100%
Passed
Tokens
207
Input
279
Total output
256
Reasoning within output
git_bisect f004
100%
Passed
Tokens
217
Input
313
Total output
291
Reasoning within output
git_bisect f005
100%
Passed
Tokens
214
Input
214
Total output
208
Reasoning within output
git_bisect f006
100%
Passed
Tokens
241
Input
329
Total output
306
Reasoning within output
git_bisect f007
100%
Passed
Tokens
208
Input
329
Total output
304
Reasoning within output
git_bisect f008
100%
Passed
Tokens
213
Input
227
Total output
203
Reasoning within output
git_bisect f009
100%
Passed
Tokens
210
Input
260
Total output
254
Reasoning within output
git_bisect f010
100%
Passed
Tokens
211
Input
196
Total output
189
Reasoning within output
git_bisect f011
100%
Passed
Tokens
210
Input
182
Total output
175
Reasoning within output
git_bisect f012
100%
Passed
Tokens
240
Input
268
Total output
253
Reasoning within output
git_clean f001
100%
Passed
Tokens
50
Input
649
Total output
640
Reasoning within output
git_clean f002
100%
Passed
Tokens
63
Input
277
Total output
273
Reasoning within output
git_clean f003
100%
Passed
Tokens
63
Input
278
Total output
274
Reasoning within output
git_clean f004
100%
Passed
Tokens
63
Input
387
Total output
382
Reasoning within output
git_clean f005
100%
Passed
Tokens
50
Input
520
Total output
516
Reasoning within output
git_clean f006
100%
Passed
Tokens
80
Input
437
Total output
431
Reasoning within output
git_clean f007
100%
Passed
Tokens
69
Input
454
Total output
445
Reasoning within output
git_clean f008
100%
Passed
Tokens
77
Input
259
Total output
255
Reasoning within output
git_clean f009
100%
Passed
Tokens
74
Input
455
Total output
447
Reasoning within output
git_clean f010
100%
Passed
Tokens
65
Input
574
Total output
570
Reasoning within output
git_clean f011
100%
Passed
Tokens
65
Input
538
Total output
533
Reasoning within output
git_clean f012
100%
Passed
Tokens
69
Input
449
Total output
442
Reasoning within output
git_grep f001
100%
Passed
Tokens
48
Input
211
Total output
206
Reasoning within output
git_grep f002
100%
Passed
Tokens
59
Input
190
Total output
189
Reasoning within output
git_grep f003
100%
Passed
Tokens
101
Input
183
Total output
182
Reasoning within output
git_grep f004
100%
Passed
Tokens
76
Input
465
Total output
460
Reasoning within output
git_grep f005
100%
Passed
Tokens
115
Input
273
Total output
272
Reasoning within output
git_grep f006
100%
Passed
Tokens
34
Input
402
Total output
401
Reasoning within output
git_grep f007
100%
Passed
Tokens
177
Input
526
Total output
524
Reasoning within output
git_grep f008
100%
Passed
Tokens
57
Input
205
Total output
204
Reasoning within output
git_grep f009
100%
Passed
Tokens
50
Input
231
Total output
228
Reasoning within output
git_grep f010
100%
Passed
Tokens
64
Input
141
Total output
140
Reasoning within output
git_grep f011
100%
Passed
Tokens
127
Input
367
Total output
366
Reasoning within output
git_grep f012
100%
Passed
Tokens
65
Input
251
Total output
238
Reasoning within output
git_log_format f001
100%
Passed
Tokens
911
Input
256
Total output
255
Reasoning within output
git_log_format f002
100%
Passed
Tokens
920
Input
364
Total output
357
Reasoning within output
git_log_format f003
100%
Passed
Tokens
751
Input
311
Total output
302
Reasoning within output
git_log_format f004
100%
Passed
Tokens
911
Input
187
Total output
186
Reasoning within output
git_log_format f005
100%
Passed
Tokens
746
Input
613
Total output
608
Reasoning within output
git_log_format f006
100%
Passed
Tokens
935
Input
676
Total output
675
Reasoning within output
git_log_format f007
100%
Passed
Tokens
935
Input
283
Total output
276
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,249
Input
296
Total output
295
Reasoning within output
git_log_format f009
100%
Passed
Tokens
756
Input
146
Total output
145
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,451
Input
256
Total output
255
Reasoning within output
git_log_format f011
100%
Passed
Tokens
444
Input
361
Total output
358
Reasoning within output
git_log_format f012
100%
Passed
Tokens
414
Input
196
Total output
195
Reasoning within output
git_show f001
100%
Passed
Tokens
196
Input
244
Total output
239
Reasoning within output
git_show f002
100%
Passed
Tokens
205
Input
1,249
Total output
1,246
Reasoning within output
git_show f003
100%
Passed
Tokens
732
Input
204
Total output
198
Reasoning within output
git_show f004
100%
Passed
Tokens
486
Input
154
Total output
147
Reasoning within output
git_show f005
100%
Passed
Tokens
210
Input
282
Total output
280
Reasoning within output
git_show f006
100%
Passed
Tokens
219
Input
277
Total output
276
Reasoning within output
git_show f007
100%
Passed
Tokens
203
Input
286
Total output
281
Reasoning within output
git_show f008
100%
Passed
Tokens
212
Input
354
Total output
316
Reasoning within output
git_show f009
100%
Passed
Tokens
328
Input
345
Total output
344
Reasoning within output
git_show f010
100%
Passed
Tokens
204
Input
570
Total output
569
Reasoning within output
git_show f011
100%
Passed
Tokens
229
Input
183
Total output
180
Reasoning within output
git_show f012
100%
Passed
Tokens
364
Input
298
Total output
297
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
83
Input
323
Total output
319
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
101
Input
494
Total output
487
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
74
Input
1,120
Total output
1,117
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
150
Input
4,288
Total output
4,262
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
141
Input
586
Total output
566
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
127
Input
659
Total output
637
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
137
Input
465
Total output
455
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
107
Input
226
Total output
220
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
100
Input
339
Total output
334
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
191
Input
1,097
Total output
1,067
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
143
Input
613
Total output
590
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
247
Input
1,577
Total output
1,530
Reasoning within output
rebase f001
100%
Passed
Tokens
97
Input
799
Total output
795
Reasoning within output
rebase f002
100%
Passed
Tokens
123
Input
280
Total output
273
Reasoning within output
rebase f003
100%
Passed
Tokens
99
Input
439
Total output
436
Reasoning within output
rebase f004
100%
Passed
Tokens
164
Input
8,556
Total output
8,530
Reasoning within output
rebase f005
100%
Passed
Tokens
147
Input
491
Total output
475
Reasoning within output
rebase f006
100%
Passed
Tokens
141
Input
748
Total output
726
Reasoning within output
rebase f007
100%
Passed
Tokens
139
Input
420
Total output
410
Reasoning within output
rebase f008
100%
Passed
Tokens
121
Input
240
Total output
234
Reasoning within output
rebase f009
100%
Passed
Tokens
101
Input
408
Total output
403
Reasoning within output
rebase f010
100%
Passed
Tokens
218
Input
2,895
Total output
2,865
Reasoning within output
rebase f011
100%
Passed
Tokens
153
Input
675
Total output
652
Reasoning within output
rebase f012
0%
Failed
Tokens
285
Input
2,545
Total output
2,488
Reasoning within output
reflog f001
100%
Passed
Tokens
238
Input
640
Total output
606
Reasoning within output
reflog f002
100%
Passed
Tokens
235
Input
756
Total output
582
Reasoning within output
reflog f003
100%
Passed
Tokens
209
Input
566
Total output
384
Reasoning within output
reflog f004
100%
Passed
Tokens
364
Input
1,681
Total output
1,313
Reasoning within output
reflog f005
100%
Passed
Tokens
395
Input
653
Total output
616
Reasoning within output
reflog f006
100%
Passed
Tokens
253
Input
681
Total output
510
Reasoning within output
reflog f007
100%
Passed
Tokens
288
Input
641
Total output
491
Reasoning within output
reflog f008
100%
Passed
Tokens
393
Input
703
Total output
546
Reasoning within output
reflog f009
100%
Passed
Tokens
330
Input
1,437
Total output
1,113
Reasoning within output
reflog f010
100%
Passed
Tokens
292
Input
1,125
Total output
882
Reasoning within output
reflog f011
100%
Passed
Tokens
343
Input
1,914
Total output
1,593
Reasoning within output
reflog f012
100%
Passed
Tokens
345
Input
1,445
Total output
1,230
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
136
Input
250
Total output
231
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
314
Input
455
Total output
345
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
127
Input
186
Total output
170
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
120
Input
171
Total output
153
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
131
Input
298
Total output
238
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
197
Input
191
Total output
176
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
221
Input
295
Total output
279
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
192
Input
272
Total output
257
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
223
Input
315
Total output
268
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
128
Input
207
Total output
193
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
122
Input
270
Total output
253
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
143
Input
249
Total output
235
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
36
Input
224
Total output
216
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
96
Input
1,060
Total output
1,053
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
109
Input
969
Total output
946
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
94
Input
163
Total output
160
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
44
Input
1,120
Total output
1,095
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
90
Input
435
Total output
432
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
44
Input
361
Total output
344
Reasoning within output
submodule_usage f008
33.3%
Failed
Tokens
103
Input
1,078
Total output
1,069
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
93
Input
163
Total output
160
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
102
Input
409
Total output
404
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
103
Input
244
Total output
240
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
41
Input
322
Total output
311
Reasoning within output
tag_management f001
100%
Passed
Tokens
56
Input
147
Total output
141
Reasoning within output
tag_management f002
100%
Passed
Tokens
53
Input
330
Total output
313
Reasoning within output
tag_management f003
100%
Passed
Tokens
62
Input
199
Total output
189
Reasoning within output
tag_management f004
100%
Passed
Tokens
66
Input
187
Total output
185
Reasoning within output
tag_management f005
100%
Passed
Tokens
80
Input
238
Total output
231
Reasoning within output
tag_management f006
100%
Passed
Tokens
62
Input
318
Total output
306
Reasoning within output
tag_management f007
100%
Passed
Tokens
59
Input
424
Total output
413
Reasoning within output
tag_management f008
100%
Passed
Tokens
65
Input
422
Total output
399
Reasoning within output
tag_management f009
100%
Passed
Tokens
68
Input
379
Total output
363
Reasoning within output
tag_management f010
100%
Passed
Tokens
44
Input
151
Total output
144
Reasoning within output
tag_management f011
100%
Passed
Tokens
48
Input
181
Total output
176
Reasoning within output
tag_management f012
100%
Passed
Tokens
86
Input
520
Total output
511
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
149
Input
340
Total output
331
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
155
Input
528
Total output
505
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
232
Input
202
Total output
194
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
230
Input
188
Total output
184
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
143
Input
231
Total output
218
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
143
Input
323
Total output
310
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
150
Input
767
Total output
745
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
174
Input
1,994
Total output
1,940
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
270
Input
364
Total output
360
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
244
Input
271
Total output
256
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
238
Input
221
Total output
213
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
145
Input
381
Total output
368
Reasoning within output