Google / gemini-3.6-flash
max
96.6%
197 / 204 fixtures · 1 run(s)
40,836 input / 132,249 total output / 127,637 reasoning within output tokens $1.05312150
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-1.5%
Text: 96.6% →
JSON: 95.1%
+3
Gained
JSON pass / text fail
−6
Lost
Text pass / JSON fail
191
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% |
| blame_forensics | 91.7% | 100% | + 8.3% |
| git_grep | 100% | 91.7% | -8.3% |
| submodule_usage | 91.7% | 100% | + 8.3% |
| worktree_usage | 100% | 91.7% | -8.3% |
| 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_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 (9)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
264
Input
578
Total output
574
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
261
Input
419
Total output
415
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
296
Input
344
Total output
338
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
211
Input
509
Total output
504
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
272
Input
1,804
Total output
1,799
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
249
Input
864
Total output
861
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
221
Input
536
Total output
532
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
259
Input
522
Total output
519
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
212
Input
413
Total output
410
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
462
Input
567
Total output
564
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
262
Input
549
Total output
546
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
154
Input
433
Total output
429
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
96
Input
367
Total output
363
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
118
Input
347
Total output
340
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
94
Input
405
Total output
404
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
129
Input
358
Total output
351
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
100
Input
378
Total output
374
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
129
Input
507
Total output
497
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
106
Input
341
Total output
334
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
118
Input
477
Total output
468
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
75
Input
292
Total output
291
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
114
Input
389
Total output
384
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
66
Input
254
Total output
253
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
158
Input
420
Total output
408
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
95
Input
274
Total output
270
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
114
Input
270
Total output
263
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
84
Input
818
Total output
815
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
164
Input
1,033
Total output
1,009
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
156
Input
570
Total output
550
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
143
Input
1,132
Total output
1,110
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
135
Input
436
Total output
426
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
124
Input
273
Total output
267
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
105
Input
315
Total output
310
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
232
Input
1,130
Total output
1,100
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
165
Input
641
Total output
618
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
285
Input
1,820
Total output
1,773
Reasoning within output
commit_messages f001
96%
Passed
Tokens
112
Input
433
Total output
429
Reasoning within output
commit_messages f002
85.3%
Passed
Tokens
245
Input
464
Total output
451
Reasoning within output
commit_messages f003
95%
Passed
Tokens
83
Input
364
Total output
354
Reasoning within output
commit_messages f004
97%
Passed
Tokens
118
Input
343
Total output
339
Reasoning within output
commit_messages f005
91.7%
Passed
Tokens
110
Input
352
Total output
346
Reasoning within output
commit_messages f006
86.7%
Passed
Tokens
151
Input
403
Total output
397
Reasoning within output
commit_messages f007
91.7%
Passed
Tokens
209
Input
348
Total output
342
Reasoning within output
commit_messages f008
91%
Passed
Tokens
76
Input
297
Total output
292
Reasoning within output
commit_messages f009
90%
Passed
Tokens
133
Input
588
Total output
581
Reasoning within output
commit_messages f010
92.7%
Passed
Tokens
332
Input
451
Total output
444
Reasoning within output
commit_messages f011
65%
Passed
Tokens
153
Input
755
Total output
743
Reasoning within output
commit_messages f012
92%
Passed
Tokens
131
Input
340
Total output
335
Reasoning within output
commit_squash f001
50%
Failed
Tokens
135
Input
4,890
Total output
4,885
Reasoning within output
commit_squash f002
100%
Passed
Tokens
117
Input
293
Total output
284
Reasoning within output
commit_squash f003
100%
Passed
Tokens
123
Input
3,521
Total output
3,508
Reasoning within output
commit_squash f004
100%
Passed
Tokens
110
Input
522
Total output
511
Reasoning within output
commit_squash f005
100%
Passed
Tokens
113
Input
2,071
Total output
2,064
Reasoning within output
commit_squash f006
100%
Passed
Tokens
96
Input
382
Total output
371
Reasoning within output
commit_squash f007
100%
Passed
Tokens
99
Input
639
Total output
627
Reasoning within output
commit_squash f008
100%
Passed
Tokens
110
Input
709
Total output
697
Reasoning within output
commit_squash f009
100%
Passed
Tokens
100
Input
1,869
Total output
1,858
Reasoning within output
commit_squash f010
100%
Passed
Tokens
120
Input
2,771
Total output
2,756
Reasoning within output
commit_squash f011
100%
Passed
Tokens
124
Input
4,423
Total output
4,408
Reasoning within output
commit_squash f012
100%
Passed
Tokens
124
Input
507
Total output
487
Reasoning within output
git_bisect f001
100%
Passed
Tokens
179
Input
244
Total output
236
Reasoning within output
git_bisect f002
100%
Passed
Tokens
209
Input
311
Total output
298
Reasoning within output
git_bisect f003
100%
Passed
Tokens
208
Input
301
Total output
282
Reasoning within output
git_bisect f004
100%
Passed
Tokens
212
Input
254
Total output
249
Reasoning within output
git_bisect f005
100%
Passed
Tokens
207
Input
263
Total output
243
Reasoning within output
git_bisect f006
100%
Passed
Tokens
241
Input
284
Total output
260
Reasoning within output
git_bisect f007
100%
Passed
Tokens
211
Input
350
Total output
343
Reasoning within output
git_bisect f008
100%
Passed
Tokens
212
Input
339
Total output
333
Reasoning within output
git_bisect f009
100%
Passed
Tokens
216
Input
248
Total output
227
Reasoning within output
git_bisect f010
100%
Passed
Tokens
218
Input
292
Total output
285
Reasoning within output
git_bisect f011
100%
Passed
Tokens
211
Input
230
Total output
224
Reasoning within output
git_bisect f012
100%
Passed
Tokens
242
Input
276
Total output
255
Reasoning within output
git_clean f001
100%
Passed
Tokens
51
Input
672
Total output
663
Reasoning within output
git_clean f002
100%
Passed
Tokens
62
Input
271
Total output
267
Reasoning within output
git_clean f003
100%
Passed
Tokens
62
Input
291
Total output
287
Reasoning within output
git_clean f004
100%
Passed
Tokens
63
Input
398
Total output
393
Reasoning within output
git_clean f005
100%
Passed
Tokens
49
Input
515
Total output
511
Reasoning within output
git_clean f006
100%
Passed
Tokens
80
Input
481
Total output
475
Reasoning within output
git_clean f007
100%
Passed
Tokens
69
Input
328
Total output
319
Reasoning within output
git_clean f008
100%
Passed
Tokens
78
Input
245
Total output
241
Reasoning within output
git_clean f009
100%
Passed
Tokens
74
Input
1,258
Total output
1,250
Reasoning within output
git_clean f010
100%
Passed
Tokens
65
Input
464
Total output
460
Reasoning within output
git_clean f011
100%
Passed
Tokens
64
Input
470
Total output
465
Reasoning within output
git_clean f012
100%
Passed
Tokens
70
Input
547
Total output
540
Reasoning within output
git_grep f001
100%
Passed
Tokens
48
Input
254
Total output
249
Reasoning within output
git_grep f002
100%
Passed
Tokens
59
Input
174
Total output
173
Reasoning within output
git_grep f003
100%
Passed
Tokens
100
Input
208
Total output
207
Reasoning within output
git_grep f004
100%
Passed
Tokens
77
Input
380
Total output
375
Reasoning within output
git_grep f005
100%
Passed
Tokens
115
Input
258
Total output
257
Reasoning within output
git_grep f006
100%
Passed
Tokens
33
Input
457
Total output
456
Reasoning within output
git_grep f007
100%
Passed
Tokens
176
Input
550
Total output
548
Reasoning within output
git_grep f008
100%
Passed
Tokens
56
Input
196
Total output
195
Reasoning within output
git_grep f009
100%
Passed
Tokens
49
Input
234
Total output
231
Reasoning within output
git_grep f010
100%
Passed
Tokens
64
Input
143
Total output
142
Reasoning within output
git_grep f011
100%
Passed
Tokens
127
Input
321
Total output
320
Reasoning within output
git_grep f012
100%
Passed
Tokens
65
Input
261
Total output
248
Reasoning within output
git_log_format f001
100%
Passed
Tokens
920
Input
236
Total output
235
Reasoning within output
git_log_format f002
100%
Passed
Tokens
903
Input
414
Total output
407
Reasoning within output
git_log_format f003
100%
Passed
Tokens
740
Input
347
Total output
338
Reasoning within output
git_log_format f004
100%
Passed
Tokens
935
Input
398
Total output
397
Reasoning within output
git_log_format f005
100%
Passed
Tokens
746
Input
810
Total output
805
Reasoning within output
git_log_format f006
100%
Passed
Tokens
935
Input
526
Total output
525
Reasoning within output
git_log_format f007
100%
Passed
Tokens
925
Input
268
Total output
261
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,243
Input
301
Total output
300
Reasoning within output
git_log_format f009
100%
Passed
Tokens
757
Input
300
Total output
299
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,458
Input
107
Total output
106
Reasoning within output
git_log_format f011
100%
Passed
Tokens
456
Input
320
Total output
317
Reasoning within output
git_log_format f012
100%
Passed
Tokens
396
Input
247
Total output
246
Reasoning within output
git_show f001
100%
Passed
Tokens
199
Input
278
Total output
273
Reasoning within output
git_show f002
100%
Passed
Tokens
206
Input
624
Total output
621
Reasoning within output
git_show f003
100%
Passed
Tokens
727
Input
310
Total output
304
Reasoning within output
git_show f004
100%
Passed
Tokens
479
Input
302
Total output
295
Reasoning within output
git_show f005
100%
Passed
Tokens
209
Input
399
Total output
397
Reasoning within output
git_show f006
100%
Passed
Tokens
218
Input
294
Total output
293
Reasoning within output
git_show f007
100%
Passed
Tokens
204
Input
303
Total output
298
Reasoning within output
git_show f008
100%
Passed
Tokens
209
Input
358
Total output
324
Reasoning within output
git_show f009
100%
Passed
Tokens
321
Input
419
Total output
418
Reasoning within output
git_show f010
100%
Passed
Tokens
200
Input
463
Total output
462
Reasoning within output
git_show f011
100%
Passed
Tokens
234
Input
286
Total output
283
Reasoning within output
git_show f012
100%
Passed
Tokens
363
Input
411
Total output
410
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
82
Input
397
Total output
393
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
100
Input
494
Total output
487
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
73
Input
1,405
Total output
1,402
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
150
Input
3,384
Total output
3,358
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
141
Input
510
Total output
490
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
127
Input
766
Total output
744
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
136
Input
402
Total output
392
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
108
Input
338
Total output
332
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
100
Input
406
Total output
401
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
191
Input
1,211
Total output
1,181
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
143
Input
417
Total output
394
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
248
Input
2,878
Total output
2,831
Reasoning within output
rebase f001
100%
Passed
Tokens
97
Input
473
Total output
469
Reasoning within output
rebase f002
100%
Passed
Tokens
121
Input
368
Total output
361
Reasoning within output
rebase f003
100%
Passed
Tokens
99
Input
456
Total output
453
Reasoning within output
rebase f004
100%
Passed
Tokens
165
Input
6,850
Total output
6,824
Reasoning within output
rebase f005
100%
Passed
Tokens
147
Input
616
Total output
600
Reasoning within output
rebase f006
100%
Passed
Tokens
141
Input
494
Total output
472
Reasoning within output
rebase f007
100%
Passed
Tokens
138
Input
391
Total output
381
Reasoning within output
rebase f008
100%
Passed
Tokens
120
Input
339
Total output
333
Reasoning within output
rebase f009
100%
Passed
Tokens
99
Input
309
Total output
304
Reasoning within output
rebase f010
100%
Passed
Tokens
224
Input
1,915
Total output
1,885
Reasoning within output
rebase f011
100%
Passed
Tokens
154
Input
1,005
Total output
982
Reasoning within output
rebase f012
0%
Failed
Tokens
284
Input
3,562
Total output
3,515
Reasoning within output
reflog f001
100%
Passed
Tokens
250
Input
800
Total output
764
Reasoning within output
reflog f002
100%
Passed
Tokens
236
Input
675
Total output
533
Reasoning within output
reflog f003
100%
Passed
Tokens
199
Input
586
Total output
428
Reasoning within output
reflog f004
100%
Passed
Tokens
343
Input
2,129
Total output
1,725
Reasoning within output
reflog f005
100%
Passed
Tokens
405
Input
787
Total output
645
Reasoning within output
reflog f006
100%
Passed
Tokens
251
Input
887
Total output
675
Reasoning within output
reflog f007
100%
Passed
Tokens
286
Input
771
Total output
591
Reasoning within output
reflog f008
100%
Passed
Tokens
380
Input
982
Total output
780
Reasoning within output
reflog f009
100%
Passed
Tokens
350
Input
1,480
Total output
1,245
Reasoning within output
reflog f010
100%
Passed
Tokens
293
Input
1,117
Total output
915
Reasoning within output
reflog f011
100%
Passed
Tokens
345
Input
1,808
Total output
1,476
Reasoning within output
reflog f012
100%
Passed
Tokens
332
Input
1,339
Total output
1,040
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
137
Input
250
Total output
245
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
311
Input
547
Total output
447
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
128
Input
195
Total output
181
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
121
Input
218
Total output
197
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
130
Input
386
Total output
331
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
196
Input
211
Total output
197
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
219
Input
270
Total output
255
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
193
Input
254
Total output
240
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
223
Input
319
Total output
273
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
128
Input
190
Total output
176
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
123
Input
267
Total output
250
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
143
Input
197
Total output
183
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
36
Input
293
Total output
285
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
97
Input
941
Total output
934
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
112
Input
832
Total output
809
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
91
Input
249
Total output
246
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
43
Input
923
Total output
901
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
95
Input
829
Total output
826
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
44
Input
419
Total output
402
Reasoning within output
submodule_usage f008
33.3%
Failed
Tokens
101
Input
443
Total output
434
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
93
Input
197
Total output
194
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
102
Input
418
Total output
413
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
110
Input
214
Total output
210
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
41
Input
302
Total output
291
Reasoning within output
tag_management f001
100%
Passed
Tokens
56
Input
182
Total output
176
Reasoning within output
tag_management f002
100%
Passed
Tokens
52
Input
391
Total output
374
Reasoning within output
tag_management f003
100%
Passed
Tokens
60
Input
244
Total output
234
Reasoning within output
tag_management f004
100%
Passed
Tokens
65
Input
198
Total output
196
Reasoning within output
tag_management f005
100%
Passed
Tokens
78
Input
256
Total output
249
Reasoning within output
tag_management f006
100%
Passed
Tokens
65
Input
308
Total output
294
Reasoning within output
tag_management f007
100%
Passed
Tokens
58
Input
841
Total output
830
Reasoning within output
tag_management f008
100%
Passed
Tokens
64
Input
509
Total output
486
Reasoning within output
tag_management f009
100%
Passed
Tokens
68
Input
505
Total output
489
Reasoning within output
tag_management f010
100%
Passed
Tokens
46
Input
233
Total output
226
Reasoning within output
tag_management f011
100%
Passed
Tokens
46
Input
227
Total output
222
Reasoning within output
tag_management f012
100%
Passed
Tokens
86
Input
529
Total output
520
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
150
Input
279
Total output
270
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
158
Input
720
Total output
697
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
240
Input
254
Total output
246
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
232
Input
130
Total output
126
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
143
Input
317
Total output
304
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
143
Input
422
Total output
409
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
149
Input
810
Total output
787
Reasoning within output
worktree_usage f008
100%
Passed
Tokens
167
Input
1,802
Total output
1,750
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
268
Input
254
Total output
250
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
235
Input
235
Total output
220
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
236
Input
207
Total output
199
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
139
Input
276
Total output
263
Reasoning within output