Google / gemini-3.5-flash
medium
97.1%
198 / 204 fixtures · 1 run(s)
40,550 input / 108,274 total output / 103,802 reasoning within output tokens $1.03529100
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% |
| cherry_pick | 91.7% | 83.3% | -8.3% |
| rebase | 91.7% | 83.3% | -8.3% |
| commit_squash | 100% | 91.7% | -8.3% |
| blame_forensics | 91.7% | 91.7% | + 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 | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
| worktree_usage | 83.3% | 83.3% | + 0% |
Changed Fixtures (6)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
262
Input
822
Total output
818
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
254
Input
735
Total output
731
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
294
Input
399
Total output
393
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
206
Input
408
Total output
403
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
268
Input
1,773
Total output
1,768
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
246
Input
560
Total output
557
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
216
Input
447
Total output
443
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
257
Input
498
Total output
495
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
209
Input
475
Total output
472
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
458
Input
511
Total output
508
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
268
Input
493
Total output
490
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
152
Input
740
Total output
736
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
102
Input
350
Total output
346
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
120
Input
433
Total output
426
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
93
Input
370
Total output
369
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
130
Input
560
Total output
553
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
106
Input
397
Total output
393
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
128
Input
379
Total output
369
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
99
Input
335
Total output
328
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
116
Input
510
Total output
501
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
77
Input
296
Total output
295
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
111
Input
413
Total output
408
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
64
Input
238
Total output
237
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
157
Input
526
Total output
514
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
93
Input
560
Total output
556
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
113
Input
549
Total output
542
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
85
Input
735
Total output
732
Reasoning within output
cherry_pick f004
100%
Passed
Tokens
163
Input
978
Total output
952
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
154
Input
473
Total output
453
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
141
Input
515
Total output
493
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
133
Input
569
Total output
559
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
124
Input
337
Total output
331
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
105
Input
352
Total output
347
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
231
Input
1,046
Total output
1,016
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
164
Input
390
Total output
367
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
286
Input
1,733
Total output
1,676
Reasoning within output
commit_messages f001
93.3%
Passed
Tokens
112
Input
411
Total output
407
Reasoning within output
commit_messages f002
76.7%
Passed
Tokens
245
Input
495
Total output
482
Reasoning within output
commit_messages f003
94.3%
Passed
Tokens
83
Input
304
Total output
294
Reasoning within output
commit_messages f004
90%
Passed
Tokens
118
Input
280
Total output
276
Reasoning within output
commit_messages f005
80%
Passed
Tokens
109
Input
338
Total output
333
Reasoning within output
commit_messages f006
87.7%
Passed
Tokens
151
Input
494
Total output
488
Reasoning within output
commit_messages f007
91%
Passed
Tokens
209
Input
326
Total output
320
Reasoning within output
commit_messages f008
92.7%
Passed
Tokens
76
Input
543
Total output
538
Reasoning within output
commit_messages f009
85%
Passed
Tokens
133
Input
679
Total output
673
Reasoning within output
commit_messages f010
89.3%
Passed
Tokens
332
Input
356
Total output
349
Reasoning within output
commit_messages f011
64.7%
Passed
Tokens
153
Input
1,203
Total output
1,190
Reasoning within output
commit_messages f012
88.3%
Passed
Tokens
130
Input
359
Total output
354
Reasoning within output
commit_squash f001
100%
Passed
Tokens
133
Input
2,253
Total output
2,240
Reasoning within output
commit_squash f002
100%
Passed
Tokens
113
Input
319
Total output
310
Reasoning within output
commit_squash f003
100%
Passed
Tokens
123
Input
643
Total output
630
Reasoning within output
commit_squash f004
100%
Passed
Tokens
112
Input
500
Total output
489
Reasoning within output
commit_squash f005
100%
Passed
Tokens
111
Input
2,116
Total output
2,109
Reasoning within output
commit_squash f006
100%
Passed
Tokens
97
Input
428
Total output
417
Reasoning within output
commit_squash f007
100%
Passed
Tokens
99
Input
598
Total output
586
Reasoning within output
commit_squash f008
100%
Passed
Tokens
110
Input
613
Total output
601
Reasoning within output
commit_squash f009
100%
Passed
Tokens
100
Input
886
Total output
875
Reasoning within output
commit_squash f010
100%
Passed
Tokens
119
Input
387
Total output
372
Reasoning within output
commit_squash f011
100%
Passed
Tokens
123
Input
378
Total output
363
Reasoning within output
commit_squash f012
100%
Passed
Tokens
122
Input
507
Total output
487
Reasoning within output
git_bisect f001
100%
Passed
Tokens
185
Input
248
Total output
227
Reasoning within output
git_bisect f002
100%
Passed
Tokens
215
Input
194
Total output
187
Reasoning within output
git_bisect f003
100%
Passed
Tokens
199
Input
190
Total output
173
Reasoning within output
git_bisect f004
100%
Passed
Tokens
215
Input
192
Total output
186
Reasoning within output
git_bisect f005
100%
Passed
Tokens
217
Input
359
Total output
352
Reasoning within output
git_bisect f006
100%
Passed
Tokens
231
Input
260
Total output
254
Reasoning within output
git_bisect f007
100%
Passed
Tokens
205
Input
177
Total output
146
Reasoning within output
git_bisect f008
100%
Passed
Tokens
215
Input
333
Total output
327
Reasoning within output
git_bisect f009
100%
Passed
Tokens
207
Input
200
Total output
179
Reasoning within output
git_bisect f010
100%
Passed
Tokens
211
Input
211
Total output
205
Reasoning within output
git_bisect f011
100%
Passed
Tokens
215
Input
251
Total output
244
Reasoning within output
git_bisect f012
100%
Passed
Tokens
239
Input
221
Total output
214
Reasoning within output
git_clean f001
100%
Passed
Tokens
50
Input
408
Total output
404
Reasoning within output
git_clean f002
100%
Passed
Tokens
62
Input
498
Total output
494
Reasoning within output
git_clean f003
100%
Passed
Tokens
62
Input
297
Total output
293
Reasoning within output
git_clean f004
100%
Passed
Tokens
62
Input
543
Total output
538
Reasoning within output
git_clean f005
100%
Passed
Tokens
49
Input
411
Total output
407
Reasoning within output
git_clean f006
100%
Passed
Tokens
80
Input
642
Total output
636
Reasoning within output
git_clean f007
100%
Passed
Tokens
69
Input
382
Total output
373
Reasoning within output
git_clean f008
100%
Passed
Tokens
77
Input
317
Total output
313
Reasoning within output
git_clean f009
100%
Passed
Tokens
73
Input
448
Total output
440
Reasoning within output
git_clean f010
100%
Passed
Tokens
64
Input
315
Total output
311
Reasoning within output
git_clean f011
100%
Passed
Tokens
64
Input
476
Total output
471
Reasoning within output
git_clean f012
100%
Passed
Tokens
69
Input
476
Total output
469
Reasoning within output
git_grep f001
100%
Passed
Tokens
48
Input
234
Total output
229
Reasoning within output
git_grep f002
100%
Passed
Tokens
60
Input
199
Total output
198
Reasoning within output
git_grep f003
100%
Passed
Tokens
100
Input
285
Total output
284
Reasoning within output
git_grep f004
100%
Passed
Tokens
76
Input
361
Total output
356
Reasoning within output
git_grep f005
100%
Passed
Tokens
114
Input
304
Total output
303
Reasoning within output
git_grep f006
100%
Passed
Tokens
33
Input
237
Total output
236
Reasoning within output
git_grep f007
100%
Passed
Tokens
176
Input
612
Total output
610
Reasoning within output
git_grep f008
100%
Passed
Tokens
56
Input
233
Total output
232
Reasoning within output
git_grep f009
100%
Passed
Tokens
49
Input
232
Total output
229
Reasoning within output
git_grep f010
100%
Passed
Tokens
63
Input
213
Total output
212
Reasoning within output
git_grep f011
100%
Passed
Tokens
126
Input
340
Total output
339
Reasoning within output
git_grep f012
100%
Passed
Tokens
64
Input
307
Total output
294
Reasoning within output
git_log_format f001
100%
Passed
Tokens
907
Input
285
Total output
284
Reasoning within output
git_log_format f002
100%
Passed
Tokens
885
Input
273
Total output
266
Reasoning within output
git_log_format f003
100%
Passed
Tokens
746
Input
338
Total output
329
Reasoning within output
git_log_format f004
100%
Passed
Tokens
901
Input
539
Total output
538
Reasoning within output
git_log_format f005
100%
Passed
Tokens
746
Input
476
Total output
471
Reasoning within output
git_log_format f006
100%
Passed
Tokens
934
Input
628
Total output
627
Reasoning within output
git_log_format f007
100%
Passed
Tokens
943
Input
234
Total output
227
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,244
Input
208
Total output
207
Reasoning within output
git_log_format f009
100%
Passed
Tokens
744
Input
193
Total output
192
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,431
Input
339
Total output
338
Reasoning within output
git_log_format f011
100%
Passed
Tokens
437
Input
302
Total output
299
Reasoning within output
git_log_format f012
100%
Passed
Tokens
389
Input
268
Total output
267
Reasoning within output
git_show f001
100%
Passed
Tokens
197
Input
204
Total output
199
Reasoning within output
git_show f002
100%
Passed
Tokens
202
Input
426
Total output
423
Reasoning within output
git_show f003
100%
Passed
Tokens
725
Input
441
Total output
435
Reasoning within output
git_show f004
100%
Passed
Tokens
474
Input
264
Total output
257
Reasoning within output
git_show f005
100%
Passed
Tokens
209
Input
319
Total output
317
Reasoning within output
git_show f006
100%
Passed
Tokens
214
Input
288
Total output
287
Reasoning within output
git_show f007
100%
Passed
Tokens
203
Input
310
Total output
305
Reasoning within output
git_show f008
100%
Passed
Tokens
210
Input
409
Total output
372
Reasoning within output
git_show f009
100%
Passed
Tokens
314
Input
439
Total output
438
Reasoning within output
git_show f010
100%
Passed
Tokens
205
Input
438
Total output
437
Reasoning within output
git_show f011
100%
Passed
Tokens
227
Input
222
Total output
219
Reasoning within output
git_show f012
100%
Passed
Tokens
356
Input
246
Total output
245
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
82
Input
453
Total output
449
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
100
Input
725
Total output
718
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
73
Input
594
Total output
591
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
150
Input
1,177
Total output
1,151
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
140
Input
487
Total output
467
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
126
Input
517
Total output
495
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
136
Input
361
Total output
351
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
107
Input
333
Total output
327
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
99
Input
491
Total output
486
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
190
Input
977
Total output
947
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
143
Input
521
Total output
498
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
247
Input
2,404
Total output
2,357
Reasoning within output
rebase f001
100%
Passed
Tokens
93
Input
613
Total output
609
Reasoning within output
rebase f002
100%
Passed
Tokens
119
Input
396
Total output
389
Reasoning within output
rebase f003
100%
Passed
Tokens
100
Input
463
Total output
460
Reasoning within output
rebase f004
100%
Passed
Tokens
165
Input
1,428
Total output
1,402
Reasoning within output
rebase f005
100%
Passed
Tokens
148
Input
529
Total output
513
Reasoning within output
rebase f006
100%
Passed
Tokens
141
Input
922
Total output
900
Reasoning within output
rebase f007
100%
Passed
Tokens
138
Input
549
Total output
539
Reasoning within output
rebase f008
100%
Passed
Tokens
120
Input
461
Total output
455
Reasoning within output
rebase f009
100%
Passed
Tokens
101
Input
514
Total output
509
Reasoning within output
rebase f010
100%
Passed
Tokens
221
Input
1,020
Total output
990
Reasoning within output
rebase f011
100%
Passed
Tokens
154
Input
624
Total output
601
Reasoning within output
rebase f012
0%
Failed
Tokens
284
Input
3,371
Total output
3,324
Reasoning within output
reflog f001
100%
Passed
Tokens
246
Input
604
Total output
570
Reasoning within output
reflog f002
100%
Passed
Tokens
229
Input
647
Total output
533
Reasoning within output
reflog f003
100%
Passed
Tokens
198
Input
589
Total output
432
Reasoning within output
reflog f004
100%
Passed
Tokens
349
Input
1,351
Total output
1,027
Reasoning within output
reflog f005
100%
Passed
Tokens
416
Input
888
Total output
744
Reasoning within output
reflog f006
100%
Passed
Tokens
257
Input
727
Total output
454
Reasoning within output
reflog f007
100%
Passed
Tokens
283
Input
783
Total output
582
Reasoning within output
reflog f008
100%
Passed
Tokens
381
Input
772
Total output
608
Reasoning within output
reflog f009
100%
Passed
Tokens
329
Input
1,350
Total output
1,102
Reasoning within output
reflog f010
100%
Passed
Tokens
292
Input
938
Total output
703
Reasoning within output
reflog f011
100%
Passed
Tokens
337
Input
1,941
Total output
1,616
Reasoning within output
reflog f012
100%
Passed
Tokens
328
Input
1,871
Total output
1,600
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
136
Input
244
Total output
222
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
310
Input
275
Total output
258
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
127
Input
188
Total output
171
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
120
Input
183
Total output
162
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
131
Input
313
Total output
293
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
196
Input
250
Total output
233
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
220
Input
215
Total output
199
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
192
Input
239
Total output
222
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
222
Input
409
Total output
358
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
128
Input
260
Total output
243
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
121
Input
304
Total output
285
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
143
Input
338
Total output
324
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
36
Input
293
Total output
285
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
98
Input
1,001
Total output
994
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
108
Input
828
Total output
805
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
94
Input
250
Total output
247
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
43
Input
896
Total output
871
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
92
Input
755
Total output
753
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
43
Input
346
Total output
329
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
97
Input
427
Total output
422
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
96
Input
230
Total output
227
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
103
Input
476
Total output
471
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
109
Input
162
Total output
158
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
41
Input
254
Total output
243
Reasoning within output
tag_management f001
100%
Passed
Tokens
57
Input
240
Total output
234
Reasoning within output
tag_management f002
100%
Passed
Tokens
52
Input
386
Total output
369
Reasoning within output
tag_management f003
100%
Passed
Tokens
62
Input
276
Total output
266
Reasoning within output
tag_management f004
100%
Passed
Tokens
68
Input
325
Total output
323
Reasoning within output
tag_management f005
100%
Passed
Tokens
79
Input
331
Total output
324
Reasoning within output
tag_management f006
100%
Passed
Tokens
65
Input
277
Total output
263
Reasoning within output
tag_management f007
100%
Passed
Tokens
59
Input
591
Total output
580
Reasoning within output
tag_management f008
100%
Passed
Tokens
63
Input
826
Total output
803
Reasoning within output
tag_management f009
100%
Passed
Tokens
67
Input
238
Total output
222
Reasoning within output
tag_management f010
100%
Passed
Tokens
44
Input
195
Total output
188
Reasoning within output
tag_management f011
100%
Passed
Tokens
46
Input
326
Total output
321
Reasoning within output
tag_management f012
100%
Passed
Tokens
87
Input
624
Total output
615
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
148
Input
245
Total output
236
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
154
Input
672
Total output
649
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
230
Input
247
Total output
239
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
226
Input
122
Total output
118
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
143
Input
367
Total output
354
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
141
Input
800
Total output
787
Reasoning within output
worktree_usage f007
0%
Failed
Tokens
150
Input
454
Total output
427
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
169
Input
2,051
Total output
2,008
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
264
Input
251
Total output
247
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
232
Input
254
Total output
239
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
235
Input
324
Total output
316
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
140
Input
309
Total output
296
Reasoning within output