Google / gemini-3.8-flash
xhigh
95.1%
194 / 204 fixtures · 1 run(s)
40,158 input / 319,829 total output / 310,363 reasoning within output tokens $1.21011450
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-2%
Text: 95.1% →
JSON: 93.1%
+5
Gained
JSON pass / text fail
−9
Lost
Text pass / JSON fail
185
Unchanged Pass
Both pass
5
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| branch_cleanup | 100% | 75% | -25% |
| commit_squash | 75% | 100% | + 25% |
| merge_conflicts | 91.7% | 75% | -16.7% |
| blame_forensics | 91.7% | 83.3% | -8.3% |
| rebase | 83.3% | 91.7% | + 8.3% |
| cherry_pick | 83.3% | 75% | -8.3% |
| git_grep | 100% | 91.7% | -8.3% |
| git_show | 91.7% | 100% | + 8.3% |
| reflog | 100% | 91.7% | -8.3% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_clean | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
| worktree_usage | 100% | 100% | + 0% |
Changed Fixtures (14)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
261
Input
588
Total output
584
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
257
Input
339
Total output
335
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
292
Input
381
Total output
375
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
203
Input
308
Total output
303
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
271
Input
3,298
Total output
3,293
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
248
Input
700
Total output
697
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
220
Input
462
Total output
458
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
265
Input
546
Total output
543
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
211
Input
401
Total output
398
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
458
Input
219
Total output
216
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
264
Input
270
Total output
267
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
151
Input
424
Total output
420
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
98
Input
297
Total output
293
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
116
Input
377
Total output
370
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
94
Input
306
Total output
305
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
127
Input
387
Total output
380
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
106
Input
341
Total output
337
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
127
Input
327
Total output
317
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
101
Input
289
Total output
282
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
117
Input
429
Total output
420
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
76
Input
265
Total output
264
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
112
Input
292
Total output
287
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
65
Input
236
Total output
235
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
158
Input
303
Total output
291
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
95
Input
358
Total output
354
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
111
Input
894
Total output
887
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
83
Input
1,229
Total output
1,226
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
164
Input
2,340
Total output
2,316
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
153
Input
4,851
Total output
4,831
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
140
Input
1,466
Total output
1,444
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
133
Input
417
Total output
407
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
126
Input
253
Total output
247
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
104
Input
193
Total output
188
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
229
Input
3,244
Total output
3,214
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
163
Input
603
Total output
580
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
282
Input
4,770
Total output
4,723
Reasoning within output
commit_messages f001
82.5%
Passed
Tokens
112
Input
628
Total output
620
Reasoning within output
commit_messages f002
87.5%
Passed
Tokens
245
Input
509
Total output
501
Reasoning within output
commit_messages f003
92.5%
Passed
Tokens
83
Input
364
Total output
354
Reasoning within output
commit_messages f004
94%
Passed
Tokens
118
Input
331
Total output
327
Reasoning within output
commit_messages f005
80%
Passed
Tokens
109
Input
322
Total output
316
Reasoning within output
commit_messages f006
85%
Passed
Tokens
151
Input
433
Total output
427
Reasoning within output
commit_messages f007
92.5%
Passed
Tokens
209
Input
374
Total output
368
Reasoning within output
commit_messages f008
87.5%
Passed
Tokens
76
Input
252
Total output
247
Reasoning within output
commit_messages f009
87.5%
Passed
Tokens
133
Input
651
Total output
644
Reasoning within output
commit_messages f010
90%
Passed
Tokens
332
Input
462
Total output
456
Reasoning within output
commit_messages f011
72.5%
Passed
Tokens
153
Input
942
Total output
930
Reasoning within output
commit_messages f012
92.5%
Passed
Tokens
130
Input
353
Total output
348
Reasoning within output
commit_squash f001
100%
Passed
Tokens
135
Input
5,390
Total output
5,377
Reasoning within output
commit_squash f002
100%
Passed
Tokens
112
Input
342
Total output
333
Reasoning within output
commit_squash f003
0%
Failed
Tokens
122
Input
5,139
Total output
0
Reasoning within output
commit_squash f004
100%
Passed
Tokens
115
Input
748
Total output
737
Reasoning within output
commit_squash f005
50%
Failed
Tokens
108
Input
36,619
Total output
36,616
Reasoning within output
commit_squash f006
100%
Passed
Tokens
96
Input
514
Total output
503
Reasoning within output
commit_squash f007
100%
Passed
Tokens
100
Input
568
Total output
556
Reasoning within output
commit_squash f008
100%
Passed
Tokens
111
Input
578
Total output
566
Reasoning within output
commit_squash f009
100%
Passed
Tokens
104
Input
847
Total output
836
Reasoning within output
commit_squash f010
100%
Passed
Tokens
119
Input
307
Total output
292
Reasoning within output
commit_squash f011
0%
Failed
Tokens
0
Input
0
Total output
0
Reasoning within output
commit_squash f012
100%
Passed
Tokens
124
Input
505
Total output
485
Reasoning within output
git_bisect f001
100%
Passed
Tokens
181
Input
190
Total output
184
Reasoning within output
git_bisect f002
100%
Passed
Tokens
207
Input
181
Total output
176
Reasoning within output
git_bisect f003
100%
Passed
Tokens
205
Input
175
Total output
169
Reasoning within output
git_bisect f004
100%
Passed
Tokens
213
Input
213
Total output
207
Reasoning within output
git_bisect f005
100%
Passed
Tokens
211
Input
195
Total output
189
Reasoning within output
git_bisect f006
100%
Passed
Tokens
233
Input
203
Total output
197
Reasoning within output
git_bisect f007
100%
Passed
Tokens
211
Input
186
Total output
179
Reasoning within output
git_bisect f008
100%
Passed
Tokens
213
Input
251
Total output
245
Reasoning within output
git_bisect f009
100%
Passed
Tokens
207
Input
226
Total output
219
Reasoning within output
git_bisect f010
100%
Passed
Tokens
207
Input
160
Total output
155
Reasoning within output
git_bisect f011
100%
Passed
Tokens
209
Input
224
Total output
219
Reasoning within output
git_bisect f012
100%
Passed
Tokens
237
Input
222
Total output
215
Reasoning within output
git_clean f001
100%
Passed
Tokens
50
Input
309
Total output
305
Reasoning within output
git_clean f002
100%
Passed
Tokens
62
Input
133
Total output
129
Reasoning within output
git_clean f003
100%
Passed
Tokens
62
Input
252
Total output
248
Reasoning within output
git_clean f004
100%
Passed
Tokens
62
Input
414
Total output
409
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
423
Total output
417
Reasoning within output
git_clean f007
100%
Passed
Tokens
69
Input
349
Total output
340
Reasoning within output
git_clean f008
100%
Passed
Tokens
77
Input
245
Total output
241
Reasoning within output
git_clean f009
100%
Passed
Tokens
73
Input
8,955
Total output
8,943
Reasoning within output
git_clean f010
100%
Passed
Tokens
64
Input
656
Total output
652
Reasoning within output
git_clean f011
100%
Passed
Tokens
64
Input
423
Total output
418
Reasoning within output
git_clean f012
100%
Passed
Tokens
69
Input
316
Total output
309
Reasoning within output
git_grep f001
100%
Passed
Tokens
48
Input
167
Total output
162
Reasoning within output
git_grep f002
100%
Passed
Tokens
59
Input
207
Total output
206
Reasoning within output
git_grep f003
100%
Passed
Tokens
100
Input
195
Total output
194
Reasoning within output
git_grep f004
100%
Passed
Tokens
76
Input
309
Total output
304
Reasoning within output
git_grep f005
100%
Passed
Tokens
114
Input
260
Total output
259
Reasoning within output
git_grep f006
100%
Passed
Tokens
33
Input
345
Total output
344
Reasoning within output
git_grep f007
100%
Passed
Tokens
176
Input
1,579
Total output
1,577
Reasoning within output
git_grep f008
100%
Passed
Tokens
56
Input
206
Total output
205
Reasoning within output
git_grep f009
100%
Passed
Tokens
49
Input
179
Total output
176
Reasoning within output
git_grep f010
100%
Passed
Tokens
63
Input
135
Total output
134
Reasoning within output
git_grep f011
100%
Passed
Tokens
126
Input
213
Total output
212
Reasoning within output
git_grep f012
100%
Passed
Tokens
65
Input
218
Total output
205
Reasoning within output
git_log_format f001
100%
Passed
Tokens
928
Input
145
Total output
144
Reasoning within output
git_log_format f002
100%
Passed
Tokens
900
Input
400
Total output
393
Reasoning within output
git_log_format f003
100%
Passed
Tokens
731
Input
328
Total output
319
Reasoning within output
git_log_format f004
100%
Passed
Tokens
902
Input
122
Total output
121
Reasoning within output
git_log_format f005
100%
Passed
Tokens
746
Input
474
Total output
469
Reasoning within output
git_log_format f006
100%
Passed
Tokens
934
Input
341
Total output
340
Reasoning within output
git_log_format f007
100%
Passed
Tokens
938
Input
208
Total output
201
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,260
Input
133
Total output
132
Reasoning within output
git_log_format f009
100%
Passed
Tokens
741
Input
100
Total output
99
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,418
Input
127
Total output
126
Reasoning within output
git_log_format f011
100%
Passed
Tokens
442
Input
331
Total output
328
Reasoning within output
git_log_format f012
100%
Passed
Tokens
397
Input
355
Total output
354
Reasoning within output
git_show f001
100%
Passed
Tokens
198
Input
200
Total output
195
Reasoning within output
git_show f002
100%
Passed
Tokens
207
Input
1,166
Total output
1,163
Reasoning within output
git_show f003
100%
Passed
Tokens
723
Input
177
Total output
171
Reasoning within output
git_show f004
100%
Passed
Tokens
486
Input
163
Total output
156
Reasoning within output
git_show f005
100%
Passed
Tokens
208
Input
250
Total output
248
Reasoning within output
git_show f006
0%
Failed
Tokens
0
Input
0
Total output
0
Reasoning within output
git_show f007
100%
Passed
Tokens
203
Input
252
Total output
247
Reasoning within output
git_show f008
100%
Passed
Tokens
212
Input
297
Total output
258
Reasoning within output
git_show f009
100%
Passed
Tokens
327
Input
322
Total output
321
Reasoning within output
git_show f010
100%
Passed
Tokens
202
Input
352
Total output
351
Reasoning within output
git_show f011
100%
Passed
Tokens
232
Input
192
Total output
189
Reasoning within output
git_show f012
100%
Passed
Tokens
364
Input
224
Total output
223
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
82
Input
522
Total output
518
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
100
Input
1,580
Total output
1,573
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
73
Input
1,319
Total output
1,316
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
150
Input
1,288
Total output
1,262
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
140
Input
699
Total output
678
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
126
Input
1,216
Total output
1,194
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
136
Input
303
Total output
293
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
1,418
Total output
1,413
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
190
Input
1,775
Total output
1,745
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
143
Input
470
Total output
447
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
247
Input
42,945
Total output
42,898
Reasoning within output
rebase f001
100%
Passed
Tokens
96
Input
659
Total output
655
Reasoning within output
rebase f002
100%
Passed
Tokens
121
Input
268
Total output
261
Reasoning within output
rebase f003
100%
Passed
Tokens
99
Input
294
Total output
291
Reasoning within output
rebase f004
100%
Passed
Tokens
164
Input
5,163
Total output
5,137
Reasoning within output
rebase f005
100%
Passed
Tokens
147
Input
2,931
Total output
2,915
Reasoning within output
rebase f006
100%
Passed
Tokens
142
Input
896
Total output
874
Reasoning within output
rebase f007
100%
Passed
Tokens
138
Input
332
Total output
322
Reasoning within output
rebase f008
100%
Passed
Tokens
120
Input
459
Total output
453
Reasoning within output
rebase f009
100%
Passed
Tokens
99
Input
293
Total output
288
Reasoning within output
rebase f010
100%
Passed
Tokens
223
Input
4,013
Total output
3,983
Reasoning within output
rebase f011
0%
Failed
Tokens
0
Input
0
Total output
0
Reasoning within output
rebase f012
0%
Failed
Tokens
280
Input
33,868
Total output
33,821
Reasoning within output
reflog f001
100%
Passed
Tokens
242
Input
624
Total output
588
Reasoning within output
reflog f002
100%
Passed
Tokens
246
Input
585
Total output
461
Reasoning within output
reflog f003
100%
Passed
Tokens
205
Input
556
Total output
418
Reasoning within output
reflog f004
100%
Passed
Tokens
352
Input
1,620
Total output
1,339
Reasoning within output
reflog f005
100%
Passed
Tokens
407
Input
684
Total output
562
Reasoning within output
reflog f006
100%
Passed
Tokens
249
Input
809
Total output
529
Reasoning within output
reflog f007
100%
Passed
Tokens
292
Input
692
Total output
510
Reasoning within output
reflog f008
100%
Passed
Tokens
378
Input
863
Total output
622
Reasoning within output
reflog f009
100%
Passed
Tokens
329
Input
1,484
Total output
1,259
Reasoning within output
reflog f010
100%
Passed
Tokens
280
Input
1,044
Total output
833
Reasoning within output
reflog f011
100%
Passed
Tokens
345
Input
1,966
Total output
1,603
Reasoning within output
reflog f012
100%
Passed
Tokens
338
Input
1,405
Total output
1,092
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
133
Input
238
Total output
234
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
313
Input
268
Total output
255
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
127
Input
146
Total output
132
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
120
Input
232
Total output
214
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
129
Input
366
Total output
322
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
196
Input
174
Total output
161
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
220
Input
196
Total output
181
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
192
Input
213
Total output
198
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
222
Input
343
Total output
298
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
128
Input
193
Total output
179
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
119
Input
235
Total output
230
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
143
Input
156
Total output
151
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
36
Input
202
Total output
194
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
102
Input
12,550
Total output
12,543
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
106
Input
1,794
Total output
1,771
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
95
Input
199
Total output
196
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
43
Input
23,569
Total output
23,551
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
93
Input
756
Total output
753
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
43
Input
393
Total output
376
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
103
Input
1,220
Total output
1,215
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
96
Input
230
Total output
227
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
101
Input
677
Total output
672
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
109
Input
284
Total output
280
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
41
Input
234
Total output
223
Reasoning within output
tag_management f001
100%
Passed
Tokens
56
Input
214
Total output
208
Reasoning within output
tag_management f002
100%
Passed
Tokens
52
Input
341
Total output
324
Reasoning within output
tag_management f003
100%
Passed
Tokens
60
Input
165
Total output
155
Reasoning within output
tag_management f004
100%
Passed
Tokens
68
Input
189
Total output
187
Reasoning within output
tag_management f005
100%
Passed
Tokens
80
Input
205
Total output
198
Reasoning within output
tag_management f006
100%
Passed
Tokens
64
Input
162
Total output
148
Reasoning within output
tag_management f007
100%
Passed
Tokens
60
Input
465
Total output
454
Reasoning within output
tag_management f008
100%
Passed
Tokens
63
Input
670
Total output
647
Reasoning within output
tag_management f009
100%
Passed
Tokens
67
Input
449
Total output
433
Reasoning within output
tag_management f010
100%
Passed
Tokens
45
Input
65
Total output
58
Reasoning within output
tag_management f011
100%
Passed
Tokens
45
Input
161
Total output
156
Reasoning within output
tag_management f012
100%
Passed
Tokens
86
Input
377
Total output
368
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
151
Input
345
Total output
336
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
156
Input
868
Total output
845
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
239
Input
126
Total output
118
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
228
Input
4,101
Total output
4,094
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
143
Input
237
Total output
224
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
139
Input
228
Total output
215
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
151
Input
1,845
Total output
1,822
Reasoning within output
worktree_usage f008
100%
Passed
Tokens
166
Input
31,849
Total output
31,795
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
266
Input
156
Total output
152
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
240
Input
369
Total output
354
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
238
Input
155
Total output
147
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
143
Input
341
Total output
328
Reasoning within output