Google / gemini-3-flash-preview
high
96.6%
197 / 204 fixtures · 1 run(s)
40,662 input / 99,727 total output / 95,594 reasoning within output tokens $0.31951200
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-2.4%
Text: 96.6% →
JSON: 94.1%
+2
Gained
JSON pass / text fail
−7
Lost
Text pass / JSON fail
190
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 | 91.7% | 75% | -16.7% |
| rebase | 91.7% | 83.3% | -8.3% |
| worktree_usage | 83.3% | 91.7% | + 8.3% |
| blame_forensics | 100% | 100% | + 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 | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
Changed Fixtures (9)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
262
Input
644
Total output
640
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
257
Input
481
Total output
477
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
297
Input
295
Total output
289
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
210
Input
919
Total output
914
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
267
Input
1,251
Total output
1,248
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
247
Input
632
Total output
629
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
218
Input
369
Total output
365
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
263
Input
617
Total output
614
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
214
Input
331
Total output
328
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
462
Input
371
Total output
368
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
256
Input
314
Total output
311
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
151
Input
379
Total output
375
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
99
Input
243
Total output
239
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
118
Input
444
Total output
437
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
90
Input
222
Total output
221
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
127
Input
236
Total output
229
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
103
Input
173
Total output
169
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
130
Input
269
Total output
259
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
105
Input
290
Total output
283
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
119
Input
326
Total output
317
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
77
Input
195
Total output
194
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
115
Input
239
Total output
234
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
65
Input
192
Total output
191
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
158
Input
351
Total output
339
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
93
Input
325
Total output
321
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
114
Input
382
Total output
375
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
85
Input
565
Total output
562
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
165
Input
1,514
Total output
1,490
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
153
Input
432
Total output
412
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
139
Input
345
Total output
323
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
133
Input
281
Total output
271
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
125
Input
156
Total output
150
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
105
Input
196
Total output
191
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
231
Input
641
Total output
611
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
163
Input
334
Total output
311
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
288
Input
3,260
Total output
3,213
Reasoning within output
commit_messages f001
91.7%
Passed
Tokens
112
Input
242
Total output
238
Reasoning within output
commit_messages f002
86%
Passed
Tokens
245
Input
500
Total output
492
Reasoning within output
commit_messages f003
93.7%
Passed
Tokens
83
Input
149
Total output
139
Reasoning within output
commit_messages f004
96.7%
Passed
Tokens
118
Input
191
Total output
187
Reasoning within output
commit_messages f005
91.7%
Passed
Tokens
109
Input
331
Total output
326
Reasoning within output
commit_messages f006
91%
Passed
Tokens
151
Input
261
Total output
254
Reasoning within output
commit_messages f007
91%
Passed
Tokens
209
Input
296
Total output
290
Reasoning within output
commit_messages f008
91%
Passed
Tokens
76
Input
301
Total output
296
Reasoning within output
commit_messages f009
85.7%
Passed
Tokens
133
Input
542
Total output
535
Reasoning within output
commit_messages f010
88.3%
Passed
Tokens
332
Input
815
Total output
806
Reasoning within output
commit_messages f011
61.3%
Passed
Tokens
153
Input
910
Total output
898
Reasoning within output
commit_messages f012
91.7%
Passed
Tokens
130
Input
227
Total output
222
Reasoning within output
commit_squash f001
100%
Passed
Tokens
132
Input
1,636
Total output
1,623
Reasoning within output
commit_squash f002
100%
Passed
Tokens
111
Input
301
Total output
292
Reasoning within output
commit_squash f003
100%
Passed
Tokens
126
Input
564
Total output
551
Reasoning within output
commit_squash f004
100%
Passed
Tokens
111
Input
334
Total output
323
Reasoning within output
commit_squash f005
100%
Passed
Tokens
111
Input
267
Total output
260
Reasoning within output
commit_squash f006
100%
Passed
Tokens
96
Input
339
Total output
328
Reasoning within output
commit_squash f007
100%
Passed
Tokens
99
Input
341
Total output
329
Reasoning within output
commit_squash f008
100%
Passed
Tokens
110
Input
423
Total output
411
Reasoning within output
commit_squash f009
100%
Failed
Tokens
103
Input
762
Total output
748
Reasoning within output
commit_squash f010
100%
Passed
Tokens
115
Input
349
Total output
334
Reasoning within output
commit_squash f011
100%
Passed
Tokens
125
Input
321
Total output
306
Reasoning within output
commit_squash f012
100%
Passed
Tokens
119
Input
321
Total output
301
Reasoning within output
git_bisect f001
100%
Passed
Tokens
185
Input
139
Total output
122
Reasoning within output
git_bisect f002
100%
Passed
Tokens
215
Input
305
Total output
298
Reasoning within output
git_bisect f003
100%
Passed
Tokens
205
Input
215
Total output
208
Reasoning within output
git_bisect f004
100%
Passed
Tokens
211
Input
176
Total output
169
Reasoning within output
git_bisect f005
100%
Passed
Tokens
213
Input
162
Total output
156
Reasoning within output
git_bisect f006
100%
Passed
Tokens
237
Input
186
Total output
172
Reasoning within output
git_bisect f007
100%
Passed
Tokens
215
Input
286
Total output
273
Reasoning within output
git_bisect f008
100%
Passed
Tokens
213
Input
213
Total output
208
Reasoning within output
git_bisect f009
100%
Passed
Tokens
209
Input
208
Total output
202
Reasoning within output
git_bisect f010
100%
Passed
Tokens
215
Input
223
Total output
217
Reasoning within output
git_bisect f011
100%
Passed
Tokens
217
Input
206
Total output
199
Reasoning within output
git_bisect f012
100%
Passed
Tokens
237
Input
438
Total output
419
Reasoning within output
git_clean f001
100%
Passed
Tokens
50
Input
206
Total output
202
Reasoning within output
git_clean f002
100%
Passed
Tokens
62
Input
167
Total output
163
Reasoning within output
git_clean f003
100%
Passed
Tokens
62
Input
214
Total output
210
Reasoning within output
git_clean f004
100%
Passed
Tokens
62
Input
265
Total output
260
Reasoning within output
git_clean f005
100%
Passed
Tokens
49
Input
210
Total output
206
Reasoning within output
git_clean f006
100%
Passed
Tokens
80
Input
217
Total output
211
Reasoning within output
git_clean f007
100%
Passed
Tokens
69
Input
298
Total output
289
Reasoning within output
git_clean f008
100%
Passed
Tokens
77
Input
223
Total output
219
Reasoning within output
git_clean f009
100%
Passed
Tokens
73
Input
227
Total output
219
Reasoning within output
git_clean f010
100%
Passed
Tokens
64
Input
181
Total output
177
Reasoning within output
git_clean f011
100%
Passed
Tokens
64
Input
286
Total output
281
Reasoning within output
git_clean f012
100%
Passed
Tokens
69
Input
337
Total output
330
Reasoning within output
git_grep f001
100%
Passed
Tokens
48
Input
160
Total output
155
Reasoning within output
git_grep f002
100%
Passed
Tokens
60
Input
170
Total output
169
Reasoning within output
git_grep f003
100%
Passed
Tokens
100
Input
218
Total output
217
Reasoning within output
git_grep f004
100%
Passed
Tokens
76
Input
166
Total output
161
Reasoning within output
git_grep f005
100%
Passed
Tokens
114
Input
432
Total output
431
Reasoning within output
git_grep f006
100%
Passed
Tokens
33
Input
598
Total output
597
Reasoning within output
git_grep f007
100%
Passed
Tokens
176
Input
1,826
Total output
1,824
Reasoning within output
git_grep f008
100%
Passed
Tokens
56
Input
160
Total output
159
Reasoning within output
git_grep f009
100%
Passed
Tokens
49
Input
155
Total output
152
Reasoning within output
git_grep f010
100%
Passed
Tokens
63
Input
191
Total output
190
Reasoning within output
git_grep f011
100%
Passed
Tokens
126
Input
206
Total output
205
Reasoning within output
git_grep f012
100%
Passed
Tokens
64
Input
244
Total output
231
Reasoning within output
git_log_format f001
100%
Passed
Tokens
916
Input
160
Total output
159
Reasoning within output
git_log_format f002
100%
Passed
Tokens
910
Input
159
Total output
152
Reasoning within output
git_log_format f003
100%
Passed
Tokens
733
Input
259
Total output
250
Reasoning within output
git_log_format f004
100%
Passed
Tokens
916
Input
266
Total output
265
Reasoning within output
git_log_format f005
100%
Passed
Tokens
746
Input
468
Total output
463
Reasoning within output
git_log_format f006
100%
Passed
Tokens
934
Input
709
Total output
708
Reasoning within output
git_log_format f007
100%
Passed
Tokens
921
Input
194
Total output
189
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,238
Input
223
Total output
222
Reasoning within output
git_log_format f009
100%
Passed
Tokens
743
Input
187
Total output
186
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,423
Input
326
Total output
325
Reasoning within output
git_log_format f011
100%
Passed
Tokens
441
Input
386
Total output
383
Reasoning within output
git_log_format f012
100%
Passed
Tokens
409
Input
174
Total output
173
Reasoning within output
git_show f001
100%
Passed
Tokens
192
Input
207
Total output
202
Reasoning within output
git_show f002
100%
Passed
Tokens
206
Input
4,953
Total output
4,950
Reasoning within output
git_show f003
100%
Passed
Tokens
725
Input
330
Total output
324
Reasoning within output
git_show f004
100%
Passed
Tokens
480
Input
232
Total output
225
Reasoning within output
git_show f005
100%
Passed
Tokens
208
Input
265
Total output
263
Reasoning within output
git_show f006
100%
Passed
Tokens
212
Input
199
Total output
198
Reasoning within output
git_show f007
100%
Passed
Tokens
203
Input
221
Total output
216
Reasoning within output
git_show f008
100%
Passed
Tokens
206
Input
205
Total output
172
Reasoning within output
git_show f009
100%
Passed
Tokens
323
Input
349
Total output
348
Reasoning within output
git_show f010
100%
Passed
Tokens
206
Input
309
Total output
308
Reasoning within output
git_show f011
100%
Passed
Tokens
225
Input
188
Total output
185
Reasoning within output
git_show f012
100%
Passed
Tokens
358
Input
274
Total output
273
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
82
Input
843
Total output
839
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
100
Input
848
Total output
841
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
73
Input
1,127
Total output
1,124
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
150
Input
856
Total output
830
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
140
Input
309
Total output
289
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
126
Input
398
Total output
376
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
186
Total output
180
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
99
Input
290
Total output
285
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
190
Input
801
Total output
771
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
143
Input
359
Total output
336
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
247
Input
3,130
Total output
3,081
Reasoning within output
rebase f001
100%
Passed
Tokens
96
Input
1,704
Total output
1,700
Reasoning within output
rebase f002
100%
Passed
Tokens
121
Input
244
Total output
237
Reasoning within output
rebase f003
100%
Passed
Tokens
100
Input
304
Total output
301
Reasoning within output
rebase f004
100%
Passed
Tokens
165
Input
1,224
Total output
1,198
Reasoning within output
rebase f005
100%
Passed
Tokens
147
Input
351
Total output
335
Reasoning within output
rebase f006
100%
Passed
Tokens
142
Input
927
Total output
905
Reasoning within output
rebase f007
100%
Passed
Tokens
137
Input
242
Total output
232
Reasoning within output
rebase f008
100%
Passed
Tokens
122
Input
443
Total output
437
Reasoning within output
rebase f009
100%
Passed
Tokens
100
Input
418
Total output
413
Reasoning within output
rebase f010
100%
Passed
Tokens
219
Input
642
Total output
612
Reasoning within output
rebase f011
100%
Passed
Tokens
155
Input
299
Total output
276
Reasoning within output
rebase f012
0%
Failed
Tokens
284
Input
10,711
Total output
10,664
Reasoning within output
reflog f001
100%
Passed
Tokens
256
Input
450
Total output
414
Reasoning within output
reflog f002
100%
Passed
Tokens
248
Input
545
Total output
337
Reasoning within output
reflog f003
100%
Passed
Tokens
200
Input
499
Total output
369
Reasoning within output
reflog f004
100%
Passed
Tokens
348
Input
782
Total output
531
Reasoning within output
reflog f005
100%
Passed
Tokens
391
Input
622
Total output
548
Reasoning within output
reflog f006
100%
Passed
Tokens
248
Input
522
Total output
383
Reasoning within output
reflog f007
100%
Passed
Tokens
295
Input
384
Total output
294
Reasoning within output
reflog f008
100%
Passed
Tokens
393
Input
432
Total output
225
Reasoning within output
reflog f009
100%
Passed
Tokens
339
Input
630
Total output
382
Reasoning within output
reflog f010
100%
Passed
Tokens
282
Input
627
Total output
461
Reasoning within output
reflog f011
100%
Passed
Tokens
351
Input
841
Total output
621
Reasoning within output
reflog f012
100%
Passed
Tokens
323
Input
676
Total output
410
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
135
Input
189
Total output
168
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
310
Input
448
Total output
283
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
127
Input
140
Total output
127
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
120
Input
170
Total output
149
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
130
Input
256
Total output
237
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
196
Input
139
Total output
128
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
216
Input
192
Total output
174
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
192
Input
229
Total output
212
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
222
Input
194
Total output
145
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
128
Input
149
Total output
136
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
121
Input
181
Total output
168
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
108
Total output
100
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
102
Input
530
Total output
523
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
108
Input
761
Total output
738
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
95
Input
77
Total output
74
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
43
Input
1,878
Total output
1,851
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
89
Input
279
Total output
276
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
43
Input
224
Total output
207
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
100
Input
150
Total output
145
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
100
Input
122
Total output
119
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
102
Input
290
Total output
285
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
110
Input
110
Total output
106
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
41
Input
156
Total output
145
Reasoning within output
tag_management f001
100%
Passed
Tokens
56
Input
168
Total output
162
Reasoning within output
tag_management f002
100%
Passed
Tokens
53
Input
127
Total output
110
Reasoning within output
tag_management f003
100%
Passed
Tokens
59
Input
143
Total output
133
Reasoning within output
tag_management f004
100%
Passed
Tokens
67
Input
139
Total output
137
Reasoning within output
tag_management f005
100%
Passed
Tokens
77
Input
247
Total output
240
Reasoning within output
tag_management f006
100%
Passed
Tokens
62
Input
196
Total output
182
Reasoning within output
tag_management f007
100%
Passed
Tokens
60
Input
258
Total output
247
Reasoning within output
tag_management f008
100%
Passed
Tokens
64
Input
1,406
Total output
1,363
Reasoning within output
tag_management f009
100%
Passed
Tokens
67
Input
264
Total output
248
Reasoning within output
tag_management f010
100%
Passed
Tokens
45
Input
121
Total output
114
Reasoning within output
tag_management f011
100%
Passed
Tokens
47
Input
75
Total output
70
Reasoning within output
tag_management f012
100%
Passed
Tokens
86
Input
379
Total output
370
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
143
Input
132
Total output
123
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
152
Input
250
Total output
229
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
236
Input
330
Total output
322
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
232
Input
544
Total output
537
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
143
Input
154
Total output
141
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
141
Input
230
Total output
217
Reasoning within output
worktree_usage f007
0%
Failed
Tokens
148
Input
1,223
Total output
1,196
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
167
Input
1,296
Total output
1,242
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
268
Input
126
Total output
122
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
241
Input
155
Total output
140
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
239
Input
122
Total output
114
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
140
Input
197
Total output
184
Reasoning within output