Google / gemini-3-flash-preview
xhigh
97.1%
198 / 204 fixtures · 1 run(s)
40,625 input / 88,987 total output / 84,565 reasoning within output tokens $0.28727350
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-3.4%
Text: 97.1% →
JSON: 93.6%
+0
Gained
JSON pass / text fail
−7
Lost
Text pass / JSON fail
191
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% |
| merge_conflicts | 91.7% | 75% | -16.7% |
| rebase | 91.7% | 83.3% | -8.3% |
| cherry_pick | 83.3% | 75% | -8.3% |
| blame_forensics | 100% | 100% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| commit_squash | 91.7% | 91.7% | + 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% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
| worktree_usage | 91.7% | 91.7% | + 0% |
Changed Fixtures (7)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
262
Input
406
Total output
402
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
257
Input
484
Total output
480
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
297
Input
456
Total output
450
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
206
Input
548
Total output
543
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
271
Input
1,407
Total output
1,404
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
245
Input
1,145
Total output
1,142
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
217
Input
420
Total output
416
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
257
Input
565
Total output
562
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
211
Input
333
Total output
330
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
466
Input
487
Total output
484
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
261
Input
282
Total output
279
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
149
Input
423
Total output
419
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
98
Input
220
Total output
216
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
117
Input
310
Total output
303
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
89
Input
242
Total output
241
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
131
Input
339
Total output
332
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
104
Input
309
Total output
305
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
129
Input
276
Total output
266
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
99
Input
199
Total output
192
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
116
Input
254
Total output
245
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
75
Input
195
Total output
194
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
113
Input
258
Total output
253
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
65
Input
182
Total output
181
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
158
Input
419
Total output
407
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
94
Input
467
Total output
463
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
113
Input
219
Total output
212
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
85
Input
552
Total output
549
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
166
Input
2,252
Total output
2,228
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
154
Input
404
Total output
384
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
141
Input
303
Total output
281
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
132
Input
231
Total output
221
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
126
Input
234
Total output
228
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
104
Input
177
Total output
172
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
227
Input
844
Total output
814
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
165
Input
285
Total output
262
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
284
Input
1,102
Total output
1,055
Reasoning within output
commit_messages f001
92.7%
Passed
Tokens
112
Input
133
Total output
129
Reasoning within output
commit_messages f002
83.3%
Passed
Tokens
245
Input
501
Total output
493
Reasoning within output
commit_messages f003
94%
Passed
Tokens
83
Input
188
Total output
178
Reasoning within output
commit_messages f004
92.7%
Passed
Tokens
118
Input
145
Total output
141
Reasoning within output
commit_messages f005
89.7%
Passed
Tokens
109
Input
288
Total output
282
Reasoning within output
commit_messages f006
89.3%
Passed
Tokens
151
Input
503
Total output
497
Reasoning within output
commit_messages f007
91%
Passed
Tokens
209
Input
308
Total output
302
Reasoning within output
commit_messages f008
91.3%
Passed
Tokens
76
Input
225
Total output
220
Reasoning within output
commit_messages f009
87.7%
Passed
Tokens
133
Input
641
Total output
635
Reasoning within output
commit_messages f010
91.7%
Passed
Tokens
332
Input
341
Total output
335
Reasoning within output
commit_messages f011
66%
Passed
Tokens
153
Input
693
Total output
683
Reasoning within output
commit_messages f012
89.3%
Passed
Tokens
130
Input
185
Total output
180
Reasoning within output
commit_squash f001
100%
Passed
Tokens
133
Input
1,024
Total output
1,011
Reasoning within output
commit_squash f002
100%
Passed
Tokens
114
Input
293
Total output
284
Reasoning within output
commit_squash f003
100%
Passed
Tokens
126
Input
633
Total output
620
Reasoning within output
commit_squash f004
100%
Passed
Tokens
109
Input
457
Total output
446
Reasoning within output
commit_squash f005
100%
Passed
Tokens
111
Input
334
Total output
327
Reasoning within output
commit_squash f006
100%
Passed
Tokens
95
Input
286
Total output
275
Reasoning within output
commit_squash f007
100%
Passed
Tokens
100
Input
405
Total output
393
Reasoning within output
commit_squash f008
100%
Passed
Tokens
111
Input
294
Total output
283
Reasoning within output
commit_squash f009
100%
Failed
Tokens
102
Input
672
Total output
658
Reasoning within output
commit_squash f010
100%
Passed
Tokens
116
Input
285
Total output
270
Reasoning within output
commit_squash f011
100%
Passed
Tokens
124
Input
272
Total output
257
Reasoning within output
commit_squash f012
100%
Passed
Tokens
120
Input
305
Total output
285
Reasoning within output
git_bisect f001
100%
Passed
Tokens
185
Input
138
Total output
131
Reasoning within output
git_bisect f002
100%
Passed
Tokens
213
Input
273
Total output
267
Reasoning within output
git_bisect f003
100%
Passed
Tokens
207
Input
285
Total output
279
Reasoning within output
git_bisect f004
100%
Passed
Tokens
213
Input
284
Total output
278
Reasoning within output
git_bisect f005
100%
Passed
Tokens
213
Input
205
Total output
185
Reasoning within output
git_bisect f006
100%
Passed
Tokens
231
Input
224
Total output
219
Reasoning within output
git_bisect f007
100%
Passed
Tokens
211
Input
325
Total output
319
Reasoning within output
git_bisect f008
100%
Passed
Tokens
205
Input
212
Total output
208
Reasoning within output
git_bisect f009
100%
Passed
Tokens
211
Input
387
Total output
380
Reasoning within output
git_bisect f010
100%
Passed
Tokens
205
Input
256
Total output
239
Reasoning within output
git_bisect f011
100%
Passed
Tokens
217
Input
270
Total output
263
Reasoning within output
git_bisect f012
100%
Passed
Tokens
239
Input
342
Total output
206
Reasoning within output
git_clean f001
100%
Passed
Tokens
50
Input
179
Total output
175
Reasoning within output
git_clean f002
100%
Passed
Tokens
62
Input
144
Total output
140
Reasoning within output
git_clean f003
100%
Passed
Tokens
62
Input
177
Total output
173
Reasoning within output
git_clean f004
100%
Passed
Tokens
62
Input
250
Total output
245
Reasoning within output
git_clean f005
100%
Passed
Tokens
49
Input
256
Total output
252
Reasoning within output
git_clean f006
100%
Passed
Tokens
80
Input
267
Total output
261
Reasoning within output
git_clean f007
100%
Passed
Tokens
69
Input
325
Total output
316
Reasoning within output
git_clean f008
100%
Passed
Tokens
77
Input
242
Total output
238
Reasoning within output
git_clean f009
100%
Passed
Tokens
73
Input
207
Total output
199
Reasoning within output
git_clean f010
100%
Passed
Tokens
64
Input
184
Total output
180
Reasoning within output
git_clean f011
100%
Passed
Tokens
64
Input
277
Total output
272
Reasoning within output
git_clean f012
100%
Passed
Tokens
69
Input
394
Total output
387
Reasoning within output
git_grep f001
100%
Passed
Tokens
48
Input
141
Total output
136
Reasoning within output
git_grep f002
100%
Passed
Tokens
60
Input
124
Total output
123
Reasoning within output
git_grep f003
100%
Passed
Tokens
100
Input
219
Total output
218
Reasoning within output
git_grep f004
100%
Passed
Tokens
76
Input
145
Total output
140
Reasoning within output
git_grep f005
100%
Passed
Tokens
114
Input
153
Total output
152
Reasoning within output
git_grep f006
100%
Passed
Tokens
33
Input
760
Total output
759
Reasoning within output
git_grep f007
100%
Passed
Tokens
176
Input
917
Total output
915
Reasoning within output
git_grep f008
100%
Passed
Tokens
56
Input
166
Total output
165
Reasoning within output
git_grep f009
100%
Passed
Tokens
49
Input
142
Total output
139
Reasoning within output
git_grep f010
100%
Passed
Tokens
63
Input
153
Total output
152
Reasoning within output
git_grep f011
100%
Passed
Tokens
126
Input
167
Total output
166
Reasoning within output
git_grep f012
100%
Passed
Tokens
64
Input
184
Total output
171
Reasoning within output
git_log_format f001
100%
Passed
Tokens
916
Input
223
Total output
222
Reasoning within output
git_log_format f002
100%
Passed
Tokens
916
Input
514
Total output
507
Reasoning within output
git_log_format f003
100%
Passed
Tokens
726
Input
318
Total output
309
Reasoning within output
git_log_format f004
100%
Passed
Tokens
909
Input
328
Total output
327
Reasoning within output
git_log_format f005
100%
Passed
Tokens
746
Input
258
Total output
253
Reasoning within output
git_log_format f006
100%
Passed
Tokens
934
Input
354
Total output
353
Reasoning within output
git_log_format f007
100%
Passed
Tokens
926
Input
246
Total output
240
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,235
Input
199
Total output
198
Reasoning within output
git_log_format f009
100%
Passed
Tokens
751
Input
246
Total output
245
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,431
Input
331
Total output
330
Reasoning within output
git_log_format f011
100%
Passed
Tokens
438
Input
257
Total output
254
Reasoning within output
git_log_format f012
100%
Passed
Tokens
413
Input
362
Total output
361
Reasoning within output
git_show f001
100%
Passed
Tokens
197
Input
152
Total output
147
Reasoning within output
git_show f002
100%
Passed
Tokens
206
Input
789
Total output
786
Reasoning within output
git_show f003
100%
Passed
Tokens
705
Input
209
Total output
203
Reasoning within output
git_show f004
100%
Passed
Tokens
476
Input
206
Total output
199
Reasoning within output
git_show f005
100%
Passed
Tokens
203
Input
320
Total output
318
Reasoning within output
git_show f006
100%
Passed
Tokens
214
Input
102
Total output
101
Reasoning within output
git_show f007
100%
Passed
Tokens
203
Input
198
Total output
193
Reasoning within output
git_show f008
100%
Passed
Tokens
209
Input
189
Total output
152
Reasoning within output
git_show f009
100%
Passed
Tokens
323
Input
361
Total output
360
Reasoning within output
git_show f010
100%
Passed
Tokens
204
Input
257
Total output
256
Reasoning within output
git_show f011
100%
Passed
Tokens
232
Input
129
Total output
126
Reasoning within output
git_show f012
100%
Passed
Tokens
360
Input
192
Total output
191
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
82
Input
265
Total output
261
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
100
Input
497
Total output
490
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
73
Input
579
Total output
576
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
150
Input
2,104
Total output
2,078
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
140
Input
272
Total output
252
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
126
Input
449
Total output
427
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
136
Input
415
Total output
405
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
107
Input
212
Total output
206
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
99
Input
278
Total output
273
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
190
Input
527
Total output
497
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
143
Input
293
Total output
270
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
247
Input
7,648
Total output
7,601
Reasoning within output
rebase f001
100%
Passed
Tokens
96
Input
1,051
Total output
1,047
Reasoning within output
rebase f002
100%
Passed
Tokens
121
Input
200
Total output
193
Reasoning within output
rebase f003
100%
Passed
Tokens
100
Input
298
Total output
295
Reasoning within output
rebase f004
100%
Passed
Tokens
165
Input
2,157
Total output
2,131
Reasoning within output
rebase f005
100%
Passed
Tokens
146
Input
614
Total output
598
Reasoning within output
rebase f006
100%
Passed
Tokens
140
Input
1,007
Total output
985
Reasoning within output
rebase f007
100%
Passed
Tokens
135
Input
283
Total output
273
Reasoning within output
rebase f008
100%
Passed
Tokens
121
Input
135
Total output
129
Reasoning within output
rebase f009
100%
Passed
Tokens
99
Input
306
Total output
301
Reasoning within output
rebase f010
100%
Passed
Tokens
217
Input
1,311
Total output
1,281
Reasoning within output
rebase f011
100%
Passed
Tokens
155
Input
268
Total output
245
Reasoning within output
rebase f012
0%
Failed
Tokens
284
Input
3,657
Total output
3,610
Reasoning within output
reflog f001
100%
Passed
Tokens
241
Input
608
Total output
572
Reasoning within output
reflog f002
100%
Passed
Tokens
238
Input
577
Total output
402
Reasoning within output
reflog f003
100%
Passed
Tokens
203
Input
395
Total output
260
Reasoning within output
reflog f004
100%
Passed
Tokens
351
Input
931
Total output
699
Reasoning within output
reflog f005
100%
Passed
Tokens
398
Input
561
Total output
435
Reasoning within output
reflog f006
100%
Passed
Tokens
254
Input
525
Total output
349
Reasoning within output
reflog f007
100%
Passed
Tokens
288
Input
577
Total output
389
Reasoning within output
reflog f008
100%
Passed
Tokens
377
Input
539
Total output
368
Reasoning within output
reflog f009
100%
Passed
Tokens
349
Input
777
Total output
555
Reasoning within output
reflog f010
100%
Passed
Tokens
282
Input
490
Total output
407
Reasoning within output
reflog f011
100%
Passed
Tokens
338
Input
1,133
Total output
940
Reasoning within output
reflog f012
100%
Passed
Tokens
347
Input
786
Total output
498
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
136
Input
176
Total output
155
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
313
Input
425
Total output
254
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
127
Input
134
Total output
118
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
120
Input
172
Total output
154
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
131
Input
342
Total output
235
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
196
Input
185
Total output
169
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
218
Input
227
Total output
211
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
192
Input
323
Total output
306
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
222
Input
200
Total output
153
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
128
Input
157
Total output
143
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
121
Input
338
Total output
208
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
143
Input
202
Total output
189
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
36
Input
124
Total output
116
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
101
Input
466
Total output
459
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
107
Input
840
Total output
817
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
97
Input
97
Total output
94
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
43
Input
1,187
Total output
1,157
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
94
Input
260
Total output
257
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
43
Input
195
Total output
178
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
96
Input
218
Total output
213
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
93
Input
137
Total output
134
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
100
Input
218
Total output
213
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
107
Input
176
Total output
172
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
41
Input
156
Total output
145
Reasoning within output
tag_management f001
100%
Passed
Tokens
55
Input
229
Total output
223
Reasoning within output
tag_management f002
100%
Passed
Tokens
53
Input
144
Total output
127
Reasoning within output
tag_management f003
100%
Passed
Tokens
62
Input
229
Total output
219
Reasoning within output
tag_management f004
100%
Passed
Tokens
64
Input
103
Total output
101
Reasoning within output
tag_management f005
100%
Passed
Tokens
81
Input
173
Total output
166
Reasoning within output
tag_management f006
100%
Passed
Tokens
64
Input
231
Total output
217
Reasoning within output
tag_management f007
100%
Passed
Tokens
60
Input
174
Total output
163
Reasoning within output
tag_management f008
100%
Passed
Tokens
64
Input
577
Total output
554
Reasoning within output
tag_management f009
100%
Passed
Tokens
68
Input
194
Total output
178
Reasoning within output
tag_management f010
100%
Passed
Tokens
44
Input
116
Total output
109
Reasoning within output
tag_management f011
100%
Passed
Tokens
46
Input
166
Total output
161
Reasoning within output
tag_management f012
100%
Passed
Tokens
86
Input
353
Total output
344
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
149
Input
156
Total output
147
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
158
Input
332
Total output
309
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
237
Input
174
Total output
166
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
233
Input
95
Total output
91
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
144
Input
197
Total output
184
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
140
Input
263
Total output
250
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
150
Input
212
Total output
189
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
167
Input
1,854
Total output
1,800
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
274
Input
152
Total output
148
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
240
Input
173
Total output
158
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
236
Input
77
Total output
69
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
142
Input
179
Total output
166
Reasoning within output