Google / gemini-3.8-flash
max
97.1%
198 / 204 fixtures · 1 run(s)
40,537 input / 206,639 total output / 195,097 reasoning within output tokens $0.77675550
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-2.9%
Text: 97.1% →
JSON: 94.1%
+1
Gained
JSON pass / text fail
−7
Lost
Text pass / JSON fail
191
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% | 100% | + 8.3% |
| git_grep | 100% | 91.7% | -8.3% |
| git_show | 100% | 91.7% | -8.3% |
| reflog | 100% | 91.7% | -8.3% |
| submodule_usage | 100% | 91.7% | -8.3% |
| blame_forensics | 91.7% | 91.7% | + 0% |
| cherry_pick | 83.3% | 83.3% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_clean | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| merge_conflicts | 91.7% | 91.7% | + 0% |
| rebase | 91.7% | 91.7% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
| worktree_usage | 100% | 100% | + 0% |
Changed Fixtures (8)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
263
Input
549
Total output
545
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
254
Input
350
Total output
346
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
288
Input
297
Total output
291
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
207
Input
540
Total output
535
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
273
Input
2,480
Total output
2,475
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
249
Input
431
Total output
428
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
216
Input
329
Total output
325
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
265
Input
430
Total output
427
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
205
Input
412
Total output
409
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
454
Input
414
Total output
411
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
266
Input
372
Total output
369
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
152
Input
422
Total output
418
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
101
Input
285
Total output
281
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
117
Input
371
Total output
364
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
95
Input
282
Total output
281
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
127
Input
336
Total output
329
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
106
Input
279
Total output
275
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
124
Input
359
Total output
349
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
101
Input
382
Total output
375
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
118
Input
476
Total output
467
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
77
Input
228
Total output
227
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
113
Input
274
Total output
269
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
64
Input
257
Total output
256
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
157
Input
359
Total output
347
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
94
Input
411
Total output
407
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
113
Input
624
Total output
617
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
86
Input
1,069
Total output
1,066
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
166
Input
1,540
Total output
1,516
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
155
Input
238
Total output
218
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
141
Input
436
Total output
414
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
133
Input
382
Total output
372
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
126
Input
210
Total output
204
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
104
Input
176
Total output
171
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
227
Input
1,399
Total output
1,369
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
164
Input
542
Total output
519
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
288
Input
2,840
Total output
2,793
Reasoning within output
commit_messages f001
85%
Passed
Tokens
112
Input
749
Total output
739
Reasoning within output
commit_messages f002
93.5%
Passed
Tokens
245
Input
640
Total output
632
Reasoning within output
commit_messages f003
92.5%
Passed
Tokens
83
Input
304
Total output
294
Reasoning within output
commit_messages f004
95%
Passed
Tokens
118
Input
317
Total output
313
Reasoning within output
commit_messages f005
84%
Passed
Tokens
109
Input
346
Total output
341
Reasoning within output
commit_messages f006
82.5%
Passed
Tokens
151
Input
428
Total output
422
Reasoning within output
commit_messages f007
92.5%
Passed
Tokens
209
Input
344
Total output
338
Reasoning within output
commit_messages f008
92.5%
Passed
Tokens
76
Input
336
Total output
331
Reasoning within output
commit_messages f009
82.5%
Passed
Tokens
133
Input
658
Total output
651
Reasoning within output
commit_messages f010
91.5%
Passed
Tokens
332
Input
350
Total output
344
Reasoning within output
commit_messages f011
80%
Passed
Tokens
153
Input
1,032
Total output
1,020
Reasoning within output
commit_messages f012
92.5%
Passed
Tokens
130
Input
377
Total output
372
Reasoning within output
commit_squash f001
0%
Failed
Tokens
138
Input
2,162
Total output
0
Reasoning within output
commit_squash f002
100%
Passed
Tokens
113
Input
418
Total output
409
Reasoning within output
commit_squash f003
100%
Passed
Tokens
121
Input
1,172
Total output
1,159
Reasoning within output
commit_squash f004
100%
Passed
Tokens
109
Input
1,536
Total output
1,525
Reasoning within output
commit_squash f005
100%
Passed
Tokens
110
Input
45,310
Total output
45,303
Reasoning within output
commit_squash f006
100%
Passed
Tokens
92
Input
365
Total output
354
Reasoning within output
commit_squash f007
100%
Passed
Tokens
99
Input
517
Total output
505
Reasoning within output
commit_squash f008
100%
Passed
Tokens
113
Input
443
Total output
431
Reasoning within output
commit_squash f009
100%
Passed
Tokens
104
Input
661
Total output
650
Reasoning within output
commit_squash f010
100%
Passed
Tokens
117
Input
475
Total output
460
Reasoning within output
commit_squash f011
100%
Passed
Tokens
121
Input
2,898
Total output
2,883
Reasoning within output
commit_squash f012
100%
Passed
Tokens
121
Input
500
Total output
480
Reasoning within output
git_bisect f001
100%
Passed
Tokens
183
Input
122
Total output
115
Reasoning within output
git_bisect f002
100%
Passed
Tokens
211
Input
184
Total output
178
Reasoning within output
git_bisect f003
100%
Passed
Tokens
213
Input
247
Total output
240
Reasoning within output
git_bisect f004
100%
Passed
Tokens
213
Input
194
Total output
189
Reasoning within output
git_bisect f005
100%
Passed
Tokens
213
Input
160
Total output
154
Reasoning within output
git_bisect f006
100%
Passed
Tokens
241
Input
210
Total output
203
Reasoning within output
git_bisect f007
100%
Passed
Tokens
209
Input
162
Total output
156
Reasoning within output
git_bisect f008
100%
Passed
Tokens
213
Input
188
Total output
181
Reasoning within output
git_bisect f009
100%
Passed
Tokens
207
Input
161
Total output
156
Reasoning within output
git_bisect f010
100%
Passed
Tokens
213
Input
219
Total output
212
Reasoning within output
git_bisect f011
100%
Passed
Tokens
215
Input
179
Total output
173
Reasoning within output
git_bisect f012
100%
Passed
Tokens
237
Input
270
Total output
265
Reasoning within output
git_clean f001
100%
Passed
Tokens
50
Input
326
Total output
322
Reasoning within output
git_clean f002
100%
Passed
Tokens
62
Input
291
Total output
287
Reasoning within output
git_clean f003
100%
Passed
Tokens
62
Input
368
Total output
364
Reasoning within output
git_clean f004
100%
Passed
Tokens
62
Input
323
Total output
318
Reasoning within output
git_clean f005
100%
Passed
Tokens
49
Input
285
Total output
281
Reasoning within output
git_clean f006
100%
Passed
Tokens
80
Input
1,649
Total output
1,643
Reasoning within output
git_clean f007
100%
Passed
Tokens
69
Input
275
Total output
266
Reasoning within output
git_clean f008
100%
Passed
Tokens
77
Input
258
Total output
254
Reasoning within output
git_clean f009
100%
Passed
Tokens
73
Input
17,212
Total output
17,205
Reasoning within output
git_clean f010
100%
Passed
Tokens
0
Input
0
Total output
0
Reasoning within output
git_clean f011
100%
Passed
Tokens
64
Input
491
Total output
486
Reasoning within output
git_clean f012
100%
Passed
Tokens
69
Input
320
Total output
313
Reasoning within output
git_grep f001
100%
Passed
Tokens
48
Input
162
Total output
157
Reasoning within output
git_grep f002
100%
Passed
Tokens
60
Input
190
Total output
189
Reasoning within output
git_grep f003
100%
Passed
Tokens
100
Input
188
Total output
187
Reasoning within output
git_grep f004
100%
Passed
Tokens
76
Input
408
Total output
403
Reasoning within output
git_grep f005
100%
Passed
Tokens
114
Input
257
Total output
256
Reasoning within output
git_grep f006
100%
Passed
Tokens
33
Input
352
Total output
351
Reasoning within output
git_grep f007
100%
Passed
Tokens
176
Input
975
Total output
973
Reasoning within output
git_grep f008
100%
Passed
Tokens
56
Input
211
Total output
210
Reasoning within output
git_grep f009
100%
Passed
Tokens
49
Input
172
Total output
169
Reasoning within output
git_grep f010
100%
Passed
Tokens
63
Input
212
Total output
211
Reasoning within output
git_grep f011
100%
Passed
Tokens
126
Input
237
Total output
236
Reasoning within output
git_grep f012
100%
Passed
Tokens
64
Input
192
Total output
179
Reasoning within output
git_log_format f001
100%
Passed
Tokens
911
Input
158
Total output
157
Reasoning within output
git_log_format f002
100%
Passed
Tokens
905
Input
373
Total output
366
Reasoning within output
git_log_format f003
100%
Passed
Tokens
734
Input
299
Total output
290
Reasoning within output
git_log_format f004
100%
Passed
Tokens
903
Input
174
Total output
173
Reasoning within output
git_log_format f005
100%
Passed
Tokens
746
Input
407
Total output
402
Reasoning within output
git_log_format f006
100%
Passed
Tokens
934
Input
520
Total output
519
Reasoning within output
git_log_format f007
100%
Passed
Tokens
921
Input
118
Total output
111
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,250
Input
138
Total output
137
Reasoning within output
git_log_format f009
100%
Passed
Tokens
755
Input
207
Total output
206
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,444
Input
191
Total output
190
Reasoning within output
git_log_format f011
100%
Passed
Tokens
444
Input
277
Total output
274
Reasoning within output
git_log_format f012
100%
Passed
Tokens
395
Input
146
Total output
145
Reasoning within output
git_show f001
100%
Passed
Tokens
197
Input
217
Total output
212
Reasoning within output
git_show f002
100%
Passed
Tokens
205
Input
1,371
Total output
1,368
Reasoning within output
git_show f003
100%
Passed
Tokens
727
Input
162
Total output
156
Reasoning within output
git_show f004
100%
Passed
Tokens
484
Input
158
Total output
151
Reasoning within output
git_show f005
100%
Passed
Tokens
210
Input
213
Total output
211
Reasoning within output
git_show f006
100%
Passed
Tokens
217
Input
144
Total output
143
Reasoning within output
git_show f007
100%
Passed
Tokens
203
Input
200
Total output
195
Reasoning within output
git_show f008
100%
Passed
Tokens
209
Input
300
Total output
264
Reasoning within output
git_show f009
100%
Passed
Tokens
324
Input
333
Total output
332
Reasoning within output
git_show f010
100%
Passed
Tokens
200
Input
337
Total output
336
Reasoning within output
git_show f011
100%
Passed
Tokens
232
Input
180
Total output
177
Reasoning within output
git_show f012
100%
Passed
Tokens
362
Input
248
Total output
247
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
82
Input
812
Total output
808
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
100
Input
588
Total output
581
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
73
Input
1,247
Total output
1,244
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
150
Input
1,144
Total output
1,118
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
140
Input
520
Total output
500
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
126
Input
707
Total output
685
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
136
Input
394
Total output
384
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
107
Input
222
Total output
216
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
99
Input
1,112
Total output
1,107
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
190
Input
1,238
Total output
1,208
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
143
Input
549
Total output
526
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
216
Input
2,003
Total output
0
Reasoning within output
rebase f001
100%
Passed
Tokens
94
Input
623
Total output
619
Reasoning within output
rebase f002
100%
Passed
Tokens
120
Input
324
Total output
317
Reasoning within output
rebase f003
100%
Passed
Tokens
99
Input
387
Total output
384
Reasoning within output
rebase f004
100%
Passed
Tokens
164
Input
5,302
Total output
5,276
Reasoning within output
rebase f005
100%
Passed
Tokens
148
Input
2,138
Total output
2,122
Reasoning within output
rebase f006
100%
Passed
Tokens
140
Input
651
Total output
629
Reasoning within output
rebase f007
100%
Passed
Tokens
135
Input
471
Total output
461
Reasoning within output
rebase f008
100%
Passed
Tokens
121
Input
515
Total output
509
Reasoning within output
rebase f009
100%
Passed
Tokens
100
Input
241
Total output
236
Reasoning within output
rebase f010
100%
Passed
Tokens
217
Input
1,483
Total output
1,453
Reasoning within output
rebase f011
100%
Passed
Tokens
155
Input
948
Total output
925
Reasoning within output
rebase f012
0%
Failed
Tokens
239
Input
3,328
Total output
0
Reasoning within output
reflog f001
100%
Passed
Tokens
255
Input
694
Total output
655
Reasoning within output
reflog f002
100%
Passed
Tokens
235
Input
595
Total output
466
Reasoning within output
reflog f003
100%
Passed
Tokens
210
Input
499
Total output
374
Reasoning within output
reflog f004
100%
Passed
Tokens
328
Input
1,360
Total output
1,069
Reasoning within output
reflog f005
100%
Passed
Tokens
391
Input
654
Total output
539
Reasoning within output
reflog f006
100%
Passed
Tokens
258
Input
741
Total output
553
Reasoning within output
reflog f007
100%
Passed
Tokens
291
Input
679
Total output
513
Reasoning within output
reflog f008
100%
Passed
Tokens
386
Input
858
Total output
690
Reasoning within output
reflog f009
100%
Passed
Tokens
345
Input
1,171
Total output
951
Reasoning within output
reflog f010
100%
Passed
Tokens
284
Input
949
Total output
742
Reasoning within output
reflog f011
100%
Passed
Tokens
349
Input
2,193
Total output
1,816
Reasoning within output
reflog f012
100%
Passed
Tokens
331
Input
1,451
Total output
1,207
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
136
Input
244
Total output
239
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
316
Input
345
Total output
309
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
127
Input
205
Total output
191
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
120
Input
220
Total output
209
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
131
Input
256
Total output
196
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
196
Input
164
Total output
150
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
220
Input
183
Total output
167
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
192
Input
222
Total output
211
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
222
Input
319
Total output
270
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
128
Input
166
Total output
155
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
123
Input
230
Total output
225
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
143
Input
180
Total output
175
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
36
Input
194
Total output
186
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
99
Input
12,827
Total output
12,820
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
106
Input
1,353
Total output
1,330
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
92
Input
362
Total output
359
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
43
Input
7,570
Total output
7,548
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
91
Input
732
Total output
729
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
43
Input
266
Total output
249
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
98
Input
228
Total output
223
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
97
Input
159
Total output
156
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
104
Input
527
Total output
522
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
107
Input
185
Total output
181
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
41
Input
300
Total output
289
Reasoning within output
tag_management f001
100%
Passed
Tokens
57
Input
163
Total output
157
Reasoning within output
tag_management f002
100%
Passed
Tokens
53
Input
264
Total output
247
Reasoning within output
tag_management f003
100%
Passed
Tokens
62
Input
109
Total output
99
Reasoning within output
tag_management f004
100%
Passed
Tokens
64
Input
151
Total output
149
Reasoning within output
tag_management f005
100%
Passed
Tokens
79
Input
167
Total output
160
Reasoning within output
tag_management f006
100%
Passed
Tokens
62
Input
187
Total output
174
Reasoning within output
tag_management f007
100%
Passed
Tokens
60
Input
651
Total output
640
Reasoning within output
tag_management f008
100%
Passed
Tokens
64
Input
552
Total output
529
Reasoning within output
tag_management f009
100%
Passed
Tokens
68
Input
341
Total output
325
Reasoning within output
tag_management f010
100%
Passed
Tokens
44
Input
156
Total output
149
Reasoning within output
tag_management f011
100%
Passed
Tokens
46
Input
205
Total output
200
Reasoning within output
tag_management f012
100%
Passed
Tokens
83
Input
362
Total output
353
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
149
Input
219
Total output
210
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
154
Input
1,188
Total output
1,165
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
235
Input
179
Total output
171
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
241
Input
198
Total output
194
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
141
Input
234
Total output
221
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
143
Input
265
Total output
252
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
147
Input
1,529
Total output
1,506
Reasoning within output
worktree_usage f008
100%
Passed
Tokens
167
Input
14,408
Total output
14,356
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
274
Input
232
Total output
228
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
240
Input
250
Total output
235
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
234
Input
216
Total output
208
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
142
Input
545
Total output
532
Reasoning within output