Google / gemini-3.8-flash
high
95.6%
195 / 204 fixtures · 1 run(s)
40,311 input / 269,663 total output / 256,052 reasoning within output tokens $1.00561050
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-0.5%
Text: 95.6% →
JSON: 95.1%
+4
Gained
JSON pass / text fail
−5
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 | 91.7% | 75% | -16.7% |
| rebase | 91.7% | 83.3% | -8.3% |
| commit_squash | 91.7% | 100% | + 8.3% |
| reflog | 100% | 91.7% | -8.3% |
| tag_management | 91.7% | 100% | + 8.3% |
| worktree_usage | 91.7% | 100% | + 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_grep | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 100% | 100% | + 0% |
| merge_conflicts | 91.7% | 91.7% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 100% | 100% | + 0% |
Changed Fixtures (9)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
260
Input
785
Total output
781
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
258
Input
391
Total output
387
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
293
Input
285
Total output
279
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
210
Input
412
Total output
407
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
267
Input
2,900
Total output
2,895
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
247
Input
656
Total output
653
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
220
Input
303
Total output
299
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
260
Input
390
Total output
387
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
213
Input
484
Total output
481
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
462
Input
415
Total output
412
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
268
Input
332
Total output
329
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
151
Input
472
Total output
468
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
96
Input
311
Total output
307
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
117
Input
367
Total output
360
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
93
Input
290
Total output
289
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
132
Input
385
Total output
378
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
102
Input
365
Total output
361
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
128
Input
327
Total output
317
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
104
Input
283
Total output
276
Reasoning within output
branch_cleanup f008
0%
Failed
Tokens
0
Input
0
Total output
0
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
77
Input
285
Total output
284
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
113
Input
290
Total output
285
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
64
Input
216
Total output
215
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
153
Input
442
Total output
430
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
95
Input
261
Total output
257
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
114
Input
912
Total output
905
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
83
Input
801
Total output
798
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
163
Input
2,087
Total output
2,063
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
154
Input
309
Total output
289
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
141
Input
655
Total output
633
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
131
Input
520
Total output
510
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
126
Input
244
Total output
238
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
105
Input
155
Total output
150
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
231
Input
1,771
Total output
1,741
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
165
Input
299
Total output
276
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
284
Input
52,634
Total output
52,587
Reasoning within output
commit_messages f001
89%
Passed
Tokens
112
Input
772
Total output
766
Reasoning within output
commit_messages f002
90%
Passed
Tokens
245
Input
570
Total output
566
Reasoning within output
commit_messages f003
94%
Passed
Tokens
83
Input
292
Total output
282
Reasoning within output
commit_messages f004
92.5%
Passed
Tokens
118
Input
254
Total output
250
Reasoning within output
commit_messages f005
77.5%
Passed
Tokens
109
Input
375
Total output
369
Reasoning within output
commit_messages f006
90%
Passed
Tokens
151
Input
409
Total output
403
Reasoning within output
commit_messages f007
90%
Passed
Tokens
209
Input
397
Total output
391
Reasoning within output
commit_messages f008
91.5%
Passed
Tokens
76
Input
416
Total output
411
Reasoning within output
commit_messages f009
82.5%
Passed
Tokens
133
Input
743
Total output
737
Reasoning within output
commit_messages f010
91.5%
Passed
Tokens
332
Input
481
Total output
475
Reasoning within output
commit_messages f011
72.5%
Passed
Tokens
153
Input
1,154
Total output
1,142
Reasoning within output
commit_messages f012
89%
Passed
Tokens
130
Input
337
Total output
332
Reasoning within output
commit_squash f001
100%
Passed
Tokens
135
Input
24,405
Total output
24,392
Reasoning within output
commit_squash f002
100%
Passed
Tokens
115
Input
249
Total output
240
Reasoning within output
commit_squash f003
100%
Passed
Tokens
125
Input
26,499
Total output
26,486
Reasoning within output
commit_squash f004
100%
Passed
Tokens
110
Input
592
Total output
581
Reasoning within output
commit_squash f005
100%
Passed
Tokens
110
Input
4,292
Total output
4,285
Reasoning within output
commit_squash f006
100%
Passed
Tokens
94
Input
295
Total output
284
Reasoning within output
commit_squash f007
100%
Passed
Tokens
100
Input
384
Total output
372
Reasoning within output
commit_squash f008
100%
Passed
Tokens
110
Input
396
Total output
384
Reasoning within output
commit_squash f009
100%
Passed
Tokens
101
Input
1,409
Total output
1,398
Reasoning within output
commit_squash f010
0%
Failed
Tokens
0
Input
0
Total output
0
Reasoning within output
commit_squash f011
100%
Passed
Tokens
124
Input
3,074
Total output
3,059
Reasoning within output
commit_squash f012
100%
Passed
Tokens
123
Input
395
Total output
375
Reasoning within output
git_bisect f001
100%
Passed
Tokens
183
Input
167
Total output
161
Reasoning within output
git_bisect f002
100%
Passed
Tokens
211
Input
195
Total output
189
Reasoning within output
git_bisect f003
100%
Passed
Tokens
203
Input
139
Total output
134
Reasoning within output
git_bisect f004
100%
Passed
Tokens
213
Input
204
Total output
198
Reasoning within output
git_bisect f005
100%
Passed
Tokens
215
Input
206
Total output
200
Reasoning within output
git_bisect f006
100%
Passed
Tokens
233
Input
148
Total output
142
Reasoning within output
git_bisect f007
100%
Passed
Tokens
213
Input
199
Total output
192
Reasoning within output
git_bisect f008
100%
Passed
Tokens
209
Input
219
Total output
212
Reasoning within output
git_bisect f009
100%
Passed
Tokens
207
Input
190
Total output
184
Reasoning within output
git_bisect f010
100%
Passed
Tokens
215
Input
393
Total output
386
Reasoning within output
git_bisect f011
100%
Passed
Tokens
211
Input
155
Total output
150
Reasoning within output
git_bisect f012
100%
Passed
Tokens
243
Input
234
Total output
228
Reasoning within output
git_clean f001
100%
Passed
Tokens
51
Input
359
Total output
350
Reasoning within output
git_clean f002
100%
Passed
Tokens
62
Input
237
Total output
233
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
355
Total output
350
Reasoning within output
git_clean f005
100%
Passed
Tokens
49
Input
413
Total output
409
Reasoning within output
git_clean f006
100%
Passed
Tokens
80
Input
637
Total output
632
Reasoning within output
git_clean f007
100%
Passed
Tokens
69
Input
337
Total output
328
Reasoning within output
git_clean f008
100%
Passed
Tokens
77
Input
207
Total output
203
Reasoning within output
git_clean f009
100%
Passed
Tokens
73
Input
9,977
Total output
9,968
Reasoning within output
git_clean f010
100%
Passed
Tokens
64
Input
394
Total output
390
Reasoning within output
git_clean f011
100%
Passed
Tokens
64
Input
550
Total output
545
Reasoning within output
git_clean f012
100%
Passed
Tokens
69
Input
391
Total output
384
Reasoning within output
git_grep f001
100%
Passed
Tokens
49
Input
176
Total output
171
Reasoning within output
git_grep f002
100%
Passed
Tokens
58
Input
191
Total output
190
Reasoning within output
git_grep f003
100%
Passed
Tokens
100
Input
256
Total output
255
Reasoning within output
git_grep f004
100%
Passed
Tokens
76
Input
248
Total output
243
Reasoning within output
git_grep f005
100%
Passed
Tokens
114
Input
333
Total output
332
Reasoning within output
git_grep f006
100%
Passed
Tokens
33
Input
404
Total output
403
Reasoning within output
git_grep f007
100%
Passed
Tokens
176
Input
962
Total output
960
Reasoning within output
git_grep f008
100%
Passed
Tokens
56
Input
209
Total output
208
Reasoning within output
git_grep f009
100%
Passed
Tokens
49
Input
132
Total output
129
Reasoning within output
git_grep f010
100%
Passed
Tokens
63
Input
176
Total output
175
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
240
Total output
227
Reasoning within output
git_log_format f001
100%
Passed
Tokens
919
Input
150
Total output
149
Reasoning within output
git_log_format f002
100%
Passed
Tokens
915
Input
298
Total output
291
Reasoning within output
git_log_format f003
100%
Passed
Tokens
744
Input
301
Total output
292
Reasoning within output
git_log_format f004
100%
Passed
Tokens
921
Input
137
Total output
136
Reasoning within output
git_log_format f005
100%
Passed
Tokens
746
Input
443
Total output
438
Reasoning within output
git_log_format f006
100%
Passed
Tokens
934
Input
373
Total output
372
Reasoning within output
git_log_format f007
100%
Passed
Tokens
934
Input
114
Total output
108
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,246
Input
184
Total output
183
Reasoning within output
git_log_format f009
100%
Passed
Tokens
748
Input
225
Total output
224
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,444
Input
296
Total output
295
Reasoning within output
git_log_format f011
100%
Passed
Tokens
452
Input
186
Total output
183
Reasoning within output
git_log_format f012
100%
Passed
Tokens
419
Input
138
Total output
137
Reasoning within output
git_show f001
100%
Passed
Tokens
198
Input
190
Total output
185
Reasoning within output
git_show f002
100%
Passed
Tokens
202
Input
756
Total output
753
Reasoning within output
git_show f003
100%
Passed
Tokens
725
Input
399
Total output
393
Reasoning within output
git_show f004
100%
Passed
Tokens
490
Input
145
Total output
138
Reasoning within output
git_show f005
100%
Passed
Tokens
211
Input
234
Total output
232
Reasoning within output
git_show f006
100%
Passed
Tokens
216
Input
163
Total output
162
Reasoning within output
git_show f007
100%
Passed
Tokens
203
Input
132
Total output
127
Reasoning within output
git_show f008
100%
Passed
Tokens
211
Input
324
Total output
286
Reasoning within output
git_show f009
100%
Passed
Tokens
325
Input
172
Total output
171
Reasoning within output
git_show f010
100%
Passed
Tokens
200
Input
311
Total output
310
Reasoning within output
git_show f011
100%
Passed
Tokens
230
Input
178
Total output
175
Reasoning within output
git_show f012
100%
Passed
Tokens
363
Input
273
Total output
272
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
82
Input
840
Total output
836
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
100
Input
565
Total output
558
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
73
Input
1,484
Total output
1,481
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
150
Input
1,157
Total output
1,131
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
140
Input
458
Total output
438
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
126
Input
4,125
Total output
4,103
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
137
Input
495
Total output
485
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
107
Input
272
Total output
266
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
99
Input
352
Total output
347
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
190
Input
1,525
Total output
1,495
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
143
Input
495
Total output
472
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
216
Input
5,428
Total output
0
Reasoning within output
rebase f001
100%
Passed
Tokens
94
Input
635
Total output
631
Reasoning within output
rebase f002
100%
Passed
Tokens
121
Input
365
Total output
358
Reasoning within output
rebase f003
100%
Passed
Tokens
99
Input
311
Total output
308
Reasoning within output
rebase f004
100%
Passed
Tokens
164
Input
4,808
Total output
4,782
Reasoning within output
rebase f005
100%
Passed
Tokens
147
Input
2,062
Total output
2,046
Reasoning within output
rebase f006
100%
Passed
Tokens
140
Input
1,355
Total output
1,333
Reasoning within output
rebase f007
100%
Passed
Tokens
138
Input
354
Total output
344
Reasoning within output
rebase f008
100%
Passed
Tokens
120
Input
248
Total output
242
Reasoning within output
rebase f009
100%
Passed
Tokens
101
Input
374
Total output
369
Reasoning within output
rebase f010
100%
Passed
Tokens
223
Input
1,938
Total output
1,908
Reasoning within output
rebase f011
100%
Passed
Tokens
155
Input
1,084
Total output
1,061
Reasoning within output
rebase f012
0%
Failed
Tokens
278
Input
29,491
Total output
29,444
Reasoning within output
reflog f001
100%
Passed
Tokens
246
Input
615
Total output
578
Reasoning within output
reflog f002
100%
Passed
Tokens
234
Input
561
Total output
438
Reasoning within output
reflog f003
100%
Passed
Tokens
211
Input
585
Total output
470
Reasoning within output
reflog f004
100%
Passed
Tokens
337
Input
1,656
Total output
1,345
Reasoning within output
reflog f005
100%
Passed
Tokens
398
Input
623
Total output
492
Reasoning within output
reflog f006
100%
Passed
Tokens
253
Input
709
Total output
492
Reasoning within output
reflog f007
100%
Passed
Tokens
295
Input
745
Total output
482
Reasoning within output
reflog f008
100%
Passed
Tokens
379
Input
823
Total output
629
Reasoning within output
reflog f009
100%
Passed
Tokens
333
Input
1,680
Total output
1,411
Reasoning within output
reflog f010
100%
Passed
Tokens
281
Input
1,491
Total output
1,247
Reasoning within output
reflog f011
100%
Passed
Tokens
340
Input
1,528
Total output
1,284
Reasoning within output
reflog f012
100%
Passed
Tokens
336
Input
1,154
Total output
938
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
137
Input
152
Total output
147
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
313
Input
286
Total output
245
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
127
Input
212
Total output
201
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
120
Input
216
Total output
211
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
130
Input
239
Total output
190
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
196
Input
222
Total output
208
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
216
Input
187
Total output
182
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
192
Input
183
Total output
169
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
222
Input
303
Total output
255
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
128
Input
180
Total output
166
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
123
Input
207
Total output
202
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
143
Input
208
Total output
194
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
36
Input
156
Total output
148
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
99
Input
6,113
Total output
6,104
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
106
Input
1,616
Total output
1,593
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
92
Input
197
Total output
194
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
43
Input
3,083
Total output
3,061
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
91
Input
950
Total output
947
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
43
Input
457
Total output
440
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
95
Input
759
Total output
754
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
95
Input
190
Total output
187
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
101
Input
308
Total output
303
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
109
Input
146
Total output
142
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
41
Input
237
Total output
226
Reasoning within output
tag_management f001
100%
Passed
Tokens
54
Input
189
Total output
183
Reasoning within output
tag_management f002
100%
Passed
Tokens
52
Input
368
Total output
351
Reasoning within output
tag_management f003
100%
Passed
Tokens
62
Input
187
Total output
177
Reasoning within output
tag_management f004
100%
Passed
Tokens
67
Input
197
Total output
195
Reasoning within output
tag_management f005
100%
Passed
Tokens
78
Input
402
Total output
395
Reasoning within output
tag_management f006
100%
Passed
Tokens
65
Input
231
Total output
217
Reasoning within output
tag_management f007
100%
Passed
Tokens
59
Input
578
Total output
567
Reasoning within output
tag_management f008
100%
Passed
Tokens
64
Input
338
Total output
315
Reasoning within output
tag_management f009
100%
Passed
Tokens
67
Input
399
Total output
383
Reasoning within output
tag_management f010
100%
Passed
Tokens
44
Input
123
Total output
116
Reasoning within output
tag_management f011
100%
Passed
Tokens
48
Input
253
Total output
248
Reasoning within output
tag_management f012
50%
Failed
Tokens
0
Input
0
Total output
0
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
148
Input
190
Total output
181
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
154
Input
814
Total output
793
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
232
Input
210
Total output
202
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
235
Input
1,808
Total output
1,801
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
142
Input
298
Total output
285
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
141
Input
745
Total output
732
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
151
Input
1,074
Total output
1,051
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
106
Input
4,070
Total output
0
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
265
Input
154
Total output
150
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
242
Input
243
Total output
228
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
228
Input
127
Total output
119
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
147
Input
999
Total output
986
Reasoning within output