Google / gemma-4-26b-a4b-it
xhigh
93.6%
191 / 204 fixtures · 1 run(s)
43,814 input / 129,737 total output / 108,480 reasoning within output tokens $0.05029070
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
+1.5%
Text: 93.6% →
JSON: 95.1%
+6
Gained
JSON pass / text fail
−3
Lost
Text pass / JSON fail
188
Unchanged Pass
Both pass
7
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| worktree_usage | 83.3% | 100% | + 16.7% |
| git_clean | 83.3% | 91.7% | + 8.3% |
| cherry_pick | 83.3% | 75% | -8.3% |
| git_grep | 91.7% | 100% | + 8.3% |
| reflog | 100% | 91.7% | -8.3% |
| tag_management | 91.7% | 100% | + 8.3% |
| blame_forensics | 100% | 100% | + 0% |
| branch_cleanup | 100% | 100% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| commit_squash | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 91.7% | 91.7% | + 0% |
| merge_conflicts | 91.7% | 91.7% | + 0% |
| rebase | 75% | 75% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 100% | 100% | + 0% |
Changed Fixtures (9)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
274
Input
1,071
Total output
1,066
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
271
Input
861
Total output
685
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
311
Input
374
Total output
256
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
228
Input
647
Total output
529
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
288
Input
968
Total output
738
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
260
Input
923
Total output
661
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
236
Input
386
Total output
293
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
270
Input
980
Total output
976
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
230
Input
532
Total output
428
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
466
Input
812
Total output
689
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
284
Input
420
Total output
301
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
169
Input
812
Total output
675
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
117
Input
292
Total output
258
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
128
Input
394
Total output
310
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
109
Input
294
Total output
248
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
150
Input
371
Total output
283
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
118
Input
255
Total output
250
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
142
Input
349
Total output
270
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
118
Input
309
Total output
258
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
135
Input
391
Total output
302
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
92
Input
241
Total output
221
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
128
Input
315
Total output
256
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
79
Input
228
Total output
206
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
175
Input
359
Total output
291
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
108
Input
405
Total output
378
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
130
Input
397
Total output
389
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
101
Input
711
Total output
734
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
181
Input
2,737
Total output
2,712
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
170
Input
402
Total output
378
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
157
Input
517
Total output
424
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
146
Input
259
Total output
207
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
141
Input
175
Total output
168
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
122
Input
264
Total output
241
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
241
Input
1,648
Total output
1,538
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
180
Input
620
Total output
479
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
304
Input
3,246
Total output
2,758
Reasoning within output
commit_messages f001
94.3%
Passed
Tokens
128
Input
262
Total output
206
Reasoning within output
commit_messages f002
89.3%
Passed
Tokens
261
Input
669
Total output
632
Reasoning within output
commit_messages f003
90%
Passed
Tokens
99
Input
382
Total output
303
Reasoning within output
commit_messages f004
93.3%
Passed
Tokens
134
Input
283
Total output
239
Reasoning within output
commit_messages f005
86.7%
Passed
Tokens
125
Input
311
Total output
261
Reasoning within output
commit_messages f006
94.3%
Passed
Tokens
166
Input
820
Total output
553
Reasoning within output
commit_messages f007
92%
Passed
Tokens
225
Input
313
Total output
282
Reasoning within output
commit_messages f008
92.3%
Passed
Tokens
92
Input
233
Total output
186
Reasoning within output
commit_messages f009
91.7%
Passed
Tokens
149
Input
751
Total output
665
Reasoning within output
commit_messages f010
92.3%
Passed
Tokens
348
Input
402
Total output
394
Reasoning within output
commit_messages f011
57.7%
Passed
Tokens
169
Input
1,822
Total output
1,404
Reasoning within output
commit_messages f012
91.7%
Passed
Tokens
146
Input
277
Total output
278
Reasoning within output
commit_squash f001
100%
Passed
Tokens
151
Input
2,508
Total output
1,927
Reasoning within output
commit_squash f002
100%
Passed
Tokens
130
Input
396
Total output
318
Reasoning within output
commit_squash f003
100%
Passed
Tokens
141
Input
957
Total output
943
Reasoning within output
commit_squash f004
100%
Passed
Tokens
126
Input
626
Total output
614
Reasoning within output
commit_squash f005
100%
Passed
Tokens
125
Input
1,031
Total output
946
Reasoning within output
commit_squash f006
100%
Passed
Tokens
111
Input
490
Total output
412
Reasoning within output
commit_squash f007
100%
Passed
Tokens
113
Input
375
Total output
292
Reasoning within output
commit_squash f008
100%
Passed
Tokens
127
Input
829
Total output
816
Reasoning within output
commit_squash f009
100%
Passed
Tokens
119
Input
681
Total output
553
Reasoning within output
commit_squash f010
100%
Passed
Tokens
134
Input
555
Total output
539
Reasoning within output
commit_squash f011
100%
Passed
Tokens
141
Input
291
Total output
220
Reasoning within output
commit_squash f012
100%
Passed
Tokens
136
Input
642
Total output
532
Reasoning within output
git_bisect f001
100%
Passed
Tokens
197
Input
247
Total output
190
Reasoning within output
git_bisect f002
100%
Passed
Tokens
229
Input
357
Total output
259
Reasoning within output
git_bisect f003
100%
Passed
Tokens
225
Input
875
Total output
610
Reasoning within output
git_bisect f004
100%
Passed
Tokens
227
Input
302
Total output
185
Reasoning within output
git_bisect f005
100%
Passed
Tokens
225
Input
330
Total output
220
Reasoning within output
git_bisect f006
100%
Passed
Tokens
248
Input
364
Total output
238
Reasoning within output
git_bisect f007
100%
Passed
Tokens
223
Input
368
Total output
254
Reasoning within output
git_bisect f008
100%
Passed
Tokens
233
Input
310
Total output
220
Reasoning within output
git_bisect f009
100%
Passed
Tokens
215
Input
218
Total output
160
Reasoning within output
git_bisect f010
100%
Passed
Tokens
231
Input
403
Total output
395
Reasoning within output
git_bisect f011
100%
Passed
Tokens
227
Input
180
Total output
117
Reasoning within output
git_bisect f012
100%
Passed
Tokens
253
Input
314
Total output
205
Reasoning within output
git_clean f001
100%
Passed
Tokens
66
Input
709
Total output
699
Reasoning within output
git_clean f002
100%
Passed
Tokens
78
Input
232
Total output
205
Reasoning within output
git_clean f003
100%
Passed
Tokens
78
Input
187
Total output
152
Reasoning within output
git_clean f004
33.3%
Failed
Tokens
78
Input
287
Total output
253
Reasoning within output
git_clean f005
100%
Passed
Tokens
64
Input
299
Total output
265
Reasoning within output
git_clean f006
100%
Passed
Tokens
96
Input
1,069
Total output
912
Reasoning within output
git_clean f007
100%
Passed
Tokens
85
Input
370
Total output
318
Reasoning within output
git_clean f008
100%
Passed
Tokens
93
Input
277
Total output
234
Reasoning within output
git_clean f009
100%
Passed
Tokens
89
Input
603
Total output
518
Reasoning within output
git_clean f010
100%
Passed
Tokens
80
Input
250
Total output
245
Reasoning within output
git_clean f011
40%
Failed
Tokens
80
Input
428
Total output
375
Reasoning within output
git_clean f012
100%
Passed
Tokens
85
Input
421
Total output
332
Reasoning within output
git_grep f001
100%
Passed
Tokens
63
Input
195
Total output
163
Reasoning within output
git_grep f002
100%
Passed
Tokens
76
Input
146
Total output
144
Reasoning within output
git_grep f003
100%
Passed
Tokens
116
Input
211
Total output
157
Reasoning within output
git_grep f004
100%
Passed
Tokens
92
Input
186
Total output
138
Reasoning within output
git_grep f005
100%
Passed
Tokens
130
Input
231
Total output
180
Reasoning within output
git_grep f006
100%
Passed
Tokens
48
Input
1,013
Total output
1,042
Reasoning within output
git_grep f007
0%
Failed
Tokens
192
Input
3,354
Total output
2,350
Reasoning within output
git_grep f008
100%
Passed
Tokens
72
Input
174
Total output
172
Reasoning within output
git_grep f009
100%
Passed
Tokens
65
Input
166
Total output
162
Reasoning within output
git_grep f010
100%
Passed
Tokens
79
Input
293
Total output
250
Reasoning within output
git_grep f011
100%
Passed
Tokens
142
Input
531
Total output
402
Reasoning within output
git_grep f012
100%
Passed
Tokens
80
Input
261
Total output
179
Reasoning within output
git_log_format f001
100%
Passed
Tokens
943
Input
400
Total output
313
Reasoning within output
git_log_format f002
100%
Passed
Tokens
929
Input
664
Total output
511
Reasoning within output
git_log_format f003
100%
Passed
Tokens
751
Input
526
Total output
384
Reasoning within output
git_log_format f004
100%
Passed
Tokens
931
Input
839
Total output
837
Reasoning within output
git_log_format f005
100%
Passed
Tokens
762
Input
565
Total output
400
Reasoning within output
git_log_format f006
100%
Passed
Tokens
950
Input
676
Total output
277
Reasoning within output
git_log_format f007
100%
Passed
Tokens
938
Input
230
Total output
172
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,262
Input
225
Total output
223
Reasoning within output
git_log_format f009
100%
Passed
Tokens
776
Input
431
Total output
325
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,438
Input
560
Total output
492
Reasoning within output
git_log_format f011
100%
Passed
Tokens
465
Input
328
Total output
208
Reasoning within output
git_log_format f012
100%
Passed
Tokens
423
Input
328
Total output
238
Reasoning within output
git_show f001
100%
Passed
Tokens
213
Input
335
Total output
258
Reasoning within output
git_show f002
0%
Failed
Tokens
128
Input
22
Total output
22
Reasoning within output
git_show f003
100%
Passed
Tokens
745
Input
519
Total output
338
Reasoning within output
git_show f004
100%
Passed
Tokens
494
Input
317
Total output
235
Reasoning within output
git_show f005
100%
Passed
Tokens
227
Input
456
Total output
453
Reasoning within output
git_show f006
100%
Passed
Tokens
228
Input
215
Total output
177
Reasoning within output
git_show f007
100%
Passed
Tokens
218
Input
269
Total output
191
Reasoning within output
git_show f008
100%
Passed
Tokens
221
Input
307
Total output
173
Reasoning within output
git_show f009
100%
Passed
Tokens
338
Input
535
Total output
350
Reasoning within output
git_show f010
100%
Passed
Tokens
218
Input
312
Total output
310
Reasoning within output
git_show f011
100%
Passed
Tokens
242
Input
256
Total output
215
Reasoning within output
git_show f012
100%
Passed
Tokens
377
Input
482
Total output
341
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
98
Input
1,983
Total output
1,978
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
116
Input
774
Total output
704
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
89
Input
691
Total output
653
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
166
Input
1,168
Total output
994
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
156
Input
427
Total output
367
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
142
Input
1,075
Total output
861
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
152
Input
331
Total output
243
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
123
Input
164
Total output
129
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
115
Input
284
Total output
266
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
206
Input
1,136
Total output
1,006
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
159
Input
284
Total output
255
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
263
Input
8,627
Total output
8,579
Reasoning within output
rebase f001
100%
Passed
Tokens
112
Input
2,310
Total output
2,245
Reasoning within output
rebase f002
100%
Passed
Tokens
138
Input
210
Total output
183
Reasoning within output
rebase f003
100%
Passed
Tokens
116
Input
381
Total output
383
Reasoning within output
rebase f004
0%
Failed
Tokens
180
Input
2,146
Total output
1,719
Reasoning within output
rebase f005
100%
Passed
Tokens
163
Input
1,142
Total output
1,090
Reasoning within output
rebase f006
100%
Passed
Tokens
158
Input
1,596
Total output
1,573
Reasoning within output
rebase f007
100%
Passed
Tokens
153
Input
830
Total output
709
Reasoning within output
rebase f008
100%
Passed
Tokens
136
Input
232
Total output
198
Reasoning within output
rebase f009
100%
Passed
Tokens
117
Input
363
Total output
343
Reasoning within output
rebase f010
0%
Failed
Tokens
237
Input
525
Total output
494
Reasoning within output
rebase f011
100%
Passed
Tokens
171
Input
331
Total output
302
Reasoning within output
rebase f012
0%
Failed
Tokens
298
Input
4,777
Total output
4,095
Reasoning within output
reflog f001
100%
Passed
Tokens
253
Input
680
Total output
436
Reasoning within output
reflog f002
100%
Passed
Tokens
250
Input
936
Total output
558
Reasoning within output
reflog f003
100%
Passed
Tokens
220
Input
494
Total output
351
Reasoning within output
reflog f004
100%
Passed
Tokens
356
Input
1,070
Total output
577
Reasoning within output
reflog f005
100%
Passed
Tokens
411
Input
635
Total output
453
Reasoning within output
reflog f006
100%
Passed
Tokens
274
Input
702
Total output
315
Reasoning within output
reflog f007
100%
Passed
Tokens
303
Input
740
Total output
340
Reasoning within output
reflog f008
100%
Passed
Tokens
392
Input
905
Total output
451
Reasoning within output
reflog f009
100%
Passed
Tokens
363
Input
986
Total output
551
Reasoning within output
reflog f010
100%
Passed
Tokens
299
Input
704
Total output
349
Reasoning within output
reflog f011
100%
Passed
Tokens
363
Input
1,367
Total output
582
Reasoning within output
reflog f012
100%
Passed
Tokens
354
Input
954
Total output
568
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
151
Input
269
Total output
235
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
332
Input
242
Total output
218
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
143
Input
186
Total output
156
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
136
Input
190
Total output
154
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
146
Input
201
Total output
161
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
211
Input
198
Total output
147
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
234
Input
139
Total output
94
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
208
Input
209
Total output
175
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
238
Input
301
Total output
283
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
144
Input
171
Total output
141
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
137
Input
362
Total output
326
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
159
Input
193
Total output
165
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
52
Input
125
Total output
103
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
119
Input
861
Total output
868
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
125
Input
1,833
Total output
1,589
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
113
Input
144
Total output
147
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
59
Input
405
Total output
353
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
109
Input
667
Total output
663
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
59
Input
211
Total output
165
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
115
Input
146
Total output
136
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
110
Input
173
Total output
174
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
118
Input
607
Total output
624
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
120
Input
208
Total output
203
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
56
Input
181
Total output
147
Reasoning within output
tag_management f001
100%
Passed
Tokens
71
Input
109
Total output
102
Reasoning within output
tag_management f002
100%
Passed
Tokens
69
Input
164
Total output
118
Reasoning within output
tag_management f003
100%
Passed
Tokens
76
Input
270
Total output
259
Reasoning within output
tag_management f004
100%
Passed
Tokens
80
Input
167
Total output
164
Reasoning within output
tag_management f005
100%
Passed
Tokens
96
Input
207
Total output
144
Reasoning within output
tag_management f006
100%
Passed
Tokens
80
Input
1,608
Total output
1,316
Reasoning within output
tag_management f007
100%
Passed
Tokens
75
Input
242
Total output
217
Reasoning within output
tag_management f008
100%
Passed
Tokens
79
Input
1,173
Total output
1,074
Reasoning within output
tag_management f009
100%
Passed
Tokens
82
Input
272
Total output
212
Reasoning within output
tag_management f010
100%
Passed
Tokens
61
Input
121
Total output
92
Reasoning within output
tag_management f011
100%
Passed
Tokens
64
Input
162
Total output
153
Reasoning within output
tag_management f012
50%
Failed
Tokens
102
Input
2,915
Total output
2,298
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
162
Input
284
Total output
198
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
172
Input
559
Total output
427
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
253
Input
346
Total output
245
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
244
Input
176
Total output
161
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
158
Input
309
Total output
234
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
160
Input
471
Total output
377
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
165
Input
617
Total output
444
Reasoning within output
worktree_usage f008
50%
Failed
Tokens
184
Input
2,650
Total output
2,424
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
289
Input
140
Total output
141
Reasoning within output
worktree_usage f010
0%
Failed
Tokens
257
Input
284
Total output
268
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
250
Input
329
Total output
267
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
157
Input
151
Total output
104
Reasoning within output