Google / gemma-4-26b-a4b-it
medium
97.1%
198 / 204 fixtures · 1 run(s)
43,879 input / 137,619 total output / 117,267 reasoning within output tokens $0.05925484
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-3.9%
Text: 97.1% →
JSON: 93.1%
+1
Gained
JSON pass / text fail
−9
Lost
Text pass / JSON fail
189
Unchanged Pass
Both pass
5
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| worktree_usage | 100% | 83.3% | -16.7% |
| rebase | 91.7% | 83.3% | -8.3% |
| cherry_pick | 83.3% | 75% | -8.3% |
| commit_messages | 100% | 91.7% | -8.3% |
| git_clean | 100% | 91.7% | -8.3% |
| reflog | 100% | 91.7% | -8.3% |
| stash_recovery | 100% | 91.7% | -8.3% |
| blame_forensics | 100% | 100% | + 0% |
| branch_cleanup | 100% | 100% | + 0% |
| commit_squash | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_grep | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 91.7% | 91.7% | + 0% |
| merge_conflicts | 83.3% | 83.3% | + 0% |
| submodule_usage | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
Changed Fixtures (10)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
278
Input
733
Total output
628
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
272
Input
597
Total output
496
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
309
Input
296
Total output
201
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
225
Input
2,342
Total output
2,009
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
282
Input
910
Total output
736
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
262
Input
1,282
Total output
947
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
234
Input
366
Total output
290
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
275
Input
557
Total output
553
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
229
Input
496
Total output
376
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
483
Input
953
Total output
814
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
280
Input
413
Total output
316
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
168
Input
898
Total output
893
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
117
Input
357
Total output
352
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
131
Input
333
Total output
246
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
109
Input
616
Total output
533
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
145
Input
340
Total output
263
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
119
Input
283
Total output
222
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
141
Input
356
Total output
285
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
117
Input
261
Total output
253
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
132
Input
346
Total output
269
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
94
Input
232
Total output
211
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
128
Input
416
Total output
340
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
79
Input
286
Total output
284
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
172
Input
470
Total output
358
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
108
Input
811
Total output
782
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
129
Input
278
Total output
225
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
102
Input
798
Total output
796
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
180
Input
7,376
Total output
6,319
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
170
Input
388
Total output
367
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
156
Input
655
Total output
491
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
150
Input
295
Total output
284
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
141
Input
159
Total output
152
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
120
Input
199
Total output
175
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
247
Input
3,532
Total output
3,283
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
181
Input
409
Total output
311
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
301
Input
3,082
Total output
2,711
Reasoning within output
commit_messages f001
93.3%
Passed
Tokens
127
Input
294
Total output
230
Reasoning within output
commit_messages f002
91.7%
Passed
Tokens
260
Input
357
Total output
314
Reasoning within output
commit_messages f003
94.3%
Passed
Tokens
98
Input
293
Total output
226
Reasoning within output
commit_messages f004
93.3%
Passed
Tokens
134
Input
267
Total output
262
Reasoning within output
commit_messages f005
89.7%
Passed
Tokens
125
Input
545
Total output
533
Reasoning within output
commit_messages f006
91.7%
Passed
Tokens
167
Input
504
Total output
436
Reasoning within output
commit_messages f007
93.3%
Passed
Tokens
224
Input
456
Total output
388
Reasoning within output
commit_messages f008
89.3%
Passed
Tokens
92
Input
317
Total output
253
Reasoning within output
commit_messages f009
81.7%
Passed
Tokens
149
Input
682
Total output
616
Reasoning within output
commit_messages f010
91%
Passed
Tokens
348
Input
424
Total output
373
Reasoning within output
commit_messages f011
88.7%
Passed
Tokens
168
Input
950
Total output
898
Reasoning within output
commit_messages f012
93.3%
Passed
Tokens
146
Input
540
Total output
534
Reasoning within output
commit_squash f001
100%
Passed
Tokens
152
Input
4,430
Total output
3,719
Reasoning within output
commit_squash f002
100%
Passed
Tokens
130
Input
308
Total output
248
Reasoning within output
commit_squash f003
100%
Passed
Tokens
140
Input
1,291
Total output
1,060
Reasoning within output
commit_squash f004
100%
Passed
Tokens
125
Input
395
Total output
330
Reasoning within output
commit_squash f005
100%
Passed
Tokens
127
Input
941
Total output
834
Reasoning within output
commit_squash f006
100%
Passed
Tokens
113
Input
319
Total output
275
Reasoning within output
commit_squash f007
100%
Passed
Tokens
113
Input
360
Total output
290
Reasoning within output
commit_squash f008
100%
Passed
Tokens
126
Input
492
Total output
420
Reasoning within output
commit_squash f009
100%
Passed
Tokens
118
Input
693
Total output
568
Reasoning within output
commit_squash f010
100%
Passed
Tokens
135
Input
371
Total output
320
Reasoning within output
commit_squash f011
100%
Passed
Tokens
138
Input
321
Total output
251
Reasoning within output
commit_squash f012
100%
Passed
Tokens
137
Input
724
Total output
703
Reasoning within output
git_bisect f001
100%
Passed
Tokens
196
Input
158
Total output
119
Reasoning within output
git_bisect f002
100%
Passed
Tokens
231
Input
365
Total output
266
Reasoning within output
git_bisect f003
100%
Passed
Tokens
221
Input
264
Total output
256
Reasoning within output
git_bisect f004
100%
Passed
Tokens
233
Input
227
Total output
150
Reasoning within output
git_bisect f005
100%
Passed
Tokens
224
Input
232
Total output
160
Reasoning within output
git_bisect f006
100%
Passed
Tokens
250
Input
251
Total output
166
Reasoning within output
git_bisect f007
100%
Passed
Tokens
221
Input
282
Total output
276
Reasoning within output
git_bisect f008
100%
Passed
Tokens
227
Input
260
Total output
252
Reasoning within output
git_bisect f009
100%
Passed
Tokens
220
Input
298
Total output
208
Reasoning within output
git_bisect f010
100%
Passed
Tokens
227
Input
226
Total output
218
Reasoning within output
git_bisect f011
100%
Passed
Tokens
227
Input
192
Total output
116
Reasoning within output
git_bisect f012
100%
Passed
Tokens
250
Input
505
Total output
371
Reasoning within output
git_clean f001
100%
Passed
Tokens
66
Input
549
Total output
487
Reasoning within output
git_clean f002
100%
Passed
Tokens
78
Input
251
Total output
222
Reasoning within output
git_clean f003
100%
Passed
Tokens
78
Input
298
Total output
272
Reasoning within output
git_clean f004
100%
Passed
Tokens
78
Input
937
Total output
875
Reasoning within output
git_clean f005
100%
Passed
Tokens
64
Input
243
Total output
212
Reasoning within output
git_clean f006
100%
Passed
Tokens
96
Input
524
Total output
517
Reasoning within output
git_clean f007
100%
Passed
Tokens
84
Input
313
Total output
271
Reasoning within output
git_clean f008
100%
Passed
Tokens
93
Input
376
Total output
332
Reasoning within output
git_clean f009
100%
Passed
Tokens
88
Input
643
Total output
577
Reasoning within output
git_clean f010
100%
Passed
Tokens
80
Input
262
Total output
237
Reasoning within output
git_clean f011
100%
Passed
Tokens
80
Input
1,322
Total output
1,212
Reasoning within output
git_clean f012
100%
Passed
Tokens
85
Input
637
Total output
629
Reasoning within output
git_grep f001
100%
Passed
Tokens
64
Input
206
Total output
172
Reasoning within output
git_grep f002
100%
Passed
Tokens
77
Input
145
Total output
109
Reasoning within output
git_grep f003
100%
Passed
Tokens
115
Input
197
Total output
142
Reasoning within output
git_grep f004
100%
Passed
Tokens
92
Input
320
Total output
244
Reasoning within output
git_grep f005
100%
Passed
Tokens
130
Input
219
Total output
217
Reasoning within output
git_grep f006
100%
Passed
Tokens
49
Input
1,551
Total output
1,544
Reasoning within output
git_grep f007
100%
Passed
Tokens
192
Input
1,698
Total output
1,189
Reasoning within output
git_grep f008
100%
Passed
Tokens
72
Input
177
Total output
149
Reasoning within output
git_grep f009
100%
Passed
Tokens
65
Input
220
Total output
171
Reasoning within output
git_grep f010
100%
Passed
Tokens
79
Input
189
Total output
150
Reasoning within output
git_grep f011
100%
Passed
Tokens
142
Input
270
Total output
193
Reasoning within output
git_grep f012
100%
Passed
Tokens
80
Input
241
Total output
169
Reasoning within output
git_log_format f001
100%
Passed
Tokens
930
Input
566
Total output
564
Reasoning within output
git_log_format f002
100%
Passed
Tokens
946
Input
625
Total output
395
Reasoning within output
git_log_format f003
100%
Passed
Tokens
745
Input
375
Total output
325
Reasoning within output
git_log_format f004
100%
Passed
Tokens
911
Input
628
Total output
368
Reasoning within output
git_log_format f005
100%
Passed
Tokens
762
Input
691
Total output
568
Reasoning within output
git_log_format f006
100%
Passed
Tokens
950
Input
408
Total output
206
Reasoning within output
git_log_format f007
100%
Passed
Tokens
910
Input
283
Total output
217
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,252
Input
258
Total output
174
Reasoning within output
git_log_format f009
100%
Passed
Tokens
745
Input
405
Total output
304
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,476
Input
500
Total output
424
Reasoning within output
git_log_format f011
100%
Passed
Tokens
449
Input
285
Total output
187
Reasoning within output
git_log_format f012
100%
Passed
Tokens
418
Input
300
Total output
241
Reasoning within output
git_show f001
100%
Passed
Tokens
206
Input
396
Total output
288
Reasoning within output
git_show f002
0%
Failed
Tokens
222
Input
1,688
Total output
1,429
Reasoning within output
git_show f003
100%
Passed
Tokens
734
Input
312
Total output
213
Reasoning within output
git_show f004
100%
Passed
Tokens
502
Input
318
Total output
220
Reasoning within output
git_show f005
100%
Passed
Tokens
227
Input
384
Total output
381
Reasoning within output
git_show f006
100%
Passed
Tokens
228
Input
241
Total output
202
Reasoning within output
git_show f007
100%
Passed
Tokens
219
Input
273
Total output
267
Reasoning within output
git_show f008
100%
Passed
Tokens
225
Input
477
Total output
440
Reasoning within output
git_show f009
100%
Passed
Tokens
334
Input
582
Total output
402
Reasoning within output
git_show f010
100%
Passed
Tokens
220
Input
414
Total output
333
Reasoning within output
git_show f011
100%
Passed
Tokens
246
Input
265
Total output
221
Reasoning within output
git_show f012
100%
Passed
Tokens
377
Input
352
Total output
350
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
98
Input
2,187
Total output
2,103
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
116
Input
749
Total output
705
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
89
Input
1,334
Total output
1,330
Reasoning within output
merge_conflicts f004
0%
Failed
Tokens
166
Input
8,252
Total output
7,032
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
156
Input
836
Total output
815
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
142
Input
1,312
Total output
1,064
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
152
Input
339
Total output
275
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
123
Input
145
Total output
138
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
115
Input
267
Total output
245
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
205
Input
1,015
Total output
880
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
159
Input
512
Total output
458
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
262
Input
1,526
Total output
1,281
Reasoning within output
rebase f001
100%
Passed
Tokens
111
Input
3,654
Total output
3,649
Reasoning within output
rebase f002
100%
Passed
Tokens
137
Input
271
Total output
241
Reasoning within output
rebase f003
100%
Passed
Tokens
116
Input
702
Total output
683
Reasoning within output
rebase f004
100%
Passed
Tokens
178
Input
688
Total output
549
Reasoning within output
rebase f005
100%
Passed
Tokens
161
Input
1,058
Total output
1,078
Reasoning within output
rebase f006
100%
Passed
Tokens
158
Input
902
Total output
683
Reasoning within output
rebase f007
100%
Passed
Tokens
151
Input
284
Total output
219
Reasoning within output
rebase f008
100%
Passed
Tokens
136
Input
562
Total output
514
Reasoning within output
rebase f009
100%
Passed
Tokens
117
Input
345
Total output
306
Reasoning within output
rebase f010
100%
Passed
Tokens
235
Input
2,469
Total output
2,497
Reasoning within output
rebase f011
100%
Passed
Tokens
170
Input
1,131
Total output
961
Reasoning within output
rebase f012
0%
Failed
Tokens
300
Input
1,530
Total output
1,214
Reasoning within output
reflog f001
100%
Passed
Tokens
258
Input
621
Total output
386
Reasoning within output
reflog f002
100%
Passed
Tokens
258
Input
643
Total output
285
Reasoning within output
reflog f003
100%
Passed
Tokens
219
Input
540
Total output
302
Reasoning within output
reflog f004
100%
Passed
Tokens
358
Input
1,162
Total output
516
Reasoning within output
reflog f005
100%
Passed
Tokens
415
Input
553
Total output
272
Reasoning within output
reflog f006
100%
Passed
Tokens
274
Input
459
Total output
243
Reasoning within output
reflog f007
100%
Passed
Tokens
305
Input
771
Total output
341
Reasoning within output
reflog f008
100%
Passed
Tokens
407
Input
848
Total output
429
Reasoning within output
reflog f009
100%
Passed
Tokens
367
Input
973
Total output
658
Reasoning within output
reflog f010
100%
Passed
Tokens
300
Input
550
Total output
309
Reasoning within output
reflog f011
100%
Passed
Tokens
374
Input
1,238
Total output
921
Reasoning within output
reflog f012
100%
Passed
Tokens
352
Input
1,068
Total output
591
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
152
Input
212
Total output
189
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
329
Input
213
Total output
174
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
143
Input
197
Total output
169
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
135
Input
181
Total output
157
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
147
Input
199
Total output
173
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
212
Input
233
Total output
188
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
232
Input
166
Total output
125
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
207
Input
220
Total output
170
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
238
Input
248
Total output
215
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
144
Input
129
Total output
114
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
138
Input
400
Total output
380
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
159
Input
162
Total output
127
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
52
Input
132
Total output
107
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
117
Input
1,047
Total output
1,085
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
122
Input
1,115
Total output
1,012
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
110
Input
137
Total output
137
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
59
Input
1,402
Total output
1,344
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
106
Input
835
Total output
836
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
59
Input
175
Total output
127
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
116
Input
252
Total output
215
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
114
Input
239
Total output
222
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
119
Input
544
Total output
535
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
120
Input
233
Total output
196
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
57
Input
184
Total output
147
Reasoning within output
tag_management f001
100%
Passed
Tokens
73
Input
172
Total output
144
Reasoning within output
tag_management f002
100%
Passed
Tokens
68
Input
242
Total output
189
Reasoning within output
tag_management f003
100%
Passed
Tokens
77
Input
227
Total output
197
Reasoning within output
tag_management f004
100%
Passed
Tokens
82
Input
251
Total output
213
Reasoning within output
tag_management f005
100%
Passed
Tokens
95
Input
387
Total output
322
Reasoning within output
tag_management f006
100%
Passed
Tokens
80
Input
603
Total output
448
Reasoning within output
tag_management f007
100%
Passed
Tokens
75
Input
210
Total output
160
Reasoning within output
tag_management f008
100%
Passed
Tokens
79
Input
559
Total output
535
Reasoning within output
tag_management f009
100%
Passed
Tokens
84
Input
275
Total output
210
Reasoning within output
tag_management f010
100%
Passed
Tokens
60
Input
165
Total output
128
Reasoning within output
tag_management f011
100%
Passed
Tokens
63
Input
189
Total output
188
Reasoning within output
tag_management f012
100%
Passed
Tokens
102
Input
2,028
Total output
2,018
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
168
Input
180
Total output
170
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
172
Input
467
Total output
401
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
251
Input
390
Total output
336
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
251
Input
138
Total output
133
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
156
Input
294
Total output
215
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
159
Input
407
Total output
345
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
165
Input
870
Total output
691
Reasoning within output
worktree_usage f008
100%
Passed
Tokens
191
Input
3,260
Total output
3,207
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
284
Input
210
Total output
207
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
262
Input
487
Total output
402
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
251
Input
562
Total output
498
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
158
Input
226
Total output
172
Reasoning within output