Google / gemma-4-31b-it
xhigh
97.1%
198 / 204 fixtures · 1 run(s)
43,901 input / 69,727 total output / 41,886 reasoning within output tokens $0.03261417
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-6.4%
Text: 97.1% →
JSON: 90.7%
+0
Gained
JSON pass / text fail
−13
Lost
Text pass / JSON fail
185
Unchanged Pass
Both pass
6
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| blame_forensics | 100% | 83.3% | -16.7% |
| merge_conflicts | 91.7% | 75% | -16.7% |
| tag_management | 100% | 83.3% | -16.7% |
| rebase | 91.7% | 83.3% | -8.3% |
| worktree_usage | 91.7% | 83.3% | -8.3% |
| cherry_pick | 83.3% | 75% | -8.3% |
| commit_messages | 100% | 91.7% | -8.3% |
| git_bisect | 100% | 91.7% | -8.3% |
| git_clean | 100% | 91.7% | -8.3% |
| reflog | 100% | 91.7% | -8.3% |
| branch_cleanup | 100% | 100% | + 0% |
| commit_squash | 100% | 100% | + 0% |
| git_grep | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 91.7% | 91.7% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 100% | 100% | + 0% |
Changed Fixtures (13)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
278
Input
370
Total output
365
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
268
Input
318
Total output
240
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
309
Input
386
Total output
266
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
221
Input
525
Total output
451
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
289
Input
1,815
Total output
1,367
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
266
Input
648
Total output
644
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
233
Input
370
Total output
257
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
276
Input
485
Total output
431
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
228
Input
426
Total output
341
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
474
Input
424
Total output
337
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
284
Input
306
Total output
1
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
169
Input
294
Total output
253
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
117
Input
250
Total output
1
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
135
Input
241
Total output
1
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
108
Input
212
Total output
1
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
148
Input
226
Total output
1
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
120
Input
245
Total output
1
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
142
Input
260
Total output
1
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
121
Input
294
Total output
1
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
129
Input
211
Total output
1
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
94
Input
203
Total output
1
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
130
Input
179
Total output
1
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
80
Input
131
Total output
1
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
174
Input
347
Total output
1
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
109
Input
571
Total output
579
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
129
Input
207
Total output
162
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
100
Input
238
Total output
235
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
182
Input
1,600
Total output
1,404
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
169
Input
285
Total output
229
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
158
Input
220
Total output
126
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
149
Input
232
Total output
180
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
141
Input
145
Total output
117
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
119
Input
194
Total output
1
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
244
Input
435
Total output
377
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
181
Input
235
Total output
159
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
302
Input
561
Total output
398
Reasoning within output
commit_messages f001
92.7%
Passed
Tokens
128
Input
190
Total output
152
Reasoning within output
commit_messages f002
91%
Passed
Tokens
261
Input
246
Total output
1
Reasoning within output
commit_messages f003
92.3%
Passed
Tokens
99
Input
241
Total output
177
Reasoning within output
commit_messages f004
93%
Passed
Tokens
133
Input
110
Total output
95
Reasoning within output
commit_messages f005
85%
Passed
Tokens
125
Input
131
Total output
112
Reasoning within output
commit_messages f006
90%
Passed
Tokens
166
Input
201
Total output
178
Reasoning within output
commit_messages f007
91%
Passed
Tokens
224
Input
200
Total output
171
Reasoning within output
commit_messages f008
91.7%
Passed
Tokens
92
Input
226
Total output
175
Reasoning within output
commit_messages f009
82.7%
Passed
Tokens
149
Input
366
Total output
337
Reasoning within output
commit_messages f010
91%
Passed
Tokens
348
Input
269
Total output
213
Reasoning within output
commit_messages f011
79.3%
Passed
Tokens
169
Input
248
Total output
219
Reasoning within output
commit_messages f012
91.7%
Passed
Tokens
146
Input
231
Total output
218
Reasoning within output
commit_squash f001
100%
Passed
Tokens
150
Input
717
Total output
616
Reasoning within output
commit_squash f002
100%
Passed
Tokens
130
Input
305
Total output
244
Reasoning within output
commit_squash f003
100%
Passed
Tokens
140
Input
340
Total output
237
Reasoning within output
commit_squash f004
100%
Passed
Tokens
129
Input
542
Total output
458
Reasoning within output
commit_squash f005
100%
Passed
Tokens
126
Input
428
Total output
1
Reasoning within output
commit_squash f006
100%
Passed
Tokens
115
Input
424
Total output
412
Reasoning within output
commit_squash f007
100%
Passed
Tokens
109
Input
235
Total output
185
Reasoning within output
commit_squash f008
100%
Passed
Tokens
126
Input
272
Total output
213
Reasoning within output
commit_squash f009
100%
Passed
Tokens
121
Input
321
Total output
247
Reasoning within output
commit_squash f010
100%
Passed
Tokens
134
Input
235
Total output
193
Reasoning within output
commit_squash f011
100%
Passed
Tokens
138
Input
295
Total output
231
Reasoning within output
commit_squash f012
100%
Passed
Tokens
137
Input
415
Total output
311
Reasoning within output
git_bisect f001
100%
Passed
Tokens
196
Input
173
Total output
118
Reasoning within output
git_bisect f002
100%
Passed
Tokens
222
Input
205
Total output
138
Reasoning within output
git_bisect f003
100%
Passed
Tokens
222
Input
231
Total output
170
Reasoning within output
git_bisect f004
100%
Passed
Tokens
228
Input
272
Total output
194
Reasoning within output
git_bisect f005
100%
Passed
Tokens
226
Input
167
Total output
119
Reasoning within output
git_bisect f006
100%
Passed
Tokens
255
Input
361
Total output
1
Reasoning within output
git_bisect f007
100%
Passed
Tokens
225
Input
153
Total output
1
Reasoning within output
git_bisect f008
100%
Passed
Tokens
232
Input
190
Total output
124
Reasoning within output
git_bisect f009
100%
Passed
Tokens
227
Input
188
Total output
1
Reasoning within output
git_bisect f010
100%
Passed
Tokens
224
Input
151
Total output
104
Reasoning within output
git_bisect f011
100%
Passed
Tokens
230
Input
173
Total output
118
Reasoning within output
git_bisect f012
100%
Passed
Tokens
257
Input
219
Total output
1
Reasoning within output
git_clean f001
100%
Passed
Tokens
65
Input
226
Total output
202
Reasoning within output
git_clean f002
100%
Passed
Tokens
77
Input
139
Total output
124
Reasoning within output
git_clean f003
100%
Passed
Tokens
78
Input
159
Total output
1
Reasoning within output
git_clean f004
100%
Passed
Tokens
77
Input
230
Total output
199
Reasoning within output
git_clean f005
100%
Passed
Tokens
65
Input
242
Total output
1
Reasoning within output
git_clean f006
100%
Passed
Tokens
95
Input
239
Total output
205
Reasoning within output
git_clean f007
100%
Passed
Tokens
84
Input
186
Total output
155
Reasoning within output
git_clean f008
100%
Passed
Tokens
92
Input
122
Total output
113
Reasoning within output
git_clean f009
100%
Passed
Tokens
88
Input
219
Total output
186
Reasoning within output
git_clean f010
100%
Passed
Tokens
80
Input
116
Total output
1
Reasoning within output
git_clean f011
100%
Passed
Tokens
79
Input
349
Total output
315
Reasoning within output
git_clean f012
100%
Passed
Tokens
84
Input
348
Total output
287
Reasoning within output
git_grep f001
100%
Passed
Tokens
63
Input
160
Total output
134
Reasoning within output
git_grep f002
100%
Passed
Tokens
76
Input
133
Total output
100
Reasoning within output
git_grep f003
100%
Passed
Tokens
116
Input
149
Total output
107
Reasoning within output
git_grep f004
100%
Passed
Tokens
92
Input
156
Total output
108
Reasoning within output
git_grep f005
100%
Passed
Tokens
129
Input
238
Total output
190
Reasoning within output
git_grep f006
100%
Passed
Tokens
49
Input
678
Total output
669
Reasoning within output
git_grep f007
100%
Passed
Tokens
191
Input
487
Total output
329
Reasoning within output
git_grep f008
100%
Passed
Tokens
72
Input
117
Total output
92
Reasoning within output
git_grep f009
100%
Passed
Tokens
65
Input
132
Total output
98
Reasoning within output
git_grep f010
100%
Passed
Tokens
79
Input
168
Total output
130
Reasoning within output
git_grep f011
100%
Passed
Tokens
142
Input
209
Total output
1
Reasoning within output
git_grep f012
100%
Passed
Tokens
80
Input
186
Total output
1
Reasoning within output
git_log_format f001
100%
Passed
Tokens
936
Input
220
Total output
1
Reasoning within output
git_log_format f002
100%
Passed
Tokens
934
Input
210
Total output
1
Reasoning within output
git_log_format f003
100%
Passed
Tokens
754
Input
391
Total output
1
Reasoning within output
git_log_format f004
100%
Passed
Tokens
920
Input
336
Total output
233
Reasoning within output
git_log_format f005
100%
Passed
Tokens
762
Input
243
Total output
1
Reasoning within output
git_log_format f006
100%
Passed
Tokens
950
Input
284
Total output
1
Reasoning within output
git_log_format f007
100%
Passed
Tokens
934
Input
186
Total output
1
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,250
Input
251
Total output
153
Reasoning within output
git_log_format f009
100%
Passed
Tokens
773
Input
216
Total output
1
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,421
Input
321
Total output
220
Reasoning within output
git_log_format f011
100%
Passed
Tokens
454
Input
278
Total output
1
Reasoning within output
git_log_format f012
100%
Passed
Tokens
426
Input
249
Total output
1
Reasoning within output
git_show f001
100%
Passed
Tokens
210
Input
227
Total output
168
Reasoning within output
git_show f002
0%
Failed
Tokens
216
Input
4,046
Total output
3,565
Reasoning within output
git_show f003
100%
Passed
Tokens
744
Input
295
Total output
179
Reasoning within output
git_show f004
100%
Passed
Tokens
498
Input
146
Total output
117
Reasoning within output
git_show f005
100%
Passed
Tokens
226
Input
248
Total output
210
Reasoning within output
git_show f006
100%
Passed
Tokens
228
Input
226
Total output
183
Reasoning within output
git_show f007
100%
Passed
Tokens
222
Input
250
Total output
244
Reasoning within output
git_show f008
100%
Passed
Tokens
226
Input
276
Total output
160
Reasoning within output
git_show f009
100%
Passed
Tokens
333
Input
415
Total output
227
Reasoning within output
git_show f010
100%
Passed
Tokens
217
Input
351
Total output
280
Reasoning within output
git_show f011
100%
Passed
Tokens
249
Input
148
Total output
1
Reasoning within output
git_show f012
100%
Passed
Tokens
379
Input
200
Total output
178
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
98
Input
891
Total output
1
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
116
Input
248
Total output
1
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
89
Input
505
Total output
1
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
166
Input
614
Total output
1
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
156
Input
315
Total output
1
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
142
Input
313
Total output
1
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
152
Input
290
Total output
217
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
123
Input
129
Total output
1
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
115
Input
264
Total output
1
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
206
Input
343
Total output
1
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
159
Input
255
Total output
180
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
263
Input
881
Total output
710
Reasoning within output
rebase f001
100%
Passed
Tokens
112
Input
1,560
Total output
1,541
Reasoning within output
rebase f002
100%
Passed
Tokens
138
Input
245
Total output
174
Reasoning within output
rebase f003
100%
Passed
Tokens
113
Input
221
Total output
212
Reasoning within output
rebase f004
100%
Passed
Tokens
181
Input
364
Total output
1
Reasoning within output
rebase f005
100%
Passed
Tokens
162
Input
837
Total output
795
Reasoning within output
rebase f006
100%
Passed
Tokens
157
Input
294
Total output
197
Reasoning within output
rebase f007
100%
Passed
Tokens
154
Input
264
Total output
182
Reasoning within output
rebase f008
100%
Passed
Tokens
137
Input
153
Total output
1
Reasoning within output
rebase f009
100%
Passed
Tokens
119
Input
249
Total output
243
Reasoning within output
rebase f010
100%
Passed
Tokens
233
Input
567
Total output
453
Reasoning within output
rebase f011
100%
Passed
Tokens
170
Input
240
Total output
1
Reasoning within output
rebase f012
0%
Failed
Tokens
298
Input
1,501
Total output
1,241
Reasoning within output
reflog f001
100%
Passed
Tokens
262
Input
563
Total output
1
Reasoning within output
reflog f002
100%
Passed
Tokens
246
Input
467
Total output
1
Reasoning within output
reflog f003
100%
Passed
Tokens
222
Input
372
Total output
1
Reasoning within output
reflog f004
100%
Passed
Tokens
375
Input
1,038
Total output
1
Reasoning within output
reflog f005
100%
Passed
Tokens
424
Input
593
Total output
1
Reasoning within output
reflog f006
100%
Passed
Tokens
273
Input
393
Total output
182
Reasoning within output
reflog f007
100%
Passed
Tokens
310
Input
567
Total output
309
Reasoning within output
reflog f008
100%
Passed
Tokens
397
Input
499
Total output
274
Reasoning within output
reflog f009
100%
Passed
Tokens
345
Input
693
Total output
1
Reasoning within output
reflog f010
100%
Passed
Tokens
305
Input
296
Total output
244
Reasoning within output
reflog f011
100%
Passed
Tokens
355
Input
953
Total output
455
Reasoning within output
reflog f012
100%
Passed
Tokens
356
Input
1,021
Total output
1
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
151
Input
149
Total output
118
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
320
Input
165
Total output
123
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
142
Input
143
Total output
124
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
135
Input
157
Total output
121
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
145
Input
267
Total output
230
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
211
Input
185
Total output
145
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
235
Input
144
Total output
112
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
207
Input
194
Total output
165
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
237
Input
190
Total output
146
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
144
Input
154
Total output
1
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
139
Input
192
Total output
1
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
159
Input
185
Total output
1
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
52
Input
114
Total output
90
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
117
Input
425
Total output
441
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
125
Input
593
Total output
529
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
111
Input
175
Total output
145
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
59
Input
259
Total output
198
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
105
Input
275
Total output
282
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
59
Input
207
Total output
162
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
113
Input
167
Total output
160
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
110
Input
127
Total output
125
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
118
Input
254
Total output
248
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
126
Input
93
Total output
89
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
57
Input
167
Total output
136
Reasoning within output
tag_management f001
100%
Passed
Tokens
73
Input
151
Total output
124
Reasoning within output
tag_management f002
100%
Passed
Tokens
67
Input
203
Total output
149
Reasoning within output
tag_management f003
100%
Passed
Tokens
78
Input
165
Total output
131
Reasoning within output
tag_management f004
100%
Passed
Tokens
80
Input
123
Total output
112
Reasoning within output
tag_management f005
100%
Passed
Tokens
98
Input
170
Total output
140
Reasoning within output
tag_management f006
100%
Passed
Tokens
80
Input
210
Total output
143
Reasoning within output
tag_management f007
100%
Passed
Tokens
75
Input
226
Total output
1
Reasoning within output
tag_management f008
100%
Passed
Tokens
82
Input
492
Total output
468
Reasoning within output
tag_management f009
100%
Passed
Tokens
84
Input
163
Total output
118
Reasoning within output
tag_management f010
100%
Passed
Tokens
59
Input
129
Total output
98
Reasoning within output
tag_management f011
100%
Passed
Tokens
64
Input
135
Total output
136
Reasoning within output
tag_management f012
100%
Passed
Tokens
101
Input
320
Total output
259
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
163
Input
249
Total output
161
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
172
Input
253
Total output
191
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
252
Input
255
Total output
165
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
245
Input
74
Total output
69
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
162
Input
177
Total output
1
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
159
Input
128
Total output
97
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
162
Input
215
Total output
152
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
188
Input
2,200
Total output
1,863
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
286
Input
143
Total output
140
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
259
Input
168
Total output
152
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
251
Input
112
Total output
92
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
160
Input
126
Total output
112
Reasoning within output