Google / gemma-4-31b-it
medium
95.1%
194 / 204 fixtures · 1 run(s)
43,961 input / 65,981 total output / 51,931 reasoning within output tokens $0.03441727
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-0.5%
Text: 95.1% →
JSON: 94.6%
+4
Gained
JSON pass / text fail
−5
Lost
Text pass / JSON fail
189
Unchanged Pass
Both pass
6
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| rebase | 83.3% | 91.7% | + 8.3% |
| blame_forensics | 100% | 91.7% | -8.3% |
| cherry_pick | 83.3% | 75% | -8.3% |
| git_grep | 100% | 91.7% | -8.3% |
| merge_conflicts | 75% | 83.3% | + 8.3% |
| branch_cleanup | 100% | 100% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| commit_squash | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_clean | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 91.7% | 91.7% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
| worktree_usage | 83.3% | 83.3% | + 0% |
Changed Fixtures (9)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
275
Input
443
Total output
391
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
274
Input
22
Total output
8
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
309
Input
355
Total output
249
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
223
Input
310
Total output
304
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
285
Input
305
Total output
238
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
267
Input
724
Total output
504
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
234
Input
361
Total output
243
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
273
Input
503
Total output
437
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
232
Input
403
Total output
399
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
474
Input
355
Total output
298
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
282
Input
414
Total output
259
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
172
Input
460
Total output
455
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
115
Input
198
Total output
167
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
135
Input
266
Total output
210
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
107
Input
221
Total output
184
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
146
Input
302
Total output
238
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
120
Input
174
Total output
155
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
142
Input
296
Total output
217
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
112
Input
214
Total output
174
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
135
Input
229
Total output
183
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
93
Input
133
Total output
126
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
129
Input
202
Total output
171
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
80
Input
200
Total output
185
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
176
Input
373
Total output
360
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
112
Input
1,004
Total output
999
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
130
Input
228
Total output
181
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
101
Input
202
Total output
203
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
183
Input
1,024
Total output
999
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
171
Input
210
Total output
184
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
161
Input
259
Total output
236
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
149
Input
228
Total output
1
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
143
Input
193
Total output
186
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
122
Input
206
Total output
173
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
250
Input
509
Total output
478
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
181
Input
243
Total output
158
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
302
Input
1,158
Total output
974
Reasoning within output
commit_messages f001
93.3%
Passed
Tokens
128
Input
225
Total output
172
Reasoning within output
commit_messages f002
90%
Passed
Tokens
261
Input
349
Total output
319
Reasoning within output
commit_messages f003
91.7%
Passed
Tokens
99
Input
220
Total output
163
Reasoning within output
commit_messages f004
93.7%
Passed
Tokens
134
Input
149
Total output
117
Reasoning within output
commit_messages f005
92.7%
Passed
Tokens
125
Input
168
Total output
147
Reasoning within output
commit_messages f006
82%
Passed
Tokens
167
Input
242
Total output
227
Reasoning within output
commit_messages f007
90%
Passed
Tokens
225
Input
251
Total output
219
Reasoning within output
commit_messages f008
90%
Passed
Tokens
92
Input
225
Total output
174
Reasoning within output
commit_messages f009
97.3%
Passed
Tokens
152
Input
391
Total output
383
Reasoning within output
commit_messages f010
88.3%
Passed
Tokens
348
Input
224
Total output
186
Reasoning within output
commit_messages f011
72%
Passed
Tokens
169
Input
343
Total output
316
Reasoning within output
commit_messages f012
91.7%
Passed
Tokens
146
Input
157
Total output
158
Reasoning within output
commit_squash f001
100%
Passed
Tokens
150
Input
1,098
Total output
914
Reasoning within output
commit_squash f002
100%
Passed
Tokens
128
Input
255
Total output
203
Reasoning within output
commit_squash f003
100%
Passed
Tokens
139
Input
346
Total output
253
Reasoning within output
commit_squash f004
100%
Passed
Tokens
131
Input
919
Total output
907
Reasoning within output
commit_squash f005
100%
Passed
Tokens
131
Input
292
Total output
284
Reasoning within output
commit_squash f006
100%
Passed
Tokens
111
Input
209
Total output
177
Reasoning within output
commit_squash f007
100%
Passed
Tokens
113
Input
184
Total output
171
Reasoning within output
commit_squash f008
100%
Passed
Tokens
125
Input
303
Total output
1
Reasoning within output
commit_squash f009
100%
Passed
Tokens
122
Input
233
Total output
221
Reasoning within output
commit_squash f010
100%
Passed
Tokens
136
Input
219
Total output
203
Reasoning within output
commit_squash f011
100%
Passed
Tokens
141
Input
243
Total output
227
Reasoning within output
commit_squash f012
100%
Passed
Tokens
140
Input
301
Total output
280
Reasoning within output
git_bisect f001
100%
Passed
Tokens
197
Input
119
Total output
72
Reasoning within output
git_bisect f002
100%
Passed
Tokens
227
Input
140
Total output
93
Reasoning within output
git_bisect f003
100%
Passed
Tokens
223
Input
145
Total output
96
Reasoning within output
git_bisect f004
100%
Passed
Tokens
226
Input
141
Total output
85
Reasoning within output
git_bisect f005
100%
Passed
Tokens
226
Input
239
Total output
162
Reasoning within output
git_bisect f006
100%
Passed
Tokens
253
Input
233
Total output
168
Reasoning within output
git_bisect f007
100%
Passed
Tokens
225
Input
169
Total output
105
Reasoning within output
git_bisect f008
100%
Passed
Tokens
229
Input
290
Total output
205
Reasoning within output
git_bisect f009
100%
Passed
Tokens
228
Input
197
Total output
119
Reasoning within output
git_bisect f010
100%
Passed
Tokens
233
Input
151
Total output
98
Reasoning within output
git_bisect f011
100%
Passed
Tokens
226
Input
328
Total output
227
Reasoning within output
git_bisect f012
100%
Passed
Tokens
255
Input
184
Total output
118
Reasoning within output
git_clean f001
100%
Passed
Tokens
65
Input
331
Total output
286
Reasoning within output
git_clean f002
100%
Passed
Tokens
78
Input
153
Total output
136
Reasoning within output
git_clean f003
100%
Passed
Tokens
78
Input
208
Total output
181
Reasoning within output
git_clean f004
100%
Passed
Tokens
78
Input
214
Total output
187
Reasoning within output
git_clean f005
100%
Passed
Tokens
65
Input
553
Total output
494
Reasoning within output
git_clean f006
100%
Passed
Tokens
99
Input
240
Total output
234
Reasoning within output
git_clean f007
100%
Passed
Tokens
85
Input
234
Total output
188
Reasoning within output
git_clean f008
100%
Passed
Tokens
96
Input
232
Total output
227
Reasoning within output
git_clean f009
100%
Passed
Tokens
92
Input
257
Total output
248
Reasoning within output
git_clean f010
100%
Passed
Tokens
80
Input
226
Total output
204
Reasoning within output
git_clean f011
100%
Passed
Tokens
80
Input
283
Total output
248
Reasoning within output
git_clean f012
100%
Passed
Tokens
88
Input
320
Total output
312
Reasoning within output
git_grep f001
100%
Passed
Tokens
64
Input
124
Total output
104
Reasoning within output
git_grep f002
100%
Passed
Tokens
74
Input
129
Total output
100
Reasoning within output
git_grep f003
100%
Passed
Tokens
116
Input
155
Total output
112
Reasoning within output
git_grep f004
100%
Passed
Tokens
95
Input
155
Total output
149
Reasoning within output
git_grep f005
100%
Passed
Tokens
133
Input
216
Total output
214
Reasoning within output
git_grep f006
100%
Passed
Tokens
52
Input
428
Total output
426
Reasoning within output
git_grep f007
100%
Passed
Tokens
195
Input
518
Total output
515
Reasoning within output
git_grep f008
100%
Passed
Tokens
72
Input
123
Total output
98
Reasoning within output
git_grep f009
100%
Passed
Tokens
68
Input
123
Total output
119
Reasoning within output
git_grep f010
100%
Passed
Tokens
79
Input
144
Total output
115
Reasoning within output
git_grep f011
100%
Passed
Tokens
142
Input
252
Total output
189
Reasoning within output
git_grep f012
100%
Passed
Tokens
80
Input
197
Total output
1
Reasoning within output
git_log_format f001
100%
Passed
Tokens
929
Input
209
Total output
162
Reasoning within output
git_log_format f002
100%
Passed
Tokens
934
Input
196
Total output
157
Reasoning within output
git_log_format f003
100%
Passed
Tokens
739
Input
299
Total output
223
Reasoning within output
git_log_format f004
100%
Passed
Tokens
921
Input
299
Total output
177
Reasoning within output
git_log_format f005
100%
Passed
Tokens
762
Input
268
Total output
177
Reasoning within output
git_log_format f006
100%
Passed
Tokens
950
Input
299
Total output
158
Reasoning within output
git_log_format f007
100%
Passed
Tokens
944
Input
181
Total output
141
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,236
Input
187
Total output
131
Reasoning within output
git_log_format f009
100%
Passed
Tokens
745
Input
318
Total output
244
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,429
Input
348
Total output
253
Reasoning within output
git_log_format f011
100%
Passed
Tokens
445
Input
260
Total output
199
Reasoning within output
git_log_format f012
100%
Passed
Tokens
431
Input
157
Total output
141
Reasoning within output
git_show f001
100%
Passed
Tokens
209
Input
216
Total output
131
Reasoning within output
git_show f002
0%
Failed
Tokens
219
Input
3,977
Total output
3,973
Reasoning within output
git_show f003
100%
Passed
Tokens
745
Input
256
Total output
165
Reasoning within output
git_show f004
100%
Passed
Tokens
494
Input
235
Total output
179
Reasoning within output
git_show f005
100%
Passed
Tokens
223
Input
316
Total output
1
Reasoning within output
git_show f006
100%
Passed
Tokens
233
Input
200
Total output
158
Reasoning within output
git_show f007
100%
Passed
Tokens
219
Input
271
Total output
200
Reasoning within output
git_show f008
100%
Passed
Tokens
228
Input
271
Total output
147
Reasoning within output
git_show f009
100%
Passed
Tokens
340
Input
440
Total output
268
Reasoning within output
git_show f010
100%
Passed
Tokens
220
Input
278
Total output
276
Reasoning within output
git_show f011
100%
Passed
Tokens
244
Input
192
Total output
148
Reasoning within output
git_show f012
100%
Passed
Tokens
378
Input
219
Total output
1
Reasoning within output
merge_conflicts f001
0%
Failed
Tokens
98
Input
1,470
Total output
1,398
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
116
Input
230
Total output
194
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
89
Input
164
Total output
149
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
166
Input
245
Total output
185
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
156
Input
306
Total output
259
Reasoning within output
merge_conflicts f006
0%
Failed
Tokens
142
Input
278
Total output
190
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
152
Input
298
Total output
220
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
123
Input
116
Total output
90
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
115
Input
245
Total output
219
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
206
Input
315
Total output
249
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
159
Input
225
Total output
147
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
263
Input
1,139
Total output
958
Reasoning within output
rebase f001
0%
Failed
Tokens
112
Input
928
Total output
1
Reasoning within output
rebase f002
100%
Passed
Tokens
134
Input
249
Total output
1
Reasoning within output
rebase f003
100%
Passed
Tokens
112
Input
143
Total output
130
Reasoning within output
rebase f004
100%
Passed
Tokens
180
Input
707
Total output
556
Reasoning within output
rebase f005
100%
Passed
Tokens
164
Input
336
Total output
286
Reasoning within output
rebase f006
100%
Passed
Tokens
156
Input
234
Total output
146
Reasoning within output
rebase f007
100%
Passed
Tokens
153
Input
248
Total output
193
Reasoning within output
rebase f008
100%
Passed
Tokens
136
Input
139
Total output
117
Reasoning within output
rebase f009
100%
Passed
Tokens
116
Input
252
Total output
239
Reasoning within output
rebase f010
100%
Passed
Tokens
234
Input
469
Total output
397
Reasoning within output
rebase f011
100%
Passed
Tokens
170
Input
308
Total output
207
Reasoning within output
rebase f012
0%
Failed
Tokens
300
Input
1,145
Total output
979
Reasoning within output
reflog f001
100%
Passed
Tokens
265
Input
513
Total output
286
Reasoning within output
reflog f002
100%
Passed
Tokens
261
Input
541
Total output
383
Reasoning within output
reflog f003
100%
Passed
Tokens
214
Input
359
Total output
223
Reasoning within output
reflog f004
100%
Passed
Tokens
369
Input
983
Total output
446
Reasoning within output
reflog f005
100%
Passed
Tokens
409
Input
434
Total output
379
Reasoning within output
reflog f006
100%
Passed
Tokens
271
Input
315
Total output
259
Reasoning within output
reflog f007
100%
Passed
Tokens
314
Input
546
Total output
287
Reasoning within output
reflog f008
100%
Passed
Tokens
409
Input
579
Total output
383
Reasoning within output
reflog f009
100%
Passed
Tokens
359
Input
723
Total output
368
Reasoning within output
reflog f010
100%
Passed
Tokens
301
Input
516
Total output
278
Reasoning within output
reflog f011
100%
Passed
Tokens
367
Input
787
Total output
363
Reasoning within output
reflog f012
100%
Passed
Tokens
348
Input
683
Total output
324
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
153
Input
148
Total output
128
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
329
Input
228
Total output
222
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
142
Input
181
Total output
157
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
136
Input
165
Total output
141
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
147
Input
210
Total output
190
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
211
Input
173
Total output
134
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
236
Input
150
Total output
115
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
207
Input
243
Total output
206
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
238
Input
210
Total output
171
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
143
Input
158
Total output
132
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
138
Input
195
Total output
137
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
159
Input
192
Total output
156
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
51
Input
113
Total output
83
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
121
Input
914
Total output
906
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
125
Input
349
Total output
286
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
110
Input
140
Total output
133
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
62
Input
258
Total output
231
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
105
Input
206
Total output
215
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
62
Input
166
Total output
148
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
114
Input
144
Total output
142
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
107
Input
153
Total output
154
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
120
Input
283
Total output
297
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
127
Input
109
Total output
104
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
57
Input
138
Total output
114
Reasoning within output
tag_management f001
100%
Passed
Tokens
69
Input
93
Total output
70
Reasoning within output
tag_management f002
100%
Passed
Tokens
69
Input
172
Total output
122
Reasoning within output
tag_management f003
100%
Passed
Tokens
75
Input
177
Total output
146
Reasoning within output
tag_management f004
100%
Passed
Tokens
83
Input
120
Total output
117
Reasoning within output
tag_management f005
100%
Passed
Tokens
94
Input
122
Total output
97
Reasoning within output
tag_management f006
100%
Passed
Tokens
79
Input
211
Total output
153
Reasoning within output
tag_management f007
100%
Passed
Tokens
74
Input
236
Total output
185
Reasoning within output
tag_management f008
100%
Passed
Tokens
78
Input
628
Total output
434
Reasoning within output
tag_management f009
100%
Passed
Tokens
84
Input
122
Total output
83
Reasoning within output
tag_management f010
100%
Passed
Tokens
61
Input
154
Total output
122
Reasoning within output
tag_management f011
100%
Passed
Tokens
64
Input
179
Total output
169
Reasoning within output
tag_management f012
100%
Passed
Tokens
100
Input
448
Total output
330
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
165
Input
255
Total output
171
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
172
Input
243
Total output
219
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
253
Input
156
Total output
124
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
252
Input
98
Total output
96
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
160
Input
147
Total output
106
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
163
Input
121
Total output
109
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
164
Input
375
Total output
303
Reasoning within output
worktree_usage f008
50%
Failed
Tokens
186
Input
467
Total output
354
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
285
Input
137
Total output
131
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
254
Input
150
Total output
116
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
251
Input
123
Total output
100
Reasoning within output
worktree_usage f012
0%
Failed
Tokens
160
Input
137
Total output
89
Reasoning within output