Google / gemini-3.6-flash
low
96.1%
196 / 204 fixtures · 1 run(s)
40,874 input / 47,908 total output / 43,989 reasoning within output tokens $0.42062100
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-8.3%
Text: 96.1% →
JSON: 87.8%
+1
Gained
JSON pass / text fail
−18
Lost
Text pass / JSON fail
178
Unchanged Pass
Both pass
7
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|---|---|---|
| f011 | 100% (1/1) | 0% (0/1) | +100% |
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| commit_squash | 91.7% | 25% | -66.7% |
| branch_cleanup | 100% | 75% | -25% |
| git_clean | 100% | 75% | -25% |
| cherry_pick | 83.3% | 75% | -8.3% |
| commit_messages | 100% | 91.7% | -8.3% |
| tag_management | 100% | 91.7% | -8.3% |
| blame_forensics | 91.7% | 91.7% | + 0% |
| git_bisect | 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% |
| rebase | 83.3% | 83.3% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 100% | 100% | + 0% |
| worktree_usage | 91.7% | 91.7% | + 0% |
Changed Fixtures (19)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
263
Input
292
Total output
288
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
258
Input
219
Total output
215
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
297
Input
95
Total output
89
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
204
Input
107
Total output
102
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
270
Input
490
Total output
485
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
249
Input
345
Total output
342
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
215
Input
114
Total output
110
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
266
Input
154
Total output
151
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
213
Input
167
Total output
164
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
460
Input
146
Total output
143
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
267
Input
113
Total output
110
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
154
Input
246
Total output
242
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
97
Input
153
Total output
149
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
118
Input
158
Total output
151
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
91
Input
149
Total output
148
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
134
Input
138
Total output
131
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
107
Input
188
Total output
184
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
131
Input
115
Total output
105
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
102
Input
120
Total output
113
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
121
Input
147
Total output
138
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
76
Input
123
Total output
122
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
113
Input
101
Total output
96
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
65
Input
103
Total output
102
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
156
Input
97
Total output
85
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
94
Input
257
Total output
253
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
112
Input
314
Total output
307
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
86
Input
269
Total output
266
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
166
Input
586
Total output
562
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
154
Input
258
Total output
238
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
142
Input
203
Total output
181
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
134
Input
160
Total output
150
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
127
Input
195
Total output
189
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
107
Input
87
Total output
82
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
230
Input
338
Total output
308
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
165
Input
111
Total output
88
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
287
Input
878
Total output
831
Reasoning within output
commit_messages f001
93.3%
Passed
Tokens
113
Input
190
Total output
186
Reasoning within output
commit_messages f002
91%
Passed
Tokens
246
Input
216
Total output
203
Reasoning within output
commit_messages f003
90%
Passed
Tokens
84
Input
184
Total output
174
Reasoning within output
commit_messages f004
93.7%
Passed
Tokens
119
Input
155
Total output
151
Reasoning within output
commit_messages f005
86.7%
Passed
Tokens
110
Input
151
Total output
146
Reasoning within output
commit_messages f006
91.7%
Passed
Tokens
152
Input
180
Total output
174
Reasoning within output
commit_messages f007
93.3%
Passed
Tokens
210
Input
167
Total output
161
Reasoning within output
commit_messages f008
91%
Passed
Tokens
77
Input
188
Total output
183
Reasoning within output
commit_messages f009
87.7%
Passed
Tokens
134
Input
108
Total output
101
Reasoning within output
commit_messages f010
93.3%
Passed
Tokens
333
Input
235
Total output
228
Reasoning within output
commit_messages f011
51.3%
Passed
Tokens
154
Input
394
Total output
382
Reasoning within output
commit_messages f012
90.3%
Passed
Tokens
131
Input
186
Total output
181
Reasoning within output
commit_squash f001
100%
Passed
Tokens
135
Input
695
Total output
682
Reasoning within output
commit_squash f002
100%
Passed
Tokens
116
Input
184
Total output
175
Reasoning within output
commit_squash f003
50%
Failed
Tokens
125
Input
1,305
Total output
1,300
Reasoning within output
commit_squash f004
100%
Passed
Tokens
113
Input
412
Total output
401
Reasoning within output
commit_squash f005
100%
Passed
Tokens
111
Input
330
Total output
323
Reasoning within output
commit_squash f006
100%
Passed
Tokens
96
Input
141
Total output
130
Reasoning within output
commit_squash f007
100%
Passed
Tokens
100
Input
368
Total output
357
Reasoning within output
commit_squash f008
100%
Passed
Tokens
111
Input
380
Total output
368
Reasoning within output
commit_squash f009
100%
Passed
Tokens
104
Input
2,100
Total output
2,089
Reasoning within output
commit_squash f010
100%
Passed
Tokens
120
Input
355
Total output
340
Reasoning within output
commit_squash f011
100%
Passed
Tokens
125
Input
346
Total output
331
Reasoning within output
commit_squash f012
100%
Passed
Tokens
122
Input
180
Total output
160
Reasoning within output
git_bisect f001
100%
Passed
Tokens
184
Input
97
Total output
75
Reasoning within output
git_bisect f002
100%
Passed
Tokens
212
Input
136
Total output
114
Reasoning within output
git_bisect f003
100%
Passed
Tokens
206
Input
114
Total output
97
Reasoning within output
git_bisect f004
100%
Passed
Tokens
212
Input
116
Total output
94
Reasoning within output
git_bisect f005
100%
Passed
Tokens
212
Input
145
Total output
119
Reasoning within output
git_bisect f006
100%
Passed
Tokens
242
Input
109
Total output
88
Reasoning within output
git_bisect f007
100%
Passed
Tokens
206
Input
96
Total output
90
Reasoning within output
git_bisect f008
100%
Passed
Tokens
214
Input
120
Total output
96
Reasoning within output
git_bisect f009
100%
Passed
Tokens
206
Input
51
Total output
45
Reasoning within output
git_bisect f010
100%
Passed
Tokens
214
Input
128
Total output
107
Reasoning within output
git_bisect f011
100%
Passed
Tokens
212
Input
120
Total output
97
Reasoning within output
git_bisect f012
100%
Passed
Tokens
234
Input
126
Total output
104
Reasoning within output
git_clean f001
100%
Passed
Tokens
51
Input
137
Total output
128
Reasoning within output
git_clean f002
100%
Passed
Tokens
63
Input
156
Total output
152
Reasoning within output
git_clean f003
100%
Passed
Tokens
63
Input
230
Total output
226
Reasoning within output
git_clean f004
100%
Passed
Tokens
63
Input
349
Total output
344
Reasoning within output
git_clean f005
100%
Passed
Tokens
50
Input
226
Total output
222
Reasoning within output
git_clean f006
100%
Passed
Tokens
81
Input
305
Total output
299
Reasoning within output
git_clean f007
100%
Passed
Tokens
70
Input
224
Total output
215
Reasoning within output
git_clean f008
100%
Passed
Tokens
78
Input
172
Total output
168
Reasoning within output
git_clean f009
100%
Passed
Tokens
74
Input
133
Total output
125
Reasoning within output
git_clean f010
100%
Passed
Tokens
65
Input
214
Total output
210
Reasoning within output
git_clean f011
100%
Passed
Tokens
65
Input
135
Total output
130
Reasoning within output
git_clean f012
100%
Passed
Tokens
70
Input
188
Total output
181
Reasoning within output
git_grep f001
100%
Passed
Tokens
49
Input
70
Total output
65
Reasoning within output
git_grep f002
100%
Passed
Tokens
61
Input
72
Total output
71
Reasoning within output
git_grep f003
100%
Passed
Tokens
101
Input
166
Total output
165
Reasoning within output
git_grep f004
100%
Passed
Tokens
77
Input
229
Total output
224
Reasoning within output
git_grep f005
100%
Passed
Tokens
115
Input
278
Total output
277
Reasoning within output
git_grep f006
100%
Passed
Tokens
34
Input
237
Total output
236
Reasoning within output
git_grep f007
100%
Passed
Tokens
177
Input
204
Total output
202
Reasoning within output
git_grep f008
100%
Passed
Tokens
57
Input
90
Total output
89
Reasoning within output
git_grep f009
100%
Passed
Tokens
50
Input
173
Total output
170
Reasoning within output
git_grep f010
100%
Passed
Tokens
64
Input
189
Total output
188
Reasoning within output
git_grep f011
100%
Passed
Tokens
127
Input
136
Total output
135
Reasoning within output
git_grep f012
100%
Passed
Tokens
65
Input
233
Total output
220
Reasoning within output
git_log_format f001
100%
Passed
Tokens
916
Input
99
Total output
98
Reasoning within output
git_log_format f002
100%
Passed
Tokens
900
Input
109
Total output
102
Reasoning within output
git_log_format f003
100%
Passed
Tokens
734
Input
179
Total output
170
Reasoning within output
git_log_format f004
100%
Passed
Tokens
918
Input
90
Total output
89
Reasoning within output
git_log_format f005
100%
Passed
Tokens
747
Input
316
Total output
311
Reasoning within output
git_log_format f006
100%
Passed
Tokens
935
Input
149
Total output
148
Reasoning within output
git_log_format f007
100%
Passed
Tokens
945
Input
62
Total output
55
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,207
Input
124
Total output
123
Reasoning within output
git_log_format f009
100%
Passed
Tokens
747
Input
36
Total output
35
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,447
Input
89
Total output
88
Reasoning within output
git_log_format f011
100%
Passed
Tokens
442
Input
133
Total output
130
Reasoning within output
git_log_format f012
100%
Passed
Tokens
407
Input
101
Total output
100
Reasoning within output
git_show f001
100%
Passed
Tokens
197
Input
59
Total output
54
Reasoning within output
git_show f002
100%
Passed
Tokens
209
Input
154
Total output
151
Reasoning within output
git_show f003
100%
Passed
Tokens
724
Input
148
Total output
142
Reasoning within output
git_show f004
100%
Passed
Tokens
481
Input
50
Total output
43
Reasoning within output
git_show f005
100%
Passed
Tokens
209
Input
82
Total output
80
Reasoning within output
git_show f006
100%
Passed
Tokens
219
Input
38
Total output
37
Reasoning within output
git_show f007
100%
Passed
Tokens
204
Input
73
Total output
68
Reasoning within output
git_show f008
100%
Passed
Tokens
209
Input
145
Total output
110
Reasoning within output
git_show f009
100%
Passed
Tokens
325
Input
138
Total output
137
Reasoning within output
git_show f010
100%
Passed
Tokens
198
Input
234
Total output
233
Reasoning within output
git_show f011
100%
Passed
Tokens
235
Input
71
Total output
68
Reasoning within output
git_show f012
100%
Passed
Tokens
360
Input
99
Total output
98
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
83
Input
179
Total output
175
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
101
Input
253
Total output
246
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
74
Input
349
Total output
346
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
151
Input
885
Total output
859
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
141
Input
166
Total output
146
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
127
Input
394
Total output
372
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
137
Input
105
Total output
95
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
108
Input
79
Total output
73
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
100
Input
88
Total output
83
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
191
Input
494
Total output
464
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
144
Input
342
Total output
319
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
248
Input
1,329
Total output
1,282
Reasoning within output
rebase f001
100%
Passed
Tokens
94
Input
282
Total output
278
Reasoning within output
rebase f002
100%
Passed
Tokens
121
Input
265
Total output
258
Reasoning within output
rebase f003
100%
Passed
Tokens
100
Input
165
Total output
162
Reasoning within output
rebase f004
0%
Failed
Tokens
166
Input
963
Total output
939
Reasoning within output
rebase f005
100%
Passed
Tokens
148
Input
266
Total output
250
Reasoning within output
rebase f006
100%
Passed
Tokens
142
Input
254
Total output
232
Reasoning within output
rebase f007
100%
Passed
Tokens
139
Input
265
Total output
255
Reasoning within output
rebase f008
100%
Passed
Tokens
123
Input
202
Total output
196
Reasoning within output
rebase f009
100%
Passed
Tokens
101
Input
164
Total output
159
Reasoning within output
rebase f010
100%
Passed
Tokens
222
Input
463
Total output
433
Reasoning within output
rebase f011
100%
Passed
Tokens
156
Input
203
Total output
180
Reasoning within output
rebase f012
0%
Failed
Tokens
279
Input
651
Total output
594
Reasoning within output
reflog f001
100%
Passed
Tokens
247
Input
183
Total output
151
Reasoning within output
reflog f002
100%
Passed
Tokens
242
Input
281
Total output
142
Reasoning within output
reflog f003
100%
Passed
Tokens
207
Input
299
Total output
203
Reasoning within output
reflog f004
100%
Passed
Tokens
351
Input
681
Total output
427
Reasoning within output
reflog f005
100%
Passed
Tokens
411
Input
275
Total output
142
Reasoning within output
reflog f006
100%
Passed
Tokens
256
Input
346
Total output
147
Reasoning within output
reflog f007
100%
Passed
Tokens
294
Input
324
Total output
130
Reasoning within output
reflog f008
100%
Passed
Tokens
382
Input
406
Total output
206
Reasoning within output
reflog f009
100%
Passed
Tokens
346
Input
447
Total output
275
Reasoning within output
reflog f010
100%
Passed
Tokens
277
Input
395
Total output
319
Reasoning within output
reflog f011
100%
Passed
Tokens
337
Input
479
Total output
333
Reasoning within output
reflog f012
100%
Passed
Tokens
338
Input
524
Total output
268
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
138
Input
71
Total output
66
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
311
Input
302
Total output
284
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
128
Input
77
Total output
63
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
121
Input
70
Total output
50
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
132
Input
194
Total output
189
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
197
Input
91
Total output
77
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
217
Input
75
Total output
59
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
193
Input
80
Total output
65
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
223
Input
113
Total output
64
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
129
Input
92
Total output
78
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
121
Input
75
Total output
58
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
144
Input
141
Total output
127
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
37
Input
135
Total output
127
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
102
Input
341
Total output
334
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
107
Input
355
Total output
332
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
94
Input
55
Total output
52
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
44
Input
389
Total output
364
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
91
Input
299
Total output
296
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
44
Input
241
Total output
224
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
102
Input
95
Total output
90
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
98
Input
146
Total output
143
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
105
Input
184
Total output
179
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
107
Input
129
Total output
125
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
42
Input
202
Total output
191
Reasoning within output
tag_management f001
100%
Passed
Tokens
58
Input
147
Total output
141
Reasoning within output
tag_management f002
100%
Passed
Tokens
52
Input
228
Total output
211
Reasoning within output
tag_management f003
100%
Passed
Tokens
63
Input
152
Total output
142
Reasoning within output
tag_management f004
100%
Passed
Tokens
69
Input
97
Total output
95
Reasoning within output
tag_management f005
100%
Passed
Tokens
81
Input
228
Total output
221
Reasoning within output
tag_management f006
100%
Passed
Tokens
66
Input
165
Total output
152
Reasoning within output
tag_management f007
100%
Passed
Tokens
61
Input
950
Total output
939
Reasoning within output
tag_management f008
100%
Passed
Tokens
65
Input
270
Total output
247
Reasoning within output
tag_management f009
100%
Passed
Tokens
69
Input
180
Total output
164
Reasoning within output
tag_management f010
100%
Passed
Tokens
46
Input
129
Total output
122
Reasoning within output
tag_management f011
100%
Passed
Tokens
46
Input
132
Total output
127
Reasoning within output
tag_management f012
100%
Passed
Tokens
86
Input
164
Total output
153
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
150
Input
162
Total output
153
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
155
Input
230
Total output
209
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
238
Input
49
Total output
41
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
231
Input
38
Total output
34
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
141
Input
221
Total output
208
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
145
Input
111
Total output
98
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
150
Input
112
Total output
89
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
175
Input
743
Total output
689
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
275
Input
55
Total output
51
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
247
Input
96
Total output
81
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
240
Input
80
Total output
72
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
143
Input
203
Total output
190
Reasoning within output