Google / gemini-3.1-flash-lite-preview
low
95.1%
194 / 204 fixtures · 1 run(s)
40,679 input / 33,653 total output / 27,680 reasoning within output tokens $0.06064925
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-3.9%
Text: 95.1% →
JSON: 91.2%
+4
Gained
JSON pass / text fail
−12
Lost
Text pass / JSON fail
182
Unchanged Pass
Both pass
6
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| commit_squash | 91.7% | 50% | -41.7% |
| branch_cleanup | 100% | 75% | -25% |
| merge_conflicts | 91.7% | 83.3% | -8.3% |
| blame_forensics | 91.7% | 100% | + 8.3% |
| git_grep | 91.7% | 100% | + 8.3% |
| rebase | 83.3% | 75% | -8.3% |
| cherry_pick | 75% | 75% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_clean | 91.7% | 91.7% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 100% | 100% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
| worktree_usage | 100% | 100% | + 0% |
Changed Fixtures (16)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
262
Input
127
Total output
123
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
255
Input
135
Total output
131
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
295
Input
135
Total output
129
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
207
Input
115
Total output
110
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
270
Input
129
Total output
124
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
250
Input
152
Total output
149
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
222
Input
121
Total output
117
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
263
Input
137
Total output
134
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
211
Input
135
Total output
132
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
461
Input
97
Total output
94
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
268
Input
142
Total output
139
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
154
Input
134
Total output
130
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
96
Input
142
Total output
138
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
115
Input
119
Total output
112
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
92
Input
118
Total output
117
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
132
Input
129
Total output
122
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
103
Input
147
Total output
143
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
124
Input
151
Total output
141
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
100
Input
121
Total output
114
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
117
Input
129
Total output
120
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
75
Input
109
Total output
108
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
110
Input
135
Total output
130
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
66
Input
122
Total output
121
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
155
Input
127
Total output
115
Reasoning within output
cherry_pick f001
0%
Failed
Tokens
93
Input
124
Total output
120
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
115
Input
153
Total output
146
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
85
Input
152
Total output
149
Reasoning within output
cherry_pick f004
100%
Passed
Tokens
164
Input
166
Total output
140
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
153
Input
160
Total output
140
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
142
Input
170
Total output
148
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
133
Input
148
Total output
138
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
124
Input
120
Total output
114
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
105
Input
121
Total output
116
Reasoning within output
cherry_pick f010
50%
Failed
Tokens
229
Input
139
Total output
109
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
163
Input
156
Total output
133
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
284
Input
191
Total output
144
Reasoning within output
commit_messages f001
93.3%
Passed
Tokens
113
Input
135
Total output
131
Reasoning within output
commit_messages f002
88.3%
Passed
Tokens
246
Input
138
Total output
134
Reasoning within output
commit_messages f003
95%
Passed
Tokens
84
Input
131
Total output
121
Reasoning within output
commit_messages f004
94.3%
Passed
Tokens
119
Input
138
Total output
134
Reasoning within output
commit_messages f005
90%
Passed
Tokens
110
Input
118
Total output
112
Reasoning within output
commit_messages f006
84.3%
Passed
Tokens
151
Input
151
Total output
144
Reasoning within output
commit_messages f007
91%
Passed
Tokens
209
Input
133
Total output
127
Reasoning within output
commit_messages f008
91.7%
Passed
Tokens
77
Input
131
Total output
126
Reasoning within output
commit_messages f009
90%
Passed
Tokens
134
Input
132
Total output
123
Reasoning within output
commit_messages f010
88.3%
Passed
Tokens
332
Input
129
Total output
122
Reasoning within output
commit_messages f011
62.7%
Passed
Tokens
153
Input
143
Total output
134
Reasoning within output
commit_messages f012
91.3%
Passed
Tokens
131
Input
113
Total output
108
Reasoning within output
commit_squash f001
100%
Passed
Tokens
135
Input
136
Total output
123
Reasoning within output
commit_squash f002
100%
Passed
Tokens
114
Input
128
Total output
119
Reasoning within output
commit_squash f003
100%
Passed
Tokens
128
Input
139
Total output
126
Reasoning within output
commit_squash f004
0%
Failed
Tokens
111
Input
139
Total output
117
Reasoning within output
commit_squash f005
100%
Passed
Tokens
113
Input
141
Total output
134
Reasoning within output
commit_squash f006
100%
Passed
Tokens
96
Input
134
Total output
123
Reasoning within output
commit_squash f007
100%
Passed
Tokens
96
Input
150
Total output
138
Reasoning within output
commit_squash f008
100%
Passed
Tokens
112
Input
200
Total output
188
Reasoning within output
commit_squash f009
100%
Passed
Tokens
100
Input
164
Total output
153
Reasoning within output
commit_squash f010
100%
Passed
Tokens
116
Input
195
Total output
180
Reasoning within output
commit_squash f011
100%
Passed
Tokens
122
Input
195
Total output
180
Reasoning within output
commit_squash f012
100%
Passed
Tokens
124
Input
145
Total output
125
Reasoning within output
git_bisect f001
100%
Passed
Tokens
185
Input
266
Total output
134
Reasoning within output
git_bisect f002
100%
Passed
Tokens
214
Input
199
Total output
112
Reasoning within output
git_bisect f003
100%
Passed
Tokens
207
Input
216
Total output
140
Reasoning within output
git_bisect f004
100%
Passed
Tokens
210
Input
207
Total output
125
Reasoning within output
git_bisect f005
100%
Passed
Tokens
215
Input
237
Total output
139
Reasoning within output
git_bisect f006
100%
Passed
Tokens
236
Input
257
Total output
154
Reasoning within output
git_bisect f007
100%
Passed
Tokens
215
Input
229
Total output
136
Reasoning within output
git_bisect f008
100%
Passed
Tokens
207
Input
209
Total output
130
Reasoning within output
git_bisect f009
100%
Passed
Tokens
211
Input
139
Total output
132
Reasoning within output
git_bisect f010
100%
Passed
Tokens
209
Input
251
Total output
135
Reasoning within output
git_bisect f011
100%
Passed
Tokens
210
Input
238
Total output
129
Reasoning within output
git_bisect f012
100%
Passed
Tokens
234
Input
224
Total output
114
Reasoning within output
git_clean f001
100%
Passed
Tokens
51
Input
124
Total output
115
Reasoning within output
git_clean f002
100%
Passed
Tokens
62
Input
112
Total output
108
Reasoning within output
git_clean f003
100%
Passed
Tokens
62
Input
115
Total output
111
Reasoning within output
git_clean f004
100%
Passed
Tokens
63
Input
146
Total output
141
Reasoning within output
git_clean f005
75%
Failed
Tokens
49
Input
119
Total output
114
Reasoning within output
git_clean f006
100%
Passed
Tokens
80
Input
127
Total output
121
Reasoning within output
git_clean f007
100%
Passed
Tokens
70
Input
127
Total output
118
Reasoning within output
git_clean f008
100%
Passed
Tokens
77
Input
147
Total output
143
Reasoning within output
git_clean f009
100%
Passed
Tokens
74
Input
127
Total output
119
Reasoning within output
git_clean f010
100%
Passed
Tokens
65
Input
134
Total output
130
Reasoning within output
git_clean f011
100%
Passed
Tokens
65
Input
118
Total output
113
Reasoning within output
git_clean f012
100%
Passed
Tokens
69
Input
138
Total output
131
Reasoning within output
git_grep f001
100%
Passed
Tokens
48
Input
136
Total output
131
Reasoning within output
git_grep f002
100%
Passed
Tokens
60
Input
129
Total output
128
Reasoning within output
git_grep f003
100%
Passed
Tokens
100
Input
126
Total output
125
Reasoning within output
git_grep f004
100%
Passed
Tokens
77
Input
134
Total output
129
Reasoning within output
git_grep f005
100%
Passed
Tokens
115
Input
105
Total output
104
Reasoning within output
git_grep f006
0%
Failed
Tokens
34
Input
142
Total output
132
Reasoning within output
git_grep f007
100%
Passed
Tokens
176
Input
713
Total output
711
Reasoning within output
git_grep f008
100%
Passed
Tokens
56
Input
141
Total output
140
Reasoning within output
git_grep f009
100%
Passed
Tokens
50
Input
128
Total output
125
Reasoning within output
git_grep f010
100%
Passed
Tokens
63
Input
116
Total output
115
Reasoning within output
git_grep f011
100%
Passed
Tokens
127
Input
117
Total output
116
Reasoning within output
git_grep f012
100%
Passed
Tokens
64
Input
139
Total output
126
Reasoning within output
git_log_format f001
100%
Passed
Tokens
922
Input
119
Total output
118
Reasoning within output
git_log_format f002
100%
Passed
Tokens
922
Input
112
Total output
105
Reasoning within output
git_log_format f003
100%
Passed
Tokens
750
Input
132
Total output
123
Reasoning within output
git_log_format f004
100%
Passed
Tokens
914
Input
177
Total output
176
Reasoning within output
git_log_format f005
100%
Passed
Tokens
746
Input
140
Total output
135
Reasoning within output
git_log_format f006
100%
Passed
Tokens
935
Input
116
Total output
115
Reasoning within output
git_log_format f007
100%
Passed
Tokens
925
Input
127
Total output
122
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,232
Input
95
Total output
94
Reasoning within output
git_log_format f009
100%
Passed
Tokens
728
Input
99
Total output
98
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,424
Input
111
Total output
110
Reasoning within output
git_log_format f011
100%
Passed
Tokens
447
Input
119
Total output
116
Reasoning within output
git_log_format f012
100%
Passed
Tokens
410
Input
132
Total output
131
Reasoning within output
git_show f001
100%
Passed
Tokens
193
Input
174
Total output
169
Reasoning within output
git_show f002
100%
Passed
Tokens
202
Input
109
Total output
106
Reasoning within output
git_show f003
100%
Passed
Tokens
730
Input
149
Total output
143
Reasoning within output
git_show f004
100%
Passed
Tokens
491
Input
324
Total output
317
Reasoning within output
git_show f005
100%
Passed
Tokens
210
Input
135
Total output
133
Reasoning within output
git_show f006
100%
Passed
Tokens
216
Input
128
Total output
127
Reasoning within output
git_show f007
100%
Passed
Tokens
203
Input
154
Total output
149
Reasoning within output
git_show f008
100%
Passed
Tokens
205
Input
154
Total output
122
Reasoning within output
git_show f009
100%
Passed
Tokens
322
Input
137
Total output
136
Reasoning within output
git_show f010
100%
Passed
Tokens
199
Input
124
Total output
123
Reasoning within output
git_show f011
100%
Passed
Tokens
233
Input
136
Total output
133
Reasoning within output
git_show f012
100%
Passed
Tokens
359
Input
141
Total output
140
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
82
Input
137
Total output
133
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
100
Input
170
Total output
163
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
73
Input
136
Total output
133
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
151
Input
180
Total output
154
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
141
Input
179
Total output
159
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
126
Input
156
Total output
134
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
136
Input
157
Total output
147
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
108
Input
133
Total output
127
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
100
Input
139
Total output
134
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
190
Input
156
Total output
126
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
144
Input
169
Total output
146
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
248
Input
174
Total output
127
Reasoning within output
rebase f001
100%
Passed
Tokens
94
Input
118
Total output
114
Reasoning within output
rebase f002
100%
Passed
Tokens
121
Input
125
Total output
118
Reasoning within output
rebase f003
100%
Passed
Tokens
100
Input
124
Total output
121
Reasoning within output
rebase f004
100%
Passed
Tokens
165
Input
155
Total output
129
Reasoning within output
rebase f005
100%
Passed
Tokens
148
Input
141
Total output
125
Reasoning within output
rebase f006
100%
Passed
Tokens
141
Input
170
Total output
148
Reasoning within output
rebase f007
100%
Passed
Tokens
138
Input
148
Total output
138
Reasoning within output
rebase f008
100%
Passed
Tokens
120
Input
134
Total output
128
Reasoning within output
rebase f009
100%
Passed
Tokens
100
Input
140
Total output
135
Reasoning within output
rebase f010
50%
Failed
Tokens
221
Input
141
Total output
111
Reasoning within output
rebase f011
100%
Passed
Tokens
154
Input
149
Total output
126
Reasoning within output
rebase f012
0%
Failed
Tokens
285
Input
210
Total output
163
Reasoning within output
reflog f001
100%
Passed
Tokens
243
Input
176
Total output
141
Reasoning within output
reflog f002
100%
Passed
Tokens
234
Input
357
Total output
126
Reasoning within output
reflog f003
100%
Passed
Tokens
204
Input
279
Total output
158
Reasoning within output
reflog f004
100%
Passed
Tokens
348
Input
429
Total output
159
Reasoning within output
reflog f005
100%
Passed
Tokens
392
Input
200
Total output
120
Reasoning within output
reflog f006
100%
Passed
Tokens
255
Input
372
Total output
133
Reasoning within output
reflog f007
100%
Passed
Tokens
300
Input
657
Total output
174
Reasoning within output
reflog f008
100%
Passed
Tokens
373
Input
301
Total output
116
Reasoning within output
reflog f009
100%
Passed
Tokens
337
Input
316
Total output
133
Reasoning within output
reflog f010
100%
Passed
Tokens
284
Input
333
Total output
167
Reasoning within output
reflog f011
100%
Passed
Tokens
347
Input
409
Total output
154
Reasoning within output
reflog f012
100%
Passed
Tokens
336
Input
551
Total output
154
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
136
Input
151
Total output
132
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
308
Input
280
Total output
129
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
127
Input
186
Total output
139
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
120
Input
136
Total output
125
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
128
Input
216
Total output
156
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
196
Input
170
Total output
156
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
220
Input
159
Total output
144
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
193
Input
238
Total output
151
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
222
Input
238
Total output
128
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
128
Input
142
Total output
131
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
122
Input
193
Total output
137
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
144
Input
158
Total output
143
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
37
Input
135
Total output
127
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
105
Input
139
Total output
130
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
110
Input
168
Total output
124
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
94
Input
115
Total output
112
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
44
Input
152
Total output
130
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
91
Input
124
Total output
121
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
43
Input
147
Total output
130
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
94
Input
127
Total output
122
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
93
Input
125
Total output
122
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
99
Input
117
Total output
111
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
106
Input
124
Total output
120
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
42
Input
111
Total output
100
Reasoning within output
tag_management f001
100%
Passed
Tokens
56
Input
133
Total output
127
Reasoning within output
tag_management f002
100%
Passed
Tokens
54
Input
144
Total output
126
Reasoning within output
tag_management f003
100%
Passed
Tokens
60
Input
140
Total output
130
Reasoning within output
tag_management f004
100%
Passed
Tokens
67
Input
147
Total output
145
Reasoning within output
tag_management f005
100%
Passed
Tokens
79
Input
125
Total output
118
Reasoning within output
tag_management f006
100%
Passed
Tokens
66
Input
159
Total output
145
Reasoning within output
tag_management f007
100%
Passed
Tokens
60
Input
159
Total output
148
Reasoning within output
tag_management f008
100%
Passed
Tokens
62
Input
191
Total output
149
Reasoning within output
tag_management f009
100%
Passed
Tokens
68
Input
141
Total output
125
Reasoning within output
tag_management f010
100%
Passed
Tokens
46
Input
146
Total output
139
Reasoning within output
tag_management f011
100%
Passed
Tokens
47
Input
108
Total output
103
Reasoning within output
tag_management f012
100%
Passed
Tokens
85
Input
156
Total output
145
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
146
Input
160
Total output
151
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
154
Input
183
Total output
162
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
231
Input
252
Total output
244
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
232
Input
123
Total output
119
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
140
Input
162
Total output
149
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
144
Input
237
Total output
224
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
145
Input
155
Total output
132
Reasoning within output
worktree_usage f008
100%
Passed
Tokens
172
Input
179
Total output
127
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
271
Input
133
Total output
129
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
238
Input
125
Total output
110
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
229
Input
132
Total output
124
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
139
Input
149
Total output
136
Reasoning within output