Xiaomi / mimo-v2.6-flash
max
92.2%
188 / 204 fixtures · 1 run(s)
39,756 input / 21,372 total output / 10,749 reasoning within output tokens $0.01147097
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-2.9%
Text: 92.2% →
JSON: 89.2%
+12
Gained
JSON pass / text fail
−18
Lost
Text pass / JSON fail
170
Unchanged Pass
Both pass
4
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| commit_squash | 91.7% | 66.7% | -25% |
| rebase | 58.3% | 83.3% | + 25% |
| reflog | 100% | 75% | -25% |
| blame_forensics | 100% | 91.7% | -8.3% |
| cherry_pick | 75% | 66.7% | -8.3% |
| merge_conflicts | 83.3% | 75% | -8.3% |
| submodule_usage | 100% | 91.7% | -8.3% |
| tag_management | 91.7% | 100% | + 8.3% |
| branch_cleanup | 100% | 100% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_clean | 83.3% | 83.3% | + 0% |
| git_grep | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| worktree_usage | 83.3% | 83.3% | + 0% |
Changed Fixtures (30)
f005 -loss f001 -loss f004 -loss f006 +gain f010 +gain f011 -loss f004 +gain f007 -loss f008 -loss f010 -loss f012 -loss f004 -loss f009 +gain f001 -loss f003 +gain f011 -loss f001 -loss f003 +gain f006 +gain f007 +gain f010 +gain f001 -loss f009 -loss f012 -loss f003 -loss f007 +gain f001 -loss f002 +gain f007 -loss f008 +gain
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
242
Input
207
Total output
200
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
237
Input
30
Total output
23
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
273
Input
31
Total output
22
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
198
Input
49
Total output
42
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
266
Input
40
Total output
35
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
236
Input
55
Total output
50
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
218
Input
33
Total output
26
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
246
Input
46
Total output
40
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
199
Input
42
Total output
36
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
429
Input
33
Total output
28
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
248
Input
26
Total output
20
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
147
Input
49
Total output
42
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
99
Input
80
Total output
75
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
113
Input
36
Total output
29
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
98
Input
33
Total output
29
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
134
Input
31
Total output
24
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
106
Input
15
Total output
10
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
134
Input
30
Total output
18
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
110
Input
19
Total output
11
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
123
Input
52
Total output
40
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
83
Input
23
Total output
20
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
118
Input
20
Total output
13
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
71
Input
17
Total output
14
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
165
Input
44
Total output
31
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
93
Input
83
Total output
77
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
115
Input
150
Total output
141
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
88
Input
51
Total output
45
Reasoning within output
cherry_pick f004
100%
Passed
Tokens
160
Input
211
Total output
179
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
145
Input
44
Total output
21
Reasoning within output
cherry_pick f006
0%
Failed
Tokens
139
Input
62
Total output
30
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
130
Input
137
Total output
125
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
121
Input
22
Total output
14
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
105
Input
25
Total output
18
Reasoning within output
cherry_pick f010
0%
Failed
Tokens
215
Input
279
Total output
247
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
158
Input
48
Total output
21
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
262
Input
199
Total output
146
Reasoning within output
commit_messages f001
92.5%
Passed
Tokens
112
Input
26
Total output
20
Reasoning within output
commit_messages f002
87.5%
Passed
Tokens
227
Input
25
Total output
15
Reasoning within output
commit_messages f003
94%
Passed
Tokens
84
Input
23
Total output
13
Reasoning within output
commit_messages f004
90%
Passed
Tokens
121
Input
14
Total output
9
Reasoning within output
commit_messages f005
65%
Passed
Tokens
105
Input
16
Total output
10
Reasoning within output
commit_messages f006
89%
Passed
Tokens
152
Input
16
Total output
7
Reasoning within output
commit_messages f007
77.5%
Passed
Tokens
192
Input
15
Total output
5
Reasoning within output
commit_messages f008
91.5%
Passed
Tokens
78
Input
44
Total output
36
Reasoning within output
commit_messages f009
90%
Passed
Tokens
129
Input
18
Total output
10
Reasoning within output
commit_messages f010
82.5%
Passed
Tokens
298
Input
19
Total output
11
Reasoning within output
commit_messages f011
72.5%
Passed
Tokens
145
Input
33
Total output
18
Reasoning within output
commit_messages f012
95%
Passed
Tokens
128
Input
13
Total output
6
Reasoning within output
commit_squash f001
100%
Passed
Tokens
143
Input
84
Total output
70
Reasoning within output
commit_squash f002
100%
Passed
Tokens
121
Input
32
Total output
22
Reasoning within output
commit_squash f003
100%
Passed
Tokens
130
Input
224
Total output
210
Reasoning within output
commit_squash f004
100%
Failed
Tokens
119
Input
354
Total output
337
Reasoning within output
commit_squash f005
100%
Passed
Tokens
118
Input
31
Total output
22
Reasoning within output
commit_squash f006
100%
Passed
Tokens
102
Input
58
Total output
45
Reasoning within output
commit_squash f007
100%
Passed
Tokens
108
Input
137
Total output
123
Reasoning within output
commit_squash f008
100%
Passed
Tokens
119
Input
69
Total output
55
Reasoning within output
commit_squash f009
100%
Passed
Tokens
113
Input
50
Total output
37
Reasoning within output
commit_squash f010
100%
Passed
Tokens
126
Input
34
Total output
17
Reasoning within output
commit_squash f011
100%
Passed
Tokens
134
Input
59
Total output
42
Reasoning within output
commit_squash f012
100%
Passed
Tokens
135
Input
67
Total output
45
Reasoning within output
git_bisect f001
100%
Passed
Tokens
181
Input
151
Total output
70
Reasoning within output
git_bisect f002
100%
Passed
Tokens
204
Input
110
Total output
13
Reasoning within output
git_bisect f003
100%
Passed
Tokens
208
Input
295
Total output
41
Reasoning within output
git_bisect f004
100%
Passed
Tokens
212
Input
117
Total output
24
Reasoning within output
git_bisect f005
100%
Passed
Tokens
206
Input
182
Total output
85
Reasoning within output
git_bisect f006
100%
Passed
Tokens
239
Input
236
Total output
43
Reasoning within output
git_bisect f007
100%
Passed
Tokens
212
Input
181
Total output
28
Reasoning within output
git_bisect f008
100%
Passed
Tokens
206
Input
251
Total output
44
Reasoning within output
git_bisect f009
100%
Passed
Tokens
208
Input
134
Total output
23
Reasoning within output
git_bisect f010
100%
Passed
Tokens
212
Input
164
Total output
39
Reasoning within output
git_bisect f011
100%
Passed
Tokens
210
Input
71
Total output
27
Reasoning within output
git_bisect f012
100%
Passed
Tokens
235
Input
121
Total output
19
Reasoning within output
git_clean f001
100%
Passed
Tokens
48
Input
28
Total output
14
Reasoning within output
git_clean f002
100%
Passed
Tokens
59
Input
11
Total output
5
Reasoning within output
git_clean f003
100%
Passed
Tokens
56
Input
26
Total output
16
Reasoning within output
git_clean f004
100%
Passed
Tokens
56
Input
43
Total output
36
Reasoning within output
git_clean f005
100%
Passed
Tokens
48
Input
80
Total output
18
Reasoning within output
git_clean f006
100%
Passed
Tokens
71
Input
18
Total output
6
Reasoning within output
git_clean f007
100%
Passed
Tokens
65
Input
108
Total output
97
Reasoning within output
git_clean f008
100%
Passed
Tokens
76
Input
17
Total output
6
Reasoning within output
git_clean f009
75%
Failed
Tokens
64
Input
12
Total output
4
Reasoning within output
git_clean f010
100%
Passed
Tokens
60
Input
374
Total output
368
Reasoning within output
git_clean f011
60%
Failed
Tokens
60
Input
35
Total output
22
Reasoning within output
git_clean f012
100%
Passed
Tokens
62
Input
211
Total output
198
Reasoning within output
git_grep f001
100%
Passed
Tokens
50
Input
16
Total output
11
Reasoning within output
git_grep f002
100%
Passed
Tokens
64
Input
5
Total output
2
Reasoning within output
git_grep f003
100%
Passed
Tokens
83
Input
5
Total output
2
Reasoning within output
git_grep f004
100%
Passed
Tokens
75
Input
25
Total output
18
Reasoning within output
git_grep f005
100%
Passed
Tokens
112
Input
5
Total output
2
Reasoning within output
git_grep f006
100%
Passed
Tokens
40
Input
75
Total output
72
Reasoning within output
git_grep f007
100%
Passed
Tokens
157
Input
150
Total output
146
Reasoning within output
git_grep f008
100%
Passed
Tokens
57
Input
5
Total output
2
Reasoning within output
git_grep f009
100%
Passed
Tokens
53
Input
9
Total output
4
Reasoning within output
git_grep f010
100%
Passed
Tokens
61
Input
13
Total output
10
Reasoning within output
git_grep f011
100%
Passed
Tokens
107
Input
5
Total output
2
Reasoning within output
git_grep f012
100%
Passed
Tokens
64
Input
18
Total output
8
Reasoning within output
git_log_format f001
100%
Passed
Tokens
898
Input
5
Total output
1
Reasoning within output
git_log_format f002
100%
Passed
Tokens
875
Input
35
Total output
25
Reasoning within output
git_log_format f003
100%
Passed
Tokens
714
Input
30
Total output
19
Reasoning within output
git_log_format f004
100%
Passed
Tokens
861
Input
5
Total output
2
Reasoning within output
git_log_format f005
100%
Passed
Tokens
723
Input
17
Total output
10
Reasoning within output
git_log_format f006
100%
Passed
Tokens
895
Input
93
Total output
89
Reasoning within output
git_log_format f007
100%
Passed
Tokens
893
Input
13
Total output
6
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,198
Input
16
Total output
12
Reasoning within output
git_log_format f009
100%
Passed
Tokens
697
Input
17
Total output
14
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,382
Input
19
Total output
16
Reasoning within output
git_log_format f011
100%
Passed
Tokens
428
Input
36
Total output
32
Reasoning within output
git_log_format f012
100%
Passed
Tokens
400
Input
17
Total output
14
Reasoning within output
git_show f001
100%
Passed
Tokens
190
Input
22
Total output
17
Reasoning within output
git_show f002
100%
Passed
Tokens
193
Input
135
Total output
131
Reasoning within output
git_show f003
100%
Passed
Tokens
672
Input
42
Total output
34
Reasoning within output
git_show f004
100%
Passed
Tokens
452
Input
15
Total output
7
Reasoning within output
git_show f005
100%
Passed
Tokens
198
Input
34
Total output
30
Reasoning within output
git_show f006
100%
Passed
Tokens
205
Input
5
Total output
2
Reasoning within output
git_show f007
100%
Passed
Tokens
195
Input
56
Total output
50
Reasoning within output
git_show f008
100%
Passed
Tokens
205
Input
77
Total output
38
Reasoning within output
git_show f009
100%
Passed
Tokens
320
Input
37
Total output
33
Reasoning within output
git_show f010
100%
Passed
Tokens
190
Input
19
Total output
15
Reasoning within output
git_show f011
100%
Passed
Tokens
225
Input
7
Total output
3
Reasoning within output
git_show f012
100%
Passed
Tokens
334
Input
5
Total output
2
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
81
Input
142
Total output
135
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
101
Input
133
Total output
123
Reasoning within output
merge_conflicts f003
0%
Failed
Tokens
76
Input
409
Total output
396
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
145
Input
376
Total output
343
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
132
Input
34
Total output
11
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
126
Input
122
Total output
94
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
131
Input
46
Total output
34
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
103
Input
41
Total output
33
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
100
Input
30
Total output
22
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
176
Input
141
Total output
105
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
138
Input
52
Total output
25
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
231
Input
103
Total output
51
Reasoning within output
rebase f001
100%
Passed
Tokens
92
Input
89
Total output
83
Reasoning within output
rebase f002
100%
Passed
Tokens
123
Input
39
Total output
30
Reasoning within output
rebase f003
0%
Failed
Tokens
102
Input
60
Total output
47
Reasoning within output
rebase f004
100%
Passed
Tokens
157
Input
64
Total output
35
Reasoning within output
rebase f005
100%
Passed
Tokens
136
Input
50
Total output
30
Reasoning within output
rebase f006
0%
Failed
Tokens
141
Input
66
Total output
33
Reasoning within output
rebase f007
0%
Failed
Tokens
133
Input
84
Total output
65
Reasoning within output
rebase f008
100%
Passed
Tokens
117
Input
46
Total output
37
Reasoning within output
rebase f009
100%
Passed
Tokens
100
Input
124
Total output
117
Reasoning within output
rebase f010
0%
Failed
Tokens
205
Input
239
Total output
206
Reasoning within output
rebase f011
100%
Passed
Tokens
148
Input
57
Total output
29
Reasoning within output
rebase f012
0%
Failed
Tokens
262
Input
158
Total output
115
Reasoning within output
reflog f001
100%
Passed
Tokens
246
Input
180
Total output
142
Reasoning within output
reflog f002
100%
Passed
Tokens
251
Input
752
Total output
168
Reasoning within output
reflog f003
100%
Passed
Tokens
211
Input
766
Total output
18
Reasoning within output
reflog f004
100%
Passed
Tokens
356
Input
739
Total output
106
Reasoning within output
reflog f005
100%
Passed
Tokens
407
Input
590
Total output
136
Reasoning within output
reflog f006
100%
Passed
Tokens
265
Input
547
Total output
30
Reasoning within output
reflog f007
100%
Passed
Tokens
301
Input
211
Total output
22
Reasoning within output
reflog f008
100%
Passed
Tokens
407
Input
565
Total output
87
Reasoning within output
reflog f009
100%
Passed
Tokens
347
Input
838
Total output
317
Reasoning within output
reflog f010
100%
Passed
Tokens
298
Input
466
Total output
35
Reasoning within output
reflog f011
100%
Passed
Tokens
361
Input
822
Total output
405
Reasoning within output
reflog f012
100%
Passed
Tokens
347
Input
1,457
Total output
795
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
135
Input
72
Total output
22
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
300
Input
176
Total output
9
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
123
Input
131
Total output
24
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
118
Input
24
Total output
9
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
129
Input
193
Total output
16
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
181
Input
94
Total output
20
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
212
Input
84
Total output
27
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
179
Input
261
Total output
68
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
209
Input
102
Total output
16
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
127
Input
248
Total output
25
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
122
Input
22
Total output
12
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
133
Input
88
Total output
10
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
42
Input
23
Total output
9
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
100
Input
37
Total output
22
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
106
Input
30
Total output
7
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
94
Input
21
Total output
16
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
49
Input
52
Total output
22
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
92
Input
23
Total output
14
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
49
Input
35
Total output
12
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
100
Input
20
Total output
13
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
94
Input
10
Total output
4
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
101
Input
27
Total output
18
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
103
Input
19
Total output
13
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
47
Input
30
Total output
13
Reasoning within output
tag_management f001
100%
Passed
Tokens
60
Input
19
Total output
11
Reasoning within output
tag_management f002
100%
Passed
Tokens
57
Input
27
Total output
7
Reasoning within output
tag_management f003
100%
Passed
Tokens
62
Input
21
Total output
6
Reasoning within output
tag_management f004
100%
Passed
Tokens
69
Input
21
Total output
13
Reasoning within output
tag_management f005
100%
Passed
Tokens
81
Input
30
Total output
17
Reasoning within output
tag_management f006
100%
Passed
Tokens
66
Input
44
Total output
19
Reasoning within output
tag_management f007
66.7%
Failed
Tokens
64
Input
49
Total output
13
Reasoning within output
tag_management f008
100%
Passed
Tokens
68
Input
39
Total output
10
Reasoning within output
tag_management f009
100%
Passed
Tokens
68
Input
65
Total output
46
Reasoning within output
tag_management f010
100%
Passed
Tokens
49
Input
24
Total output
14
Reasoning within output
tag_management f011
100%
Passed
Tokens
50
Input
19
Total output
7
Reasoning within output
tag_management f012
100%
Passed
Tokens
89
Input
32
Total output
18
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
146
Input
25
Total output
10
Reasoning within output
worktree_usage f002
0%
Failed
Tokens
153
Input
257
Total output
231
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
224
Input
23
Total output
9
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
228
Input
19
Total output
12
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
142
Input
23
Total output
10
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
141
Input
31
Total output
15
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
139
Input
32
Total output
6
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
166
Input
56
Total output
12
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
257
Input
22
Total output
16
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
229
Input
57
Total output
37
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
219
Input
38
Total output
28
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
144
Input
62
Total output
47
Reasoning within output