Xiaomi / mimo-v2.6-flash
low
92.7%
189 / 204 fixtures · 1 run(s)
39,909 input / 23,399 total output / 12,457 reasoning within output tokens $0.01205556
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-4.9%
Text: 92.7% →
JSON: 87.8%
+8
Gained
JSON pass / text fail
−18
Lost
Text pass / JSON fail
171
Unchanged Pass
Both pass
7
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| commit_squash | 91.7% | 50% | -41.7% |
| reflog | 100% | 58.3% | -41.7% |
| branch_cleanup | 100% | 83.3% | -16.7% |
| git_grep | 91.7% | 100% | + 8.3% |
| git_log_format | 100% | 91.7% | -8.3% |
| git_show | 100% | 91.7% | -8.3% |
| merge_conflicts | 75% | 83.3% | + 8.3% |
| rebase | 75% | 83.3% | + 8.3% |
| tag_management | 91.7% | 100% | + 8.3% |
| blame_forensics | 100% | 100% | + 0% |
| cherry_pick | 75% | 75% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_clean | 83.3% | 83.3% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 100% | 100% | + 0% |
| worktree_usage | 91.7% | 91.7% | + 0% |
Changed Fixtures (26)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
249
Input
54
Total output
47
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
243
Input
45
Total output
39
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
277
Input
42
Total output
33
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
192
Input
338
Total output
331
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
268
Input
722
Total output
717
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
234
Input
57
Total output
52
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
219
Input
29
Total output
22
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
250
Input
63
Total output
57
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
198
Input
43
Total output
36
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
429
Input
65
Total output
59
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
247
Input
26
Total output
20
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
146
Input
50
Total output
42
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
105
Input
15
Total output
10
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
120
Input
18
Total output
11
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
100
Input
26
Total output
22
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
131
Input
22
Total output
14
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
107
Input
21
Total output
15
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
130
Input
41
Total output
30
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
110
Input
20
Total output
13
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
128
Input
52
Total output
41
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
83
Input
25
Total output
22
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
116
Input
19
Total output
11
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
72
Input
28
Total output
25
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
155
Input
19
Total output
6
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
92
Input
93
Total output
87
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
115
Input
154
Total output
144
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
87
Input
99
Total output
92
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
160
Input
80
Total output
50
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
147
Input
67
Total output
43
Reasoning within output
cherry_pick f006
0%
Failed
Tokens
140
Input
69
Total output
37
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
132
Input
98
Total output
81
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
121
Input
23
Total output
15
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
105
Input
20
Total output
12
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
211
Input
190
Total output
153
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
159
Input
43
Total output
15
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
264
Input
182
Total output
139
Reasoning within output
commit_messages f001
92.5%
Passed
Tokens
112
Input
15
Total output
10
Reasoning within output
commit_messages f002
87.5%
Passed
Tokens
227
Input
22
Total output
11
Reasoning within output
commit_messages f003
92.5%
Passed
Tokens
84
Input
25
Total output
15
Reasoning within output
commit_messages f004
90%
Passed
Tokens
121
Input
14
Total output
9
Reasoning within output
commit_messages f005
92%
Passed
Tokens
105
Input
23
Total output
16
Reasoning within output
commit_messages f006
92.5%
Passed
Tokens
152
Input
16
Total output
7
Reasoning within output
commit_messages f007
87.5%
Passed
Tokens
192
Input
15
Total output
6
Reasoning within output
commit_messages f008
95%
Passed
Tokens
78
Input
39
Total output
33
Reasoning within output
commit_messages f009
91.5%
Passed
Tokens
129
Input
18
Total output
9
Reasoning within output
commit_messages f010
86.5%
Passed
Tokens
298
Input
18
Total output
9
Reasoning within output
commit_messages f011
92.5%
Passed
Tokens
145
Input
40
Total output
29
Reasoning within output
commit_messages f012
95%
Passed
Tokens
128
Input
14
Total output
7
Reasoning within output
commit_squash f001
100%
Passed
Tokens
142
Input
246
Total output
231
Reasoning within output
commit_squash f002
100%
Passed
Tokens
120
Input
34
Total output
24
Reasoning within output
commit_squash f003
100%
Passed
Tokens
130
Input
25
Total output
10
Reasoning within output
commit_squash f004
100%
Failed
Tokens
120
Input
200
Total output
183
Reasoning within output
commit_squash f005
100%
Passed
Tokens
117
Input
28
Total output
19
Reasoning within output
commit_squash f006
100%
Passed
Tokens
103
Input
72
Total output
59
Reasoning within output
commit_squash f007
100%
Passed
Tokens
108
Input
93
Total output
79
Reasoning within output
commit_squash f008
100%
Passed
Tokens
118
Input
41
Total output
27
Reasoning within output
commit_squash f009
100%
Passed
Tokens
109
Input
79
Total output
65
Reasoning within output
commit_squash f010
100%
Passed
Tokens
126
Input
43
Total output
26
Reasoning within output
commit_squash f011
100%
Passed
Tokens
136
Input
45
Total output
28
Reasoning within output
commit_squash f012
100%
Passed
Tokens
133
Input
62
Total output
40
Reasoning within output
git_bisect f001
100%
Passed
Tokens
185
Input
189
Total output
24
Reasoning within output
git_bisect f002
100%
Passed
Tokens
210
Input
275
Total output
39
Reasoning within output
git_bisect f003
100%
Passed
Tokens
202
Input
245
Total output
55
Reasoning within output
git_bisect f004
100%
Passed
Tokens
212
Input
180
Total output
19
Reasoning within output
git_bisect f005
100%
Passed
Tokens
206
Input
132
Total output
24
Reasoning within output
git_bisect f006
100%
Passed
Tokens
239
Input
129
Total output
17
Reasoning within output
git_bisect f007
100%
Passed
Tokens
206
Input
149
Total output
23
Reasoning within output
git_bisect f008
100%
Passed
Tokens
214
Input
255
Total output
17
Reasoning within output
git_bisect f009
100%
Passed
Tokens
210
Input
211
Total output
21
Reasoning within output
git_bisect f010
100%
Passed
Tokens
214
Input
307
Total output
78
Reasoning within output
git_bisect f011
100%
Passed
Tokens
212
Input
164
Total output
42
Reasoning within output
git_bisect f012
100%
Passed
Tokens
233
Input
226
Total output
37
Reasoning within output
git_clean f001
100%
Passed
Tokens
48
Input
22
Total output
9
Reasoning within output
git_clean f002
100%
Passed
Tokens
59
Input
25
Total output
18
Reasoning within output
git_clean f003
100%
Passed
Tokens
56
Input
19
Total output
12
Reasoning within output
git_clean f004
66.7%
Failed
Tokens
56
Input
32
Total output
21
Reasoning within output
git_clean f005
100%
Passed
Tokens
48
Input
104
Total output
98
Reasoning within output
git_clean f006
100%
Passed
Tokens
71
Input
15
Total output
7
Reasoning within output
git_clean f007
100%
Passed
Tokens
65
Input
80
Total output
70
Reasoning within output
git_clean f008
100%
Passed
Tokens
76
Input
31
Total output
19
Reasoning within output
git_clean f009
100%
Passed
Tokens
64
Input
23
Total output
14
Reasoning within output
git_clean f010
100%
Passed
Tokens
60
Input
11
Total output
5
Reasoning within output
git_clean f011
40%
Failed
Tokens
60
Input
56
Total output
43
Reasoning within output
git_clean f012
100%
Passed
Tokens
62
Input
148
Total output
135
Reasoning within output
git_grep f001
100%
Passed
Tokens
50
Input
18
Total output
13
Reasoning within output
git_grep f002
100%
Passed
Tokens
64
Input
5
Total output
1
Reasoning within output
git_grep f003
100%
Passed
Tokens
83
Input
5
Total output
1
Reasoning within output
git_grep f004
0%
Failed
Tokens
75
Input
23
Total output
13
Reasoning within output
git_grep f005
100%
Passed
Tokens
112
Input
32
Total output
28
Reasoning within output
git_grep f006
100%
Passed
Tokens
40
Input
81
Total output
77
Reasoning within output
git_grep f007
100%
Passed
Tokens
157
Input
149
Total output
144
Reasoning within output
git_grep f008
100%
Passed
Tokens
57
Input
5
Total output
1
Reasoning within output
git_grep f009
100%
Passed
Tokens
53
Input
16
Total output
11
Reasoning within output
git_grep f010
100%
Passed
Tokens
61
Input
5
Total output
2
Reasoning within output
git_grep f011
100%
Passed
Tokens
107
Input
84
Total output
80
Reasoning within output
git_grep f012
100%
Passed
Tokens
64
Input
19
Total output
9
Reasoning within output
git_log_format f001
100%
Passed
Tokens
902
Input
5
Total output
1
Reasoning within output
git_log_format f002
100%
Passed
Tokens
898
Input
25
Total output
16
Reasoning within output
git_log_format f003
100%
Passed
Tokens
709
Input
32
Total output
21
Reasoning within output
git_log_format f004
100%
Passed
Tokens
901
Input
5
Total output
2
Reasoning within output
git_log_format f005
100%
Passed
Tokens
723
Input
40
Total output
32
Reasoning within output
git_log_format f006
100%
Passed
Tokens
895
Input
5
Total output
1
Reasoning within output
git_log_format f007
100%
Passed
Tokens
899
Input
17
Total output
7
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,205
Input
5
Total output
2
Reasoning within output
git_log_format f009
100%
Passed
Tokens
709
Input
23
Total output
19
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,384
Input
5
Total output
1
Reasoning within output
git_log_format f011
100%
Passed
Tokens
438
Input
36
Total output
32
Reasoning within output
git_log_format f012
100%
Passed
Tokens
395
Input
5
Total output
2
Reasoning within output
git_show f001
100%
Passed
Tokens
186
Input
13
Total output
7
Reasoning within output
git_show f002
100%
Passed
Tokens
194
Input
90
Total output
85
Reasoning within output
git_show f003
100%
Passed
Tokens
668
Input
37
Total output
29
Reasoning within output
git_show f004
100%
Passed
Tokens
460
Input
15
Total output
7
Reasoning within output
git_show f005
100%
Passed
Tokens
200
Input
224
Total output
220
Reasoning within output
git_show f006
100%
Passed
Tokens
203
Input
5
Total output
1
Reasoning within output
git_show f007
100%
Passed
Tokens
195
Input
55
Total output
48
Reasoning within output
git_show f008
100%
Passed
Tokens
199
Input
71
Total output
37
Reasoning within output
git_show f009
100%
Passed
Tokens
313
Input
40
Total output
37
Reasoning within output
git_show f010
100%
Passed
Tokens
193
Input
5
Total output
1
Reasoning within output
git_show f011
100%
Passed
Tokens
224
Input
11
Total output
7
Reasoning within output
git_show f012
100%
Passed
Tokens
330
Input
5
Total output
1
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
81
Input
43
Total output
37
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
101
Input
67
Total output
57
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
76
Input
68
Total output
61
Reasoning within output
merge_conflicts f004
0%
Failed
Tokens
145
Input
318
Total output
282
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
132
Input
51
Total output
28
Reasoning within output
merge_conflicts f006
0%
Failed
Tokens
126
Input
130
Total output
97
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
131
Input
126
Total output
109
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
103
Input
23
Total output
15
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
100
Input
30
Total output
23
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
176
Input
156
Total output
127
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
138
Input
73
Total output
50
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
231
Input
109
Total output
66
Reasoning within output
rebase f001
100%
Passed
Tokens
92
Input
1,244
Total output
1,238
Reasoning within output
rebase f002
100%
Passed
Tokens
122
Input
35
Total output
26
Reasoning within output
rebase f003
100%
Passed
Tokens
100
Input
25
Total output
20
Reasoning within output
rebase f004
0%
Failed
Tokens
158
Input
666
Total output
630
Reasoning within output
rebase f005
100%
Passed
Tokens
137
Input
39
Total output
18
Reasoning within output
rebase f006
0%
Failed
Tokens
140
Input
596
Total output
563
Reasoning within output
rebase f007
100%
Passed
Tokens
134
Input
87
Total output
74
Reasoning within output
rebase f008
100%
Passed
Tokens
116
Input
30
Total output
21
Reasoning within output
rebase f009
100%
Passed
Tokens
101
Input
55
Total output
47
Reasoning within output
rebase f010
100%
Passed
Tokens
207
Input
221
Total output
193
Reasoning within output
rebase f011
100%
Passed
Tokens
149
Input
51
Total output
27
Reasoning within output
rebase f012
0%
Failed
Tokens
266
Input
89
Total output
41
Reasoning within output
reflog f001
100%
Passed
Tokens
259
Input
98
Total output
59
Reasoning within output
reflog f002
100%
Passed
Tokens
243
Input
412
Total output
52
Reasoning within output
reflog f003
100%
Passed
Tokens
210
Input
417
Total output
14
Reasoning within output
reflog f004
100%
Passed
Tokens
359
Input
1,055
Total output
537
Reasoning within output
reflog f005
100%
Passed
Tokens
405
Input
493
Total output
67
Reasoning within output
reflog f006
100%
Passed
Tokens
269
Input
493
Total output
26
Reasoning within output
reflog f007
100%
Passed
Tokens
301
Input
161
Total output
18
Reasoning within output
reflog f008
100%
Passed
Tokens
395
Input
562
Total output
92
Reasoning within output
reflog f009
100%
Passed
Tokens
353
Input
546
Total output
137
Reasoning within output
reflog f010
100%
Passed
Tokens
304
Input
800
Total output
76
Reasoning within output
reflog f011
100%
Passed
Tokens
358
Input
859
Total output
459
Reasoning within output
reflog f012
100%
Passed
Tokens
349
Input
985
Total output
411
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
137
Input
78
Total output
17
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
300
Input
282
Total output
76
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
123
Input
274
Total output
39
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
118
Input
174
Total output
14
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
127
Input
257
Total output
13
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
181
Input
286
Total output
23
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
214
Input
109
Total output
10
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
179
Input
144
Total output
10
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
209
Input
91
Total output
15
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
127
Input
68
Total output
10
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
120
Input
162
Total output
47
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
133
Input
221
Total output
66
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
42
Input
23
Total output
9
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
95
Input
37
Total output
22
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
105
Input
343
Total output
315
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
91
Input
9
Total output
3
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
49
Input
52
Total output
16
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
88
Input
19
Total output
13
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
49
Input
29
Total output
6
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
98
Input
34
Total output
23
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
94
Input
14
Total output
4
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
99
Input
22
Total output
13
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
105
Input
21
Total output
15
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
47
Input
27
Total output
9
Reasoning within output
tag_management f001
100%
Passed
Tokens
59
Input
22
Total output
14
Reasoning within output
tag_management f002
100%
Passed
Tokens
56
Input
42
Total output
23
Reasoning within output
tag_management f003
100%
Passed
Tokens
64
Input
16
Total output
5
Reasoning within output
tag_management f004
100%
Passed
Tokens
71
Input
20
Total output
12
Reasoning within output
tag_management f005
100%
Passed
Tokens
84
Input
20
Total output
8
Reasoning within output
tag_management f006
100%
Passed
Tokens
66
Input
54
Total output
31
Reasoning within output
tag_management f007
66.7%
Failed
Tokens
63
Input
58
Total output
19
Reasoning within output
tag_management f008
100%
Passed
Tokens
68
Input
170
Total output
124
Reasoning within output
tag_management f009
100%
Passed
Tokens
71
Input
29
Total output
9
Reasoning within output
tag_management f010
100%
Passed
Tokens
50
Input
18
Total output
9
Reasoning within output
tag_management f011
100%
Passed
Tokens
51
Input
25
Total output
13
Reasoning within output
tag_management f012
100%
Passed
Tokens
91
Input
102
Total output
87
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
149
Input
40
Total output
24
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
152
Input
45
Total output
21
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
230
Input
19
Total output
8
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
222
Input
19
Total output
12
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
144
Input
23
Total output
10
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
142
Input
47
Total output
26
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
145
Input
44
Total output
19
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
166
Input
62
Total output
13
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
268
Input
15
Total output
5
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
239
Input
29
Total output
10
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
231
Input
23
Total output
8
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
141
Input
39
Total output
23
Reasoning within output