Xiaomi / mimo-v2.6-pro
low
89.7%
183 / 204 fixtures · 1 run(s)
37,627 input / 29,199 total output / 15,540 reasoning within output tokens $0.04177088
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
+6.4%
Text: 89.7% →
JSON: 96.1%
+16
Gained
JSON pass / text fail
−3
Lost
Text pass / JSON fail
180
Unchanged Pass
Both pass
5
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| rebase | 41.7% | 91.7% | + 50% |
| worktree_usage | 58.3% | 91.7% | + 33.3% |
| merge_conflicts | 75% | 91.7% | + 16.7% |
| tag_management | 83.3% | 100% | + 16.7% |
| blame_forensics | 83.3% | 91.7% | + 8.3% |
| cherry_pick | 83.3% | 91.7% | + 8.3% |
| commit_squash | 100% | 91.7% | -8.3% |
| git_clean | 100% | 91.7% | -8.3% |
| reflog | 100% | 91.7% | -8.3% |
| branch_cleanup | 100% | 100% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_grep | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 100% | 100% | + 0% |
Changed Fixtures (19)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
248
Input
78
Total output
71
Reasoning within output
blame_forensics f002
0%
Failed
blame_forensics f003
100%
Passed
Tokens
269
Input
36
Total output
28
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
195
Input
274
Total output
267
Reasoning within output
blame_forensics f005
0%
Failed
blame_forensics f006
100%
Passed
Tokens
239
Input
178
Total output
173
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
222
Input
40
Total output
33
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
252
Input
84
Total output
78
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
200
Input
35
Total output
28
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
443
Input
43
Total output
38
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
244
Input
39
Total output
34
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
144
Input
133
Total output
126
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
104
Input
144
Total output
139
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
120
Input
283
Total output
276
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
100
Input
58
Total output
55
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
129
Input
36
Total output
29
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
110
Input
45
Total output
40
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
135
Input
29
Total output
18
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
107
Input
24
Total output
17
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
127
Input
59
Total output
48
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
85
Input
74
Total output
71
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
121
Input
53
Total output
46
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
71
Input
55
Total output
52
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
161
Input
32
Total output
20
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
92
Input
121
Total output
115
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
115
Input
154
Total output
145
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
86
Input
34
Total output
28
Reasoning within output
cherry_pick f004
100%
Passed
Tokens
159
Input
786
Total output
758
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
146
Input
38
Total output
15
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
140
Input
120
Total output
92
Reasoning within output
cherry_pick f007
0%
Failed
Tokens
130
Input
473
Total output
395
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
122
Input
27
Total output
15
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
106
Input
14
Total output
7
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
213
Input
55
Total output
27
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
159
Input
50
Total output
23
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
266
Input
168
Total output
123
Reasoning within output
commit_messages f001
70%
Passed
Tokens
112
Input
17
Total output
7
Reasoning within output
commit_messages f002
92.5%
Passed
Tokens
227
Input
47
Total output
37
Reasoning within output
commit_messages f003
92.5%
Passed
Tokens
84
Input
26
Total output
16
Reasoning within output
commit_messages f004
98%
Passed
Tokens
121
Input
31
Total output
26
Reasoning within output
commit_messages f005
71.5%
Passed
Tokens
105
Input
24
Total output
18
Reasoning within output
commit_messages f006
90%
Passed
Tokens
152
Input
16
Total output
7
Reasoning within output
commit_messages f007
95%
Passed
Tokens
192
Input
53
Total output
44
Reasoning within output
commit_messages f008
90%
Passed
Tokens
78
Input
58
Total output
52
Reasoning within output
commit_messages f009
85%
Passed
Tokens
129
Input
26
Total output
16
Reasoning within output
commit_messages f010
92.5%
Passed
Tokens
298
Input
35
Total output
26
Reasoning within output
commit_messages f011
67.5%
Passed
Tokens
145
Input
23
Total output
11
Reasoning within output
commit_messages f012
95%
Passed
Tokens
128
Input
13
Total output
6
Reasoning within output
commit_squash f001
100%
Passed
Tokens
140
Input
49
Total output
35
Reasoning within output
commit_squash f002
100%
Passed
Tokens
122
Input
34
Total output
24
Reasoning within output
commit_squash f003
100%
Passed
Tokens
131
Input
126
Total output
112
Reasoning within output
commit_squash f004
100%
Passed
Tokens
121
Input
34
Total output
21
Reasoning within output
commit_squash f005
100%
Passed
Tokens
119
Input
41
Total output
32
Reasoning within output
commit_squash f006
100%
Passed
Tokens
102
Input
64
Total output
51
Reasoning within output
commit_squash f007
100%
Passed
Tokens
106
Input
45
Total output
31
Reasoning within output
commit_squash f008
100%
Passed
Tokens
120
Input
176
Total output
162
Reasoning within output
commit_squash f009
100%
Passed
Tokens
112
Input
66
Total output
53
Reasoning within output
commit_squash f010
100%
Passed
Tokens
126
Input
59
Total output
42
Reasoning within output
commit_squash f011
100%
Passed
Tokens
133
Input
60
Total output
43
Reasoning within output
commit_squash f012
100%
Passed
Tokens
135
Input
248
Total output
226
Reasoning within output
git_bisect f001
100%
Passed
Tokens
185
Input
217
Total output
36
Reasoning within output
git_bisect f002
100%
Passed
Tokens
212
Input
438
Total output
78
Reasoning within output
git_bisect f003
100%
Passed
Tokens
210
Input
388
Total output
39
Reasoning within output
git_bisect f004
100%
Passed
Tokens
210
Input
144
Total output
19
Reasoning within output
git_bisect f005
100%
Passed
Tokens
210
Input
123
Total output
32
Reasoning within output
git_bisect f006
100%
Passed
Tokens
237
Input
344
Total output
16
Reasoning within output
git_bisect f007
100%
Passed
Tokens
208
Input
265
Total output
45
Reasoning within output
git_bisect f008
100%
Passed
Tokens
208
Input
296
Total output
23
Reasoning within output
git_bisect f009
100%
Passed
Tokens
204
Input
284
Total output
37
Reasoning within output
git_bisect f010
100%
Passed
Tokens
212
Input
361
Total output
60
Reasoning within output
git_bisect f011
100%
Passed
Tokens
214
Input
621
Total output
166
Reasoning within output
git_bisect f012
100%
Passed
Tokens
239
Input
601
Total output
137
Reasoning within output
git_clean f001
100%
Passed
Tokens
48
Input
17
Total output
11
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
11
Total output
5
Reasoning within output
git_clean f004
100%
Passed
Tokens
56
Input
20
Total output
13
Reasoning within output
git_clean f005
100%
Passed
Tokens
48
Input
125
Total output
117
Reasoning within output
git_clean f006
100%
Passed
Tokens
71
Input
20
Total output
12
Reasoning within output
git_clean f007
100%
Passed
Tokens
65
Input
23
Total output
13
Reasoning within output
git_clean f008
100%
Passed
Tokens
76
Input
11
Total output
5
Reasoning within output
git_clean f009
100%
Passed
Tokens
64
Input
628
Total output
620
Reasoning within output
git_clean f010
100%
Passed
Tokens
60
Input
36
Total output
30
Reasoning within output
git_clean f011
100%
Passed
Tokens
60
Input
38
Total output
31
Reasoning within output
git_clean f012
100%
Passed
Tokens
62
Input
71
Total output
60
Reasoning within output
git_grep f001
100%
Passed
Tokens
50
Input
13
Total output
8
Reasoning within output
git_grep f002
100%
Passed
Tokens
68
Input
11
Total output
8
Reasoning within output
git_grep f003
100%
Passed
Tokens
83
Input
12
Total output
9
Reasoning within output
git_grep f004
100%
Passed
Tokens
75
Input
13
Total output
6
Reasoning within output
git_grep f005
100%
Passed
Tokens
112
Input
11
Total output
8
Reasoning within output
git_grep f006
100%
Passed
Tokens
40
Input
42
Total output
39
Reasoning within output
git_grep f007
100%
Passed
Tokens
157
Input
185
Total output
181
Reasoning within output
git_grep f008
100%
Passed
Tokens
57
Input
8
Total output
5
Reasoning within output
git_grep f009
100%
Passed
Tokens
53
Input
31
Total output
26
Reasoning within output
git_grep f010
100%
Passed
Tokens
61
Input
9
Total output
6
Reasoning within output
git_grep f011
100%
Passed
Tokens
107
Input
10
Total output
7
Reasoning within output
git_grep f012
100%
Passed
Tokens
64
Input
28
Total output
18
Reasoning within output
git_log_format f001
100%
Passed
Tokens
884
Input
33
Total output
30
Reasoning within output
git_log_format f002
100%
Passed
Tokens
875
Input
34
Total output
25
Reasoning within output
git_log_format f003
100%
Passed
Tokens
701
Input
29
Total output
18
Reasoning within output
git_log_format f004
100%
Passed
Tokens
868
Input
27
Total output
24
Reasoning within output
git_log_format f005
100%
Passed
Tokens
723
Input
65
Total output
58
Reasoning within output
git_log_format f006
100%
Passed
Tokens
895
Input
79
Total output
76
Reasoning within output
git_log_format f007
100%
Passed
Tokens
901
Input
15
Total output
7
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,198
Input
5
Total output
2
Reasoning within output
git_log_format f009
100%
Passed
Tokens
729
Input
16
Total output
13
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,363
Input
18
Total output
15
Reasoning within output
git_log_format f011
100%
Passed
Tokens
427
Input
14
Total output
10
Reasoning within output
git_log_format f012
100%
Passed
Tokens
385
Input
8
Total output
5
Reasoning within output
git_show f001
100%
Passed
Tokens
189
Input
14
Total output
9
Reasoning within output
git_show f002
100%
Passed
Tokens
192
Input
93
Total output
89
Reasoning within output
git_show f003
100%
Passed
Tokens
676
Input
72
Total output
64
Reasoning within output
git_show f004
100%
Passed
Tokens
458
Input
20
Total output
12
Reasoning within output
git_show f005
100%
Passed
Tokens
200
Input
14
Total output
10
Reasoning within output
git_show f006
100%
Passed
Tokens
207
Input
5
Total output
2
Reasoning within output
git_show f007
100%
Passed
Tokens
195
Input
66
Total output
60
Reasoning within output
git_show f008
100%
Passed
Tokens
203
Input
84
Total output
47
Reasoning within output
git_show f009
100%
Passed
Tokens
311
Input
32
Total output
29
Reasoning within output
git_show f010
100%
Passed
Tokens
192
Input
5
Total output
2
Reasoning within output
git_show f011
100%
Passed
Tokens
220
Input
7
Total output
3
Reasoning within output
git_show f012
100%
Passed
Tokens
328
Input
5
Total output
2
Reasoning within output
merge_conflicts f001
0%
Failed
Tokens
81
Input
532
Total output
366
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
101
Input
250
Total output
241
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
76
Input
260
Total output
254
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
145
Input
88
Total output
60
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
132
Input
38
Total output
15
Reasoning within output
merge_conflicts f006
0%
Failed
Tokens
126
Input
135
Total output
103
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
131
Input
68
Total output
56
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
103
Input
47
Total output
39
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
100
Input
70
Total output
63
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
176
Input
97
Total output
59
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
138
Input
51
Total output
24
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
231
Input
251
Total output
199
Reasoning within output
rebase f001
0%
Failed
rebase f002
0%
Failed
rebase f003
0%
Failed
rebase f004
0%
Failed
rebase f005
0%
Failed
rebase f006
0%
Failed
rebase f007
100%
Passed
Tokens
133
Input
46
Total output
34
Reasoning within output
rebase f008
100%
Passed
Tokens
118
Input
53
Total output
45
Reasoning within output
rebase f009
100%
Passed
Tokens
99
Input
35
Total output
24
Reasoning within output
rebase f010
100%
Passed
Tokens
207
Input
92
Total output
54
Reasoning within output
rebase f011
100%
Passed
Tokens
149
Input
64
Total output
37
Reasoning within output
rebase f012
0%
Failed
Tokens
266
Input
513
Total output
462
Reasoning within output
reflog f001
100%
Passed
Tokens
257
Input
94
Total output
54
Reasoning within output
reflog f002
100%
Passed
Tokens
246
Input
695
Total output
284
Reasoning within output
reflog f003
100%
Passed
Tokens
213
Input
667
Total output
177
Reasoning within output
reflog f004
100%
Passed
Tokens
358
Input
1,473
Total output
819
Reasoning within output
reflog f005
100%
Passed
Tokens
396
Input
515
Total output
69
Reasoning within output
reflog f006
100%
Passed
Tokens
262
Input
519
Total output
97
Reasoning within output
reflog f007
100%
Passed
Tokens
310
Input
699
Total output
241
Reasoning within output
reflog f008
100%
Passed
Tokens
384
Input
571
Total output
247
Reasoning within output
reflog f009
100%
Passed
Tokens
375
Input
1,241
Total output
533
Reasoning within output
reflog f010
100%
Passed
Tokens
293
Input
546
Total output
175
Reasoning within output
reflog f011
100%
Passed
Tokens
359
Input
1,351
Total output
872
Reasoning within output
reflog f012
100%
Passed
Tokens
344
Input
2,027
Total output
1,286
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
136
Input
259
Total output
64
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
303
Input
340
Total output
44
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
123
Input
194
Total output
23
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
118
Input
178
Total output
53
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
126
Input
320
Total output
46
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
181
Input
284
Total output
81
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
210
Input
204
Total output
12
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
179
Input
174
Total output
37
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
209
Input
542
Total output
145
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
127
Input
356
Total output
31
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
122
Input
434
Total output
142
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
133
Input
193
Total output
35
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
42
Input
36
Total output
22
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
101
Input
37
Total output
28
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
103
Input
39
Total output
5
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
91
Input
9
Total output
4
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
49
Input
37
Total output
10
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
88
Input
9
Total output
4
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
49
Input
31
Total output
12
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
99
Input
13
Total output
6
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
94
Input
27
Total output
20
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
100
Input
39
Total output
28
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
106
Input
11
Total output
5
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
47
Input
56
Total output
39
Reasoning within output
tag_management f001
100%
Passed
Tokens
58
Input
21
Total output
12
Reasoning within output
tag_management f002
100%
Passed
Tokens
56
Input
31
Total output
8
Reasoning within output
tag_management f003
100%
Passed
Tokens
63
Input
30
Total output
7
Reasoning within output
tag_management f004
100%
Passed
Tokens
71
Input
12
Total output
8
Reasoning within output
tag_management f005
100%
Passed
Tokens
84
Input
24
Total output
15
Reasoning within output
tag_management f006
100%
Passed
Tokens
68
Input
43
Total output
28
Reasoning within output
tag_management f007
100%
Passed
Tokens
65
Input
259
Total output
246
Reasoning within output
tag_management f008
100%
Passed
Tokens
68
Input
96
Total output
70
Reasoning within output
tag_management f009
0%
Failed
tag_management f010
0%
Failed
tag_management f011
100%
Passed
Tokens
50
Input
20
Total output
13
Reasoning within output
tag_management f012
100%
Passed
Tokens
91
Input
21
Total output
10
Reasoning within output
worktree_usage f001
0%
Failed
worktree_usage f002
100%
Passed
Tokens
149
Input
32
Total output
8
Reasoning within output
worktree_usage f003
0%
Failed
worktree_usage f004
100%
Passed
Tokens
227
Input
19
Total output
13
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
140
Input
62
Total output
45
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
145
Input
37
Total output
21
Reasoning within output
worktree_usage f007
0%
Failed
worktree_usage f008
0%
Failed
worktree_usage f009
100%
Passed
Tokens
262
Input
42
Total output
36
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
237
Input
44
Total output
27
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
229
Input
27
Total output
17
Reasoning within output
worktree_usage f012
0%
Failed