Mistralai / devstral-2512
default
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
+11.3%
Text: 81.9% →
JSON: 93.1%
+29
Gained
JSON pass / text fail
−6
Lost
Text pass / JSON fail
161
Unchanged Pass
Both pass
8
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| commit_squash | 33.3% | 100% | + 66.7% |
| rebase | 50% | 91.7% | + 41.7% |
| cherry_pick | 58.3% | 91.7% | + 33.3% |
| merge_conflicts | 58.3% | 91.7% | + 33.3% |
| branch_cleanup | 100% | 75% | -25% |
| submodule_usage | 83.3% | 100% | + 16.7% |
| worktree_usage | 83.3% | 100% | + 16.7% |
| git_grep | 83.3% | 91.7% | + 8.3% |
| blame_forensics | 75% | 83.3% | + 8.3% |
| git_clean | 83.3% | 75% | -8.3% |
| git_log_format | 91.7% | 100% | + 8.3% |
| tag_management | 100% | 91.7% | -8.3% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_show | 91.7% | 91.7% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
Changed Fixtures (35)
f001 +gain f006 -loss f010 +gain f003 -loss f009 -loss f011 -loss f004 +gain f005 +gain f007 +gain f008 +gain f001 +gain f003 +gain f005 +gain f008 +gain f009 +gain f010 +gain f011 +gain f012 +gain f004 -loss f011 +gain f006 +gain f005 +gain f007 +gain f008 +gain f010 +gain f004 +gain f005 +gain f007 +gain f008 +gain f010 +gain f004 +gain f011 +gain f008 -loss f007 +gain f008 +gain
Fixture Gallery (204)
blame_forensics f001
0%
Failed
Tokens
250
Input
20
Output
blame_forensics f002
100%
Passed
Tokens
239
Input
5
Output
blame_forensics f003
100%
Passed
Tokens
281
Input
7
Output
blame_forensics f004
100%
Passed
Tokens
191
Input
6
Output
blame_forensics f005
0%
Failed
Tokens
270
Input
17
Output
blame_forensics f006
100%
Passed
Tokens
225
Input
4
Output
blame_forensics f007
100%
Passed
Tokens
223
Input
6
Output
blame_forensics f008
100%
Passed
Tokens
249
Input
5
Output
blame_forensics f009
100%
Passed
Tokens
200
Input
6
Output
blame_forensics f010
0%
Failed
Tokens
446
Input
5
Output
blame_forensics f011
100%
Passed
Tokens
244
Input
4
Output
blame_forensics f012
100%
Passed
Tokens
145
Input
7
Output
branch_cleanup f001
100%
Passed
Tokens
106
Input
5
Output
branch_cleanup f002
100%
Passed
Tokens
114
Input
6
Output
branch_cleanup f003
100%
Passed
Tokens
96
Input
2
Output
branch_cleanup f004
100%
Passed
Tokens
136
Input
6
Output
branch_cleanup f005
100%
Passed
Tokens
105
Input
4
Output
branch_cleanup f006
100%
Passed
Tokens
125
Input
10
Output
branch_cleanup f007
100%
Passed
Tokens
104
Input
6
Output
branch_cleanup f008
100%
Passed
Tokens
123
Input
11
Output
branch_cleanup f009
100%
Passed
Tokens
82
Input
2
Output
branch_cleanup f010
100%
Passed
Tokens
118
Input
6
Output
branch_cleanup f011
100%
Passed
Tokens
66
Input
2
Output
branch_cleanup f012
100%
Passed
Tokens
157
Input
12
Output
cherry_pick f001
100%
Passed
Tokens
96
Input
5
Output
cherry_pick f002
100%
Passed
Tokens
122
Input
9
Output
cherry_pick f003
100%
Passed
Tokens
90
Input
5
Output
cherry_pick f004
0%
Failed
Tokens
164
Input
118
Output
cherry_pick f005
0%
Failed
Tokens
152
Input
29
Output
cherry_pick f006
100%
Passed
Tokens
145
Input
27
Output
cherry_pick f007
0%
Failed
Tokens
141
Input
30
Output
cherry_pick f008
0%
Failed
Tokens
122
Input
34
Output
cherry_pick f009
100%
Passed
Tokens
110
Input
6
Output
cherry_pick f010
100%
Passed
Tokens
228
Input
29
Output
cherry_pick f011
100%
Passed
Tokens
163
Input
26
Output
cherry_pick f012
0%
Failed
Tokens
277
Input
63
Output
commit_messages f001
87.7%
Passed
Tokens
109
Input
8
Output
commit_messages f002
73.3%
Passed
Tokens
226
Input
11
Output
commit_messages f003
90%
Passed
Tokens
81
Input
10
Output
commit_messages f004
93.3%
Passed
Tokens
118
Input
4
Output
commit_messages f005
89.3%
Passed
Tokens
103
Input
7
Output
commit_messages f006
90%
Passed
Tokens
149
Input
7
Output
commit_messages f007
84.3%
Passed
Tokens
191
Input
8
Output
commit_messages f008
92.5%
Passed
Tokens
74
Input
7
Output
commit_messages f009
92.3%
Passed
Tokens
130
Input
10
Output
commit_messages f010
93.3%
Passed
Tokens
298
Input
10
Output
commit_messages f011
59.7%
Passed
Tokens
142
Input
16
Output
commit_messages f012
87.7%
Passed
Tokens
121
Input
8
Output
commit_squash f001
0%
Failed
Tokens
141
Input
27
Output
commit_squash f002
100%
Passed
Tokens
115
Input
9
Output
commit_squash f003
0%
Failed
Tokens
131
Input
27
Output
commit_squash f004
100%
Passed
Tokens
119
Input
12
Output
commit_squash f005
0%
Failed
Tokens
113
Input
20
Output
commit_squash f006
100%
Passed
Tokens
101
Input
13
Output
commit_squash f007
100%
Passed
Tokens
103
Input
13
Output
commit_squash f008
0%
Failed
Tokens
117
Input
25
Output
commit_squash f009
0%
Failed
Tokens
108
Input
26
Output
commit_squash f010
0%
Failed
Tokens
126
Input
30
Output
commit_squash f011
0%
Failed
Tokens
134
Input
29
Output
commit_squash f012
0%
Failed
Tokens
132
Input
39
Output
git_bisect f001
100%
Passed
Tokens
183
Input
58
Output
git_bisect f002
100%
Passed
Tokens
213
Input
96
Output
git_bisect f003
100%
Passed
Tokens
209
Input
74
Output
git_bisect f004
100%
Passed
Tokens
213
Input
94
Output
git_bisect f005
100%
Passed
Tokens
211
Input
92
Output
git_bisect f006
100%
Passed
Tokens
235
Input
92
Output
git_bisect f007
100%
Passed
Tokens
213
Input
93
Output
git_bisect f008
100%
Passed
Tokens
215
Input
89
Output
git_bisect f009
100%
Passed
Tokens
209
Input
62
Output
git_bisect f010
100%
Passed
Tokens
211
Input
68
Output
git_bisect f011
100%
Passed
Tokens
213
Input
127
Output
git_bisect f012
100%
Passed
Tokens
235
Input
91
Output
git_clean f001
100%
Passed
Tokens
48
Input
14
Output
git_clean f002
100%
Passed
Tokens
58
Input
10
Output
git_clean f003
100%
Passed
Tokens
54
Input
10
Output
git_clean f004
100%
Passed
Tokens
56
Input
11
Output
git_clean f005
75%
Failed
Tokens
46
Input
10
Output
git_clean f006
100%
Passed
Tokens
73
Input
14
Output
git_clean f007
100%
Passed
Tokens
68
Input
15
Output
git_clean f008
100%
Passed
Tokens
72
Input
10
Output
git_clean f009
100%
Passed
Tokens
63
Input
12
Output
git_clean f010
100%
Passed
Tokens
60
Input
10
Output
git_clean f011
100%
Passed
Tokens
59
Input
11
Output
git_clean f012
66.7%
Failed
Tokens
62
Input
11
Output
git_grep f001
100%
Passed
Tokens
49
Input
4
Output
git_grep f002
100%
Passed
Tokens
62
Input
2
Output
git_grep f003
100%
Passed
Tokens
82
Input
2
Output
git_grep f004
100%
Passed
Tokens
72
Input
6
Output
git_grep f005
100%
Passed
Tokens
106
Input
2
Output
git_grep f006
100%
Passed
Tokens
36
Input
2
Output
git_grep f007
0%
Failed
Tokens
156
Input
2
Output
git_grep f008
100%
Passed
Tokens
55
Input
2
Output
git_grep f009
100%
Passed
Tokens
49
Input
4
Output
git_grep f010
100%
Passed
Tokens
59
Input
2
Output
git_grep f011
0%
Failed
Tokens
104
Input
2
Output
git_grep f012
100%
Passed
Tokens
60
Input
9
Output
git_log_format f001
100%
Passed
Tokens
894
Input
2
Output
git_log_format f002
100%
Passed
Tokens
894
Input
8
Output
git_log_format f003
100%
Passed
Tokens
735
Input
10
Output
git_log_format f004
100%
Passed
Tokens
899
Input
2
Output
git_log_format f005
100%
Passed
Tokens
735
Input
6
Output
git_log_format f006
0%
Failed
Tokens
914
Input
2
Output
git_log_format f007
100%
Passed
Tokens
919
Input
6
Output
git_log_format f008
100%
Passed
Tokens
1,216
Input
2
Output
git_log_format f009
100%
Passed
Tokens
742
Input
2
Output
git_log_format f010
100%
Passed
Tokens
1,397
Input
2
Output
git_log_format f011
100%
Passed
Tokens
440
Input
3
Output
git_log_format f012
100%
Passed
Tokens
405
Input
2
Output
git_show f001
100%
Passed
Tokens
199
Input
5
Output
git_show f002
0%
Failed
Tokens
196
Input
21
Output
git_show f003
100%
Passed
Tokens
682
Input
7
Output
git_show f004
100%
Passed
Tokens
465
Input
7
Output
git_show f005
100%
Passed
Tokens
196
Input
3
Output
git_show f006
100%
Passed
Tokens
199
Input
2
Output
git_show f007
100%
Passed
Tokens
192
Input
5
Output
git_show f008
100%
Passed
Tokens
206
Input
38
Output
git_show f009
100%
Passed
Tokens
314
Input
2
Output
git_show f010
100%
Passed
Tokens
193
Input
2
Output
git_show f011
100%
Passed
Tokens
227
Input
3
Output
git_show f012
100%
Passed
Tokens
330
Input
2
Output
merge_conflicts f001
100%
Passed
Tokens
85
Input
5
Output
merge_conflicts f002
100%
Passed
Tokens
109
Input
9
Output
merge_conflicts f003
100%
Passed
Tokens
79
Input
5
Output
merge_conflicts f004
100%
Passed
Tokens
150
Input
26
Output
merge_conflicts f005
0%
Failed
Tokens
137
Input
29
Output
merge_conflicts f006
100%
Passed
Tokens
130
Input
27
Output
merge_conflicts f007
0%
Failed
Tokens
140
Input
31
Output
merge_conflicts f008
0%
Failed
Tokens
106
Input
30
Output
merge_conflicts f009
100%
Passed
Tokens
106
Input
6
Output
merge_conflicts f010
0%
Failed
Tokens
189
Input
36
Output
merge_conflicts f011
100%
Passed
Tokens
143
Input
26
Output
merge_conflicts f012
0%
Failed
Tokens
244
Input
60
Output
rebase f001
100%
Passed
Tokens
96
Input
5
Output
rebase f002
100%
Passed
Tokens
131
Input
9
Output
rebase f003
100%
Passed
Tokens
103
Input
4
Output
rebase f004
0%
Failed
Tokens
163
Input
112
Output
rebase f005
0%
Failed
Tokens
144
Input
26
Output
rebase f006
100%
Passed
Tokens
145
Input
27
Output
rebase f007
0%
Failed
Tokens
144
Input
30
Output
rebase f008
0%
Failed
Tokens
121
Input
29
Output
rebase f009
100%
Passed
Tokens
105
Input
6
Output
rebase f010
0%
Failed
Tokens
220
Input
38
Output
rebase f011
100%
Passed
Tokens
155
Input
26
Output
rebase f012
0%
Failed
Tokens
279
Input
54
Output
reflog f001
100%
Passed
Tokens
244
Input
50
Output
reflog f002
100%
Passed
Tokens
241
Input
151
Output
reflog f003
100%
Passed
Tokens
209
Input
146
Output
reflog f004
100%
Passed
Tokens
351
Input
271
Output
reflog f005
100%
Passed
Tokens
398
Input
83
Output
reflog f006
100%
Passed
Tokens
254
Input
190
Output
reflog f007
100%
Passed
Tokens
295
Input
308
Output
reflog f008
100%
Passed
Tokens
383
Input
242
Output
reflog f009
100%
Passed
Tokens
336
Input
226
Output
reflog f010
100%
Passed
Tokens
300
Input
212
Output
reflog f011
100%
Passed
Tokens
343
Input
292
Output
reflog f012
100%
Passed
Tokens
337
Input
326
Output
stash_recovery f001
100%
Passed
Tokens
137
Input
64
Output
stash_recovery f002
100%
Passed
Tokens
303
Input
123
Output
stash_recovery f003
100%
Passed
Tokens
123
Input
141
Output
stash_recovery f004
100%
Passed
Tokens
119
Input
80
Output
stash_recovery f005
100%
Passed
Tokens
131
Input
66
Output
stash_recovery f006
100%
Passed
Tokens
182
Input
79
Output
stash_recovery f007
100%
Passed
Tokens
216
Input
114
Output
stash_recovery f008
100%
Passed
Tokens
181
Input
86
Output
stash_recovery f009
100%
Passed
Tokens
216
Input
99
Output
stash_recovery f010
100%
Passed
Tokens
128
Input
70
Output
stash_recovery f011
100%
Passed
Tokens
122
Input
64
Output
stash_recovery f012
100%
Passed
Tokens
137
Input
129
Output
submodule_usage f001
100%
Passed
Tokens
39
Input
15
Output
submodule_usage f002
100%
Passed
Tokens
97
Input
15
Output
submodule_usage f003
100%
Passed
Tokens
103
Input
59
Output
submodule_usage f004
0%
Failed
Tokens
86
Input
10
Output
submodule_usage f005
100%
Passed
Tokens
46
Input
37
Output
submodule_usage f006
100%
Passed
Tokens
87
Input
10
Output
submodule_usage f007
100%
Passed
Tokens
47
Input
25
Output
submodule_usage f008
100%
Passed
Tokens
95
Input
14
Output
submodule_usage f009
100%
Passed
Tokens
94
Input
13
Output
submodule_usage f010
100%
Passed
Tokens
100
Input
13
Output
submodule_usage f011
0%
Failed
Tokens
100
Input
10
Output
submodule_usage f012
100%
Passed
Tokens
46
Input
18
Output
tag_management f001
100%
Passed
Tokens
56
Input
12
Output
tag_management f002
100%
Passed
Tokens
52
Input
24
Output
tag_management f003
100%
Passed
Tokens
59
Input
15
Output
tag_management f004
100%
Passed
Tokens
68
Input
8
Output
tag_management f005
100%
Passed
Tokens
82
Input
13
Output
tag_management f006
100%
Passed
Tokens
64
Input
24
Output
tag_management f007
100%
Passed
Tokens
59
Input
33
Output
tag_management f008
100%
Passed
Tokens
66
Input
31
Output
tag_management f009
100%
Passed
Tokens
67
Input
23
Output
tag_management f010
100%
Passed
Tokens
45
Input
13
Output
tag_management f011
100%
Passed
Tokens
47
Input
11
Output
tag_management f012
100%
Passed
Tokens
84
Input
17
Output
worktree_usage f001
100%
Passed
Tokens
147
Input
15
Output
worktree_usage f002
100%
Passed
Tokens
153
Input
28
Output
worktree_usage f003
100%
Passed
Tokens
236
Input
14
Output
worktree_usage f004
100%
Passed
Tokens
231
Input
10
Output
worktree_usage f005
100%
Passed
Tokens
142
Input
19
Output
worktree_usage f006
100%
Passed
Tokens
145
Input
21
Output
worktree_usage f007
0%
Failed
Tokens
145
Input
34
Output
worktree_usage f008
50%
Failed
Tokens
167
Input
48
Output
worktree_usage f009
100%
Passed
Tokens
267
Input
6
Output
worktree_usage f010
100%
Passed
Tokens
244
Input
21
Output
worktree_usage f011
100%
Passed
Tokens
236
Input
14
Output
worktree_usage f012
100%
Passed
Tokens
139
Input
19
Output