Ibm-granite / granite-4.2-8b
low
79.9%
163 / 204 fixtures · 1 run(s)
40,904 input / 15,517 total output / 7,459 reasoning within output tokens $0.00599665
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-4.9%
Text: 79.9% →
JSON: 75%
+16
Gained
JSON pass / text fail
−26
Lost
Text pass / JSON fail
137
Unchanged Pass
Both pass
25
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| blame_forensics | 0% | 83.3% | + 83.3% |
| branch_cleanup | 91.7% | 41.7% | -50% |
| commit_squash | 66.7% | 33.3% | -33.3% |
| reflog | 100% | 66.7% | -33.3% |
| rebase | 83.3% | 58.3% | -25% |
| git_clean | 50% | 33.3% | -16.7% |
| git_grep | 100% | 83.3% | -16.7% |
| worktree_usage | 66.7% | 83.3% | + 16.7% |
| merge_conflicts | 66.7% | 58.3% | -8.3% |
| tag_management | 91.7% | 83.3% | -8.3% |
| cherry_pick | 66.7% | 75% | + 8.3% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_log_format | 91.7% | 91.7% | + 0% |
| git_show | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 83.3% | 83.3% | + 0% |
Changed Fixtures (42)
f001 +gain f002 +gain f003 +gain f004 +gain f006 +gain f007 +gain f008 +gain f009 +gain f011 +gain f012 +gain f002 -loss f003 -loss f004 -loss f009 -loss f010 -loss f011 -loss f002 +gain f006 -loss f011 +gain f001 -loss f002 -loss f005 +gain f008 -loss f009 -loss f011 -loss f003 -loss f005 -loss f006 -loss f007 -loss f006 -loss f005 -loss f006 -loss f011 -loss f004 -loss f006 -loss f007 -loss f011 -loss f006 +gain f012 -loss f008 -loss f004 +gain f009 +gain
Fixture Gallery (204)
blame_forensics f001
0%
Failed
Tokens
260
Input
106
Total output
107
Reasoning within output
blame_forensics f002
0%
Failed
Tokens
240
Input
21
Total output
14
Reasoning within output
blame_forensics f003
0%
Failed
Tokens
275
Input
22
Total output
14
Reasoning within output
blame_forensics f004
0%
Failed
Tokens
211
Input
29
Total output
23
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
256
Input
51
Total output
57
Reasoning within output
blame_forensics f006
0%
Failed
Tokens
244
Input
58
Total output
45
Reasoning within output
blame_forensics f007
0%
Failed
Tokens
214
Input
20
Total output
14
Reasoning within output
blame_forensics f008
0%
Failed
Tokens
250
Input
33
Total output
30
Reasoning within output
blame_forensics f009
0%
Failed
Tokens
209
Input
22
Total output
21
Reasoning within output
blame_forensics f010
0%
Failed
Tokens
428
Input
29
Total output
23
Reasoning within output
blame_forensics f011
0%
Failed
Tokens
248
Input
35
Total output
25
Reasoning within output
blame_forensics f012
0%
Failed
Tokens
162
Input
35
Total output
30
Reasoning within output
branch_cleanup f001
0%
Failed
Tokens
122
Input
25
Total output
26
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
137
Input
37
Total output
29
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
115
Input
19
Total output
18
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
151
Input
32
Total output
25
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
130
Input
32
Total output
28
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
144
Input
39
Total output
30
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
129
Input
48
Total output
45
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
140
Input
37
Total output
27
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
100
Input
28
Total output
28
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
132
Input
47
Total output
38
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
89
Input
9
Total output
6
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
176
Input
78
Total output
57
Reasoning within output
cherry_pick f001
0%
Failed
Tokens
116
Input
58
Total output
57
Reasoning within output
cherry_pick f002
0%
Failed
Tokens
134
Input
67
Total output
32
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
108
Input
20
Total output
16
Reasoning within output
cherry_pick f004
100%
Passed
Tokens
171
Input
153
Total output
118
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
173
Input
39
Total output
22
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
152
Input
101
Total output
65
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
148
Input
30
Total output
19
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
145
Input
20
Total output
14
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
125
Input
25
Total output
19
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
239
Input
86
Total output
62
Reasoning within output
cherry_pick f011
0%
Failed
Tokens
188
Input
89
Total output
54
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
296
Input
87
Total output
30
Reasoning within output
commit_messages f001
66%
Passed
Tokens
126
Input
227
Total output
152
Reasoning within output
commit_messages f002
77.5%
Passed
Tokens
236
Input
46
Total output
36
Reasoning within output
commit_messages f003
95%
Passed
Tokens
106
Input
34
Total output
19
Reasoning within output
commit_messages f004
95%
Passed
Tokens
136
Input
26
Total output
20
Reasoning within output
commit_messages f005
87.5%
Passed
Tokens
125
Input
46
Total output
36
Reasoning within output
commit_messages f006
91%
Passed
Tokens
155
Input
108
Total output
78
Reasoning within output
commit_messages f007
89%
Passed
Tokens
213
Input
30
Total output
20
Reasoning within output
commit_messages f008
90%
Passed
Tokens
92
Input
23
Total output
14
Reasoning within output
commit_messages f009
94%
Passed
Tokens
149
Input
71
Total output
48
Reasoning within output
commit_messages f010
85%
Passed
Tokens
312
Input
163
Total output
122
Reasoning within output
commit_messages f011
84%
Passed
Tokens
171
Input
22
Total output
12
Reasoning within output
commit_messages f012
92.5%
Passed
Tokens
148
Input
21
Total output
16
Reasoning within output
commit_squash f001
100%
Passed
Tokens
156
Input
366
Total output
335
Reasoning within output
commit_squash f002
100%
Passed
Tokens
133
Input
32
Total output
19
Reasoning within output
commit_squash f003
0%
Failed
Tokens
147
Input
77
Total output
51
Reasoning within output
commit_squash f004
100%
Passed
Tokens
132
Input
69
Total output
59
Reasoning within output
commit_squash f005
0%
Failed
Tokens
129
Input
73
Total output
63
Reasoning within output
commit_squash f006
100%
Passed
Tokens
115
Input
30
Total output
11
Reasoning within output
commit_squash f007
0%
Failed
Tokens
119
Input
82
Total output
55
Reasoning within output
commit_squash f008
100%
Passed
Tokens
130
Input
38
Total output
14
Reasoning within output
commit_squash f009
100%
Passed
Tokens
123
Input
49
Total output
30
Reasoning within output
commit_squash f010
0%
Failed
Tokens
133
Input
43
Total output
14
Reasoning within output
commit_squash f011
100%
Passed
Tokens
145
Input
44
Total output
22
Reasoning within output
commit_squash f012
100%
Passed
Tokens
143
Input
47
Total output
31
Reasoning within output
git_bisect f001
100%
Passed
Tokens
196
Input
19
Total output
7
Reasoning within output
git_bisect f002
100%
Passed
Tokens
220
Input
22
Total output
11
Reasoning within output
git_bisect f003
100%
Passed
Tokens
220
Input
24
Total output
13
Reasoning within output
git_bisect f004
100%
Passed
Tokens
220
Input
22
Total output
11
Reasoning within output
git_bisect f005
100%
Passed
Tokens
226
Input
20
Total output
11
Reasoning within output
git_bisect f006
100%
Passed
Tokens
244
Input
21
Total output
11
Reasoning within output
git_bisect f007
100%
Passed
Tokens
214
Input
25
Total output
11
Reasoning within output
git_bisect f008
100%
Passed
Tokens
222
Input
40
Total output
36
Reasoning within output
git_bisect f009
100%
Passed
Tokens
214
Input
36
Total output
26
Reasoning within output
git_bisect f010
100%
Passed
Tokens
224
Input
38
Total output
24
Reasoning within output
git_bisect f011
100%
Passed
Tokens
222
Input
30
Total output
25
Reasoning within output
git_bisect f012
100%
Passed
Tokens
240
Input
36
Total output
32
Reasoning within output
git_clean f001
50%
Failed
Tokens
74
Input
53
Total output
43
Reasoning within output
git_clean f002
100%
Passed
Tokens
87
Input
78
Total output
62
Reasoning within output
git_clean f003
100%
Passed
Tokens
87
Input
25
Total output
18
Reasoning within output
git_clean f004
33.3%
Failed
Tokens
86
Input
154
Total output
126
Reasoning within output
git_clean f005
100%
Passed
Tokens
74
Input
241
Total output
248
Reasoning within output
git_clean f006
75%
Failed
Tokens
104
Input
229
Total output
176
Reasoning within output
git_clean f007
50%
Failed
Tokens
96
Input
233
Total output
209
Reasoning within output
git_clean f008
100%
Passed
Tokens
108
Input
43
Total output
30
Reasoning within output
git_clean f009
100%
Passed
Tokens
98
Input
34
Total output
25
Reasoning within output
git_clean f010
100%
Passed
Tokens
90
Input
101
Total output
81
Reasoning within output
git_clean f011
40%
Failed
Tokens
89
Input
209
Total output
169
Reasoning within output
git_clean f012
50%
Failed
Tokens
94
Input
118
Total output
89
Reasoning within output
git_grep f001
100%
Passed
Tokens
73
Input
13
Total output
6
Reasoning within output
git_grep f002
100%
Passed
Tokens
79
Input
35
Total output
31
Reasoning within output
git_grep f003
100%
Passed
Tokens
125
Input
8
Total output
4
Reasoning within output
git_grep f004
100%
Passed
Tokens
101
Input
18
Total output
6
Reasoning within output
git_grep f005
100%
Passed
Tokens
139
Input
26
Total output
21
Reasoning within output
git_grep f006
100%
Passed
Tokens
57
Input
32
Total output
28
Reasoning within output
git_grep f007
100%
Passed
Tokens
199
Input
165
Total output
117
Reasoning within output
git_grep f008
100%
Passed
Tokens
81
Input
12
Total output
10
Reasoning within output
git_grep f009
100%
Passed
Tokens
74
Input
12
Total output
4
Reasoning within output
git_grep f010
100%
Passed
Tokens
88
Input
63
Total output
59
Reasoning within output
git_grep f011
100%
Passed
Tokens
151
Input
15
Total output
10
Reasoning within output
git_grep f012
100%
Passed
Tokens
89
Input
27
Total output
10
Reasoning within output
git_log_format f001
100%
Passed
Tokens
767
Input
40
Total output
36
Reasoning within output
git_log_format f002
100%
Passed
Tokens
751
Input
32
Total output
28
Reasoning within output
git_log_format f003
100%
Passed
Tokens
614
Input
27
Total output
17
Reasoning within output
git_log_format f004
100%
Passed
Tokens
755
Input
37
Total output
23
Reasoning within output
git_log_format f005
0%
Failed
Tokens
621
Input
51
Total output
39
Reasoning within output
git_log_format f006
100%
Passed
Tokens
777
Input
58
Total output
39
Reasoning within output
git_log_format f007
100%
Passed
Tokens
782
Input
23
Total output
12
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,034
Input
36
Total output
24
Reasoning within output
git_log_format f009
100%
Passed
Tokens
614
Input
10
Total output
4
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,130
Input
14
Total output
9
Reasoning within output
git_log_format f011
100%
Passed
Tokens
405
Input
51
Total output
39
Reasoning within output
git_log_format f012
100%
Passed
Tokens
359
Input
9
Total output
4
Reasoning within output
git_show f001
100%
Passed
Tokens
199
Input
16
Total output
8
Reasoning within output
git_show f002
100%
Passed
Tokens
204
Input
53
Total output
48
Reasoning within output
git_show f003
100%
Passed
Tokens
653
Input
61
Total output
31
Reasoning within output
git_show f004
100%
Passed
Tokens
449
Input
25
Total output
13
Reasoning within output
git_show f005
100%
Passed
Tokens
210
Input
35
Total output
36
Reasoning within output
git_show f006
100%
Passed
Tokens
216
Input
10
Total output
4
Reasoning within output
git_show f007
100%
Passed
Tokens
198
Input
16
Total output
6
Reasoning within output
git_show f008
100%
Passed
Tokens
214
Input
67
Total output
18
Reasoning within output
git_show f009
100%
Passed
Tokens
295
Input
64
Total output
62
Reasoning within output
git_show f010
100%
Passed
Tokens
212
Input
10
Total output
5
Reasoning within output
git_show f011
100%
Passed
Tokens
230
Input
11
Total output
5
Reasoning within output
git_show f012
100%
Passed
Tokens
342
Input
10
Total output
5
Reasoning within output
merge_conflicts f001
0%
Failed
Tokens
105
Input
35
Total output
38
Reasoning within output
merge_conflicts f002
0%
Failed
Tokens
123
Input
95
Total output
50
Reasoning within output
merge_conflicts f003
0%
Failed
Tokens
98
Input
58
Total output
61
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
159
Input
64
Total output
39
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
161
Input
51
Total output
28
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
139
Input
148
Total output
92
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
154
Input
41
Total output
32
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
130
Input
27
Total output
17
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
122
Input
35
Total output
28
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
204
Input
154
Total output
143
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
167
Input
58
Total output
26
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
259
Input
82
Total output
26
Reasoning within output
rebase f001
0%
Failed
Tokens
117
Input
96
Total output
102
Reasoning within output
rebase f002
100%
Passed
Tokens
143
Input
98
Total output
78
Reasoning within output
rebase f003
100%
Passed
Tokens
122
Input
20
Total output
18
Reasoning within output
rebase f004
100%
Passed
Tokens
171
Input
117
Total output
73
Reasoning within output
rebase f005
100%
Passed
Tokens
167
Input
26
Total output
9
Reasoning within output
rebase f006
100%
Passed
Tokens
152
Input
111
Total output
65
Reasoning within output
rebase f007
100%
Passed
Tokens
151
Input
32
Total output
20
Reasoning within output
rebase f008
100%
Passed
Tokens
142
Input
18
Total output
11
Reasoning within output
rebase f009
100%
Passed
Tokens
121
Input
19
Total output
10
Reasoning within output
rebase f010
100%
Passed
Tokens
229
Input
138
Total output
102
Reasoning within output
rebase f011
100%
Passed
Tokens
176
Input
101
Total output
60
Reasoning within output
rebase f012
0%
Failed
Tokens
288
Input
120
Total output
50
Reasoning within output
reflog f001
100%
Passed
Tokens
233
Input
94
Total output
43
Reasoning within output
reflog f002
100%
Passed
Tokens
213
Input
505
Total output
21
Reasoning within output
reflog f003
100%
Passed
Tokens
204
Input
219
Total output
16
Reasoning within output
reflog f004
100%
Passed
Tokens
304
Input
465
Total output
58
Reasoning within output
reflog f005
100%
Passed
Tokens
349
Input
183
Total output
18
Reasoning within output
reflog f006
100%
Passed
Tokens
239
Input
186
Total output
18
Reasoning within output
reflog f007
100%
Passed
Tokens
266
Input
269
Total output
16
Reasoning within output
reflog f008
100%
Passed
Tokens
328
Input
270
Total output
33
Reasoning within output
reflog f009
100%
Passed
Tokens
290
Input
445
Total output
31
Reasoning within output
reflog f010
100%
Passed
Tokens
263
Input
590
Total output
11
Reasoning within output
reflog f011
100%
Passed
Tokens
302
Input
475
Total output
42
Reasoning within output
reflog f012
100%
Passed
Tokens
310
Input
439
Total output
6
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
156
Input
79
Total output
7
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
313
Input
196
Total output
7
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
145
Input
121
Total output
6
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
141
Input
121
Total output
7
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
152
Input
161
Total output
11
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
210
Input
17
Total output
7
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
233
Input
113
Total output
7
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
202
Input
35
Total output
6
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
237
Input
203
Total output
7
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
153
Input
51
Total output
7
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
139
Input
154
Total output
7
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
163
Input
142
Total output
6
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
61
Input
23
Total output
13
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
115
Input
32
Total output
28
Reasoning within output
submodule_usage f003
50%
Failed
Tokens
122
Input
38
Total output
8
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
111
Input
43
Total output
43
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
68
Input
61
Total output
38
Reasoning within output
submodule_usage f006
0%
Failed
Tokens
107
Input
41
Total output
41
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
68
Input
48
Total output
29
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
113
Input
46
Total output
47
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
110
Input
26
Total output
24
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
115
Input
19
Total output
10
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
122
Input
12
Total output
6
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
66
Input
35
Total output
22
Reasoning within output
tag_management f001
100%
Passed
Tokens
77
Input
57
Total output
33
Reasoning within output
tag_management f002
100%
Passed
Tokens
74
Input
25
Total output
6
Reasoning within output
tag_management f003
100%
Passed
Tokens
82
Input
106
Total output
62
Reasoning within output
tag_management f004
100%
Passed
Tokens
86
Input
17
Total output
10
Reasoning within output
tag_management f005
100%
Passed
Tokens
96
Input
26
Total output
15
Reasoning within output
tag_management f006
100%
Passed
Tokens
84
Input
90
Total output
51
Reasoning within output
tag_management f007
66.7%
Failed
Tokens
83
Input
220
Total output
124
Reasoning within output
tag_management f008
100%
Passed
Tokens
87
Input
155
Total output
91
Reasoning within output
tag_management f009
100%
Passed
Tokens
89
Input
39
Total output
15
Reasoning within output
tag_management f010
100%
Passed
Tokens
69
Input
21
Total output
10
Reasoning within output
tag_management f011
100%
Passed
Tokens
68
Input
18
Total output
11
Reasoning within output
tag_management f012
100%
Passed
Tokens
103
Input
52
Total output
40
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
152
Input
44
Total output
33
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
158
Input
46
Total output
22
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
218
Input
42
Total output
33
Reasoning within output
worktree_usage f004
0%
Failed
Tokens
220
Input
32
Total output
25
Reasoning within output
worktree_usage f005
33.3%
Failed
Tokens
148
Input
34
Total output
21
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
146
Input
34
Total output
17
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
155
Input
36
Total output
12
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
173
Input
64
Total output
7
Reasoning within output
worktree_usage f009
0%
Failed
Tokens
256
Input
63
Total output
7
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
228
Input
61
Total output
41
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
219
Input
22
Total output
12
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
143
Input
35
Total output
16
Reasoning within output