Prism-ml / ternary-bonsai-2-27b
none
84.8%
173 / 204 fixtures · 1 run(s)
41,705 input / 7,839 total output / 0 reasoning within output tokens $0.00704737
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-0.5%
Text: 84.8% →
JSON: 84.3%
+15
Gained
JSON pass / text fail
−16
Lost
Text pass / JSON fail
157
Unchanged Pass
Both pass
16
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| commit_squash | 33.3% | 83.3% | + 50% |
| submodule_usage | 91.7% | 58.3% | -33.3% |
| branch_cleanup | 100% | 66.7% | -33.3% |
| tag_management | 100% | 75% | -25% |
| worktree_usage | 75% | 100% | + 25% |
| blame_forensics | 58.3% | 75% | + 16.7% |
| cherry_pick | 83.3% | 75% | -8.3% |
| git_clean | 58.3% | 50% | -8.3% |
| git_log_format | 91.7% | 100% | + 8.3% |
| merge_conflicts | 75% | 83.3% | + 8.3% |
| reflog | 100% | 91.7% | -8.3% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_grep | 91.7% | 91.7% | + 0% |
| git_show | 100% | 100% | + 0% |
| rebase | 83.3% | 83.3% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
Changed Fixtures (31)
f001 -loss f002 +gain f006 +gain f009 +gain f001 -loss f003 -loss f009 -loss f011 -loss f010 -loss f001 +gain f002 +gain f003 +gain f007 +gain f009 +gain f010 +gain f001 -loss f006 -loss f009 +gain f006 +gain f007 +gain f008 -loss f005 -loss f009 -loss f010 -loss f012 -loss f007 -loss f008 -loss f011 -loss f005 +gain f008 +gain f010 +gain
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
258
Input
6
Total output
0
Reasoning within output
blame_forensics f002
0%
Failed
Tokens
259
Input
12
Total output
0
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
286
Input
7
Total output
0
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
206
Input
6
Total output
0
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
273
Input
4
Total output
0
Reasoning within output
blame_forensics f006
0%
Failed
Tokens
248
Input
14
Total output
0
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
224
Input
6
Total output
0
Reasoning within output
blame_forensics f008
0%
Failed
Tokens
262
Input
12
Total output
0
Reasoning within output
blame_forensics f009
0%
Failed
Tokens
211
Input
12
Total output
0
Reasoning within output
blame_forensics f010
0%
Failed
Tokens
455
Input
4
Total output
0
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
264
Input
4
Total output
0
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
159
Input
6
Total output
0
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
113
Input
4
Total output
0
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
127
Input
6
Total output
0
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
108
Input
2
Total output
0
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
145
Input
6
Total output
0
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
111
Input
4
Total output
0
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
137
Input
10
Total output
0
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
111
Input
6
Total output
0
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
137
Input
10
Total output
0
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
92
Input
2
Total output
0
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
127
Input
6
Total output
0
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
77
Input
2
Total output
0
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
170
Input
11
Total output
0
Reasoning within output
cherry_pick f001
0%
Failed
Tokens
102
Input
5
Total output
0
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
122
Input
8
Total output
0
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
96
Input
5
Total output
0
Reasoning within output
cherry_pick f004
100%
Passed
Tokens
162
Input
26
Total output
0
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
158
Input
19
Total output
0
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
149
Input
23
Total output
0
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
141
Input
11
Total output
0
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
130
Input
7
Total output
0
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
110
Input
6
Total output
0
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
226
Input
29
Total output
0
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
172
Input
25
Total output
0
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
283
Input
44
Total output
0
Reasoning within output
commit_messages f001
82.5%
Passed
Tokens
119
Input
10
Total output
0
Reasoning within output
commit_messages f002
92.5%
Passed
Tokens
235
Input
9
Total output
0
Reasoning within output
commit_messages f003
98%
Passed
Tokens
90
Input
9
Total output
0
Reasoning within output
commit_messages f004
90%
Passed
Tokens
127
Input
4
Total output
0
Reasoning within output
commit_messages f005
92.5%
Passed
Tokens
111
Input
5
Total output
0
Reasoning within output
commit_messages f006
92.5%
Passed
Tokens
158
Input
7
Total output
0
Reasoning within output
commit_messages f007
93%
Passed
Tokens
199
Input
8
Total output
0
Reasoning within output
commit_messages f008
92.5%
Passed
Tokens
83
Input
7
Total output
0
Reasoning within output
commit_messages f009
81.5%
Passed
Tokens
137
Input
11
Total output
0
Reasoning within output
commit_messages f010
89%
Passed
Tokens
307
Input
8
Total output
0
Reasoning within output
commit_messages f011
82.5%
Passed
Tokens
156
Input
9
Total output
0
Reasoning within output
commit_messages f012
92.5%
Passed
Tokens
137
Input
6
Total output
0
Reasoning within output
commit_squash f001
0%
Failed
Tokens
148
Input
27
Total output
0
Reasoning within output
commit_squash f002
0%
Failed
Tokens
128
Input
16
Total output
0
Reasoning within output
commit_squash f003
0%
Failed
Tokens
135
Input
24
Total output
0
Reasoning within output
commit_squash f004
0%
Failed
Tokens
126
Input
25
Total output
0
Reasoning within output
commit_squash f005
0%
Failed
Tokens
124
Input
11
Total output
0
Reasoning within output
commit_squash f006
100%
Passed
Tokens
110
Input
12
Total output
0
Reasoning within output
commit_squash f007
0%
Failed
Tokens
111
Input
26
Total output
0
Reasoning within output
commit_squash f008
100%
Passed
Tokens
124
Input
13
Total output
0
Reasoning within output
commit_squash f009
0%
Failed
Tokens
119
Input
26
Total output
0
Reasoning within output
commit_squash f010
0%
Failed
Tokens
130
Input
30
Total output
0
Reasoning within output
commit_squash f011
100%
Passed
Tokens
140
Input
16
Total output
0
Reasoning within output
commit_squash f012
100%
Passed
Tokens
137
Input
21
Total output
0
Reasoning within output
git_bisect f001
100%
Passed
Tokens
194
Input
106
Total output
0
Reasoning within output
git_bisect f002
100%
Passed
Tokens
222
Input
136
Total output
0
Reasoning within output
git_bisect f003
100%
Passed
Tokens
220
Input
8
Total output
0
Reasoning within output
git_bisect f004
100%
Passed
Tokens
226
Input
154
Total output
0
Reasoning within output
git_bisect f005
100%
Passed
Tokens
220
Input
89
Total output
0
Reasoning within output
git_bisect f006
100%
Passed
Tokens
246
Input
6
Total output
0
Reasoning within output
git_bisect f007
100%
Passed
Tokens
220
Input
11
Total output
0
Reasoning within output
git_bisect f008
100%
Passed
Tokens
224
Input
137
Total output
0
Reasoning within output
git_bisect f009
100%
Passed
Tokens
222
Input
16
Total output
0
Reasoning within output
git_bisect f010
100%
Passed
Tokens
220
Input
9
Total output
0
Reasoning within output
git_bisect f011
100%
Passed
Tokens
224
Input
73
Total output
0
Reasoning within output
git_bisect f012
100%
Passed
Tokens
252
Input
137
Total output
0
Reasoning within output
git_clean f001
100%
Passed
Tokens
57
Input
5
Total output
0
Reasoning within output
git_clean f002
100%
Passed
Tokens
68
Input
5
Total output
0
Reasoning within output
git_clean f003
100%
Passed
Tokens
67
Input
5
Total output
0
Reasoning within output
git_clean f004
33.3%
Failed
Tokens
64
Input
8
Total output
0
Reasoning within output
git_clean f005
50%
Failed
Tokens
56
Input
34
Total output
0
Reasoning within output
git_clean f006
100%
Passed
Tokens
81
Input
29
Total output
0
Reasoning within output
git_clean f007
100%
Passed
Tokens
72
Input
12
Total output
0
Reasoning within output
git_clean f008
100%
Passed
Tokens
84
Input
5
Total output
0
Reasoning within output
git_clean f009
75%
Failed
Tokens
75
Input
10
Total output
0
Reasoning within output
git_clean f010
100%
Passed
Tokens
70
Input
9
Total output
0
Reasoning within output
git_clean f011
40%
Failed
Tokens
68
Input
13
Total output
0
Reasoning within output
git_clean f012
50%
Failed
Tokens
70
Input
45
Total output
0
Reasoning within output
git_grep f001
100%
Passed
Tokens
56
Input
4
Total output
0
Reasoning within output
git_grep f002
100%
Passed
Tokens
72
Input
2
Total output
0
Reasoning within output
git_grep f003
100%
Passed
Tokens
91
Input
2
Total output
0
Reasoning within output
git_grep f004
100%
Passed
Tokens
80
Input
6
Total output
0
Reasoning within output
git_grep f005
100%
Passed
Tokens
121
Input
2
Total output
0
Reasoning within output
git_grep f006
100%
Passed
Tokens
45
Input
2
Total output
0
Reasoning within output
git_grep f007
0%
Failed
Tokens
173
Input
3
Total output
0
Reasoning within output
git_grep f008
100%
Passed
Tokens
62
Input
2
Total output
0
Reasoning within output
git_grep f009
100%
Passed
Tokens
58
Input
4
Total output
0
Reasoning within output
git_grep f010
100%
Passed
Tokens
68
Input
2
Total output
0
Reasoning within output
git_grep f011
100%
Passed
Tokens
116
Input
2
Total output
0
Reasoning within output
git_grep f012
100%
Passed
Tokens
69
Input
9
Total output
0
Reasoning within output
git_log_format f001
100%
Passed
Tokens
937
Input
2
Total output
0
Reasoning within output
git_log_format f002
100%
Passed
Tokens
889
Input
8
Total output
0
Reasoning within output
git_log_format f003
100%
Passed
Tokens
743
Input
10
Total output
0
Reasoning within output
git_log_format f004
100%
Passed
Tokens
907
Input
2
Total output
0
Reasoning within output
git_log_format f005
100%
Passed
Tokens
741
Input
6
Total output
0
Reasoning within output
git_log_format f006
0%
Failed
Tokens
915
Input
2
Total output
0
Reasoning within output
git_log_format f007
100%
Passed
Tokens
915
Input
7
Total output
0
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,217
Input
2
Total output
0
Reasoning within output
git_log_format f009
100%
Passed
Tokens
739
Input
2
Total output
0
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,382
Input
2
Total output
0
Reasoning within output
git_log_format f011
100%
Passed
Tokens
454
Input
3
Total output
0
Reasoning within output
git_log_format f012
100%
Passed
Tokens
413
Input
2
Total output
0
Reasoning within output
git_show f001
100%
Passed
Tokens
203
Input
4
Total output
0
Reasoning within output
git_show f002
100%
Passed
Tokens
206
Input
3
Total output
0
Reasoning within output
git_show f003
100%
Passed
Tokens
695
Input
7
Total output
0
Reasoning within output
git_show f004
100%
Passed
Tokens
478
Input
7
Total output
0
Reasoning within output
git_show f005
100%
Passed
Tokens
207
Input
3
Total output
0
Reasoning within output
git_show f006
100%
Passed
Tokens
212
Input
2
Total output
0
Reasoning within output
git_show f007
100%
Passed
Tokens
206
Input
5
Total output
0
Reasoning within output
git_show f008
100%
Passed
Tokens
212
Input
35
Total output
0
Reasoning within output
git_show f009
100%
Passed
Tokens
329
Input
2
Total output
0
Reasoning within output
git_show f010
100%
Passed
Tokens
203
Input
2
Total output
0
Reasoning within output
git_show f011
100%
Passed
Tokens
228
Input
3
Total output
0
Reasoning within output
git_show f012
100%
Passed
Tokens
345
Input
2
Total output
0
Reasoning within output
merge_conflicts f001
0%
Failed
Tokens
90
Input
5
Total output
0
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
108
Input
8
Total output
0
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
83
Input
5
Total output
0
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
150
Input
26
Total output
0
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
142
Input
19
Total output
0
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
134
Input
23
Total output
0
Reasoning within output
merge_conflicts f007
0%
Failed
Tokens
138
Input
11
Total output
0
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
110
Input
7
Total output
0
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
107
Input
6
Total output
0
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
187
Input
29
Total output
0
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
151
Input
25
Total output
0
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
242
Input
44
Total output
0
Reasoning within output
rebase f001
0%
Failed
Tokens
103
Input
5
Total output
0
Reasoning within output
rebase f002
100%
Passed
Tokens
129
Input
8
Total output
0
Reasoning within output
rebase f003
100%
Passed
Tokens
108
Input
4
Total output
0
Reasoning within output
rebase f004
100%
Passed
Tokens
164
Input
26
Total output
0
Reasoning within output
rebase f005
100%
Passed
Tokens
149
Input
16
Total output
0
Reasoning within output
rebase f006
100%
Passed
Tokens
150
Input
28
Total output
0
Reasoning within output
rebase f007
100%
Passed
Tokens
141
Input
11
Total output
0
Reasoning within output
rebase f008
100%
Passed
Tokens
126
Input
7
Total output
0
Reasoning within output
rebase f009
100%
Passed
Tokens
106
Input
6
Total output
0
Reasoning within output
rebase f010
100%
Passed
Tokens
216
Input
29
Total output
0
Reasoning within output
rebase f011
100%
Passed
Tokens
163
Input
25
Total output
0
Reasoning within output
rebase f012
0%
Failed
Tokens
279
Input
44
Total output
0
Reasoning within output
reflog f001
100%
Passed
Tokens
257
Input
33
Total output
0
Reasoning within output
reflog f002
100%
Passed
Tokens
255
Input
337
Total output
0
Reasoning within output
reflog f003
100%
Passed
Tokens
219
Input
116
Total output
0
Reasoning within output
reflog f004
100%
Passed
Tokens
360
Input
469
Total output
0
Reasoning within output
reflog f005
100%
Passed
Tokens
430
Input
232
Total output
0
Reasoning within output
reflog f006
100%
Passed
Tokens
264
Input
437
Total output
0
Reasoning within output
reflog f007
100%
Passed
Tokens
311
Input
131
Total output
0
Reasoning within output
reflog f008
100%
Passed
Tokens
403
Input
700
Total output
0
Reasoning within output
reflog f009
100%
Passed
Tokens
341
Input
372
Total output
0
Reasoning within output
reflog f010
100%
Passed
Tokens
307
Input
198
Total output
0
Reasoning within output
reflog f011
100%
Passed
Tokens
356
Input
424
Total output
0
Reasoning within output
reflog f012
100%
Passed
Tokens
357
Input
999
Total output
0
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
142
Input
80
Total output
0
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
310
Input
7
Total output
0
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
131
Input
32
Total output
0
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
126
Input
84
Total output
0
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
137
Input
52
Total output
0
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
190
Input
68
Total output
0
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
223
Input
30
Total output
0
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
188
Input
42
Total output
0
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
218
Input
62
Total output
0
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
135
Input
7
Total output
0
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
130
Input
73
Total output
0
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
141
Input
16
Total output
0
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
48
Input
9
Total output
0
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
105
Input
10
Total output
0
Reasoning within output
submodule_usage f003
75%
Failed
Tokens
106
Input
28
Total output
0
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
97
Input
4
Total output
0
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
55
Input
32
Total output
0
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
97
Input
4
Total output
0
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
55
Input
20
Total output
0
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
107
Input
8
Total output
0
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
104
Input
10
Total output
0
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
107
Input
9
Total output
0
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
112
Input
5
Total output
0
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
53
Input
17
Total output
0
Reasoning within output
tag_management f001
100%
Passed
Tokens
67
Input
7
Total output
0
Reasoning within output
tag_management f002
100%
Passed
Tokens
65
Input
19
Total output
0
Reasoning within output
tag_management f003
100%
Passed
Tokens
69
Input
10
Total output
0
Reasoning within output
tag_management f004
100%
Passed
Tokens
77
Input
3
Total output
0
Reasoning within output
tag_management f005
100%
Passed
Tokens
87
Input
7
Total output
0
Reasoning within output
tag_management f006
100%
Passed
Tokens
75
Input
14
Total output
0
Reasoning within output
tag_management f007
100%
Passed
Tokens
70
Input
12
Total output
0
Reasoning within output
tag_management f008
100%
Passed
Tokens
75
Input
25
Total output
0
Reasoning within output
tag_management f009
100%
Passed
Tokens
79
Input
22
Total output
0
Reasoning within output
tag_management f010
100%
Passed
Tokens
54
Input
8
Total output
0
Reasoning within output
tag_management f011
100%
Passed
Tokens
60
Input
6
Total output
0
Reasoning within output
tag_management f012
100%
Passed
Tokens
97
Input
11
Total output
0
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
154
Input
10
Total output
0
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
156
Input
23
Total output
0
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
233
Input
9
Total output
0
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
230
Input
5
Total output
0
Reasoning within output
worktree_usage f005
33.3%
Failed
Tokens
142
Input
10
Total output
0
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
145
Input
13
Total output
0
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
150
Input
20
Total output
0
Reasoning within output
worktree_usage f008
50%
Failed
Tokens
174
Input
52
Total output
0
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
261
Input
5
Total output
0
Reasoning within output
worktree_usage f010
0%
Failed
Tokens
247
Input
16
Total output
0
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
229
Input
9
Total output
0
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
145
Input
14
Total output
0
Reasoning within output