Prism-ml / ternary-bonsai-2-27b
medium
93.6%
191 / 204 fixtures · 1 run(s)
41,440 input / 65,566 total output / 56,303 reasoning within output tokens $0.03589100
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-2.9%
Text: 93.6% →
JSON: 90.7%
+8
Gained
JSON pass / text fail
−14
Lost
Text pass / JSON fail
177
Unchanged Pass
Both pass
5
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| branch_cleanup | 100% | 75% | -25% |
| git_grep | 100% | 83.3% | -16.7% |
| git_clean | 83.3% | 66.7% | -16.7% |
| cherry_pick | 83.3% | 91.7% | + 8.3% |
| rebase | 83.3% | 91.7% | + 8.3% |
| submodule_usage | 91.7% | 83.3% | -8.3% |
| worktree_usage | 83.3% | 91.7% | + 8.3% |
| blame_forensics | 91.7% | 100% | + 8.3% |
| commit_squash | 100% | 91.7% | -8.3% |
| reflog | 100% | 91.7% | -8.3% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 91.7% | 91.7% | + 0% |
| merge_conflicts | 83.3% | 83.3% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
Changed Fixtures (22)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
262
Input
355
Total output
347
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
257
Input
332
Total output
325
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
287
Input
187
Total output
178
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
208
Input
244
Total output
236
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
273
Input
1,027
Total output
1,020
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
244
Input
678
Total output
672
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
226
Input
224
Total output
216
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
264
Input
312
Total output
305
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
210
Input
288
Total output
281
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
450
Input
598
Total output
592
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
262
Input
170
Total output
164
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
153
Input
323
Total output
315
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
111
Input
131
Total output
125
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
121
Input
180
Total output
172
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
103
Input
213
Total output
209
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
141
Input
155
Total output
147
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
109
Input
160
Total output
154
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
137
Input
261
Total output
249
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
109
Input
102
Total output
94
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
128
Input
175
Total output
163
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
89
Input
133
Total output
129
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
126
Input
201
Total output
193
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
75
Input
156
Total output
152
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
168
Input
215
Total output
202
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
101
Input
379
Total output
372
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
118
Input
366
Total output
356
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
91
Input
604
Total output
597
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
163
Input
2,099
Total output
2,073
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
155
Input
202
Total output
181
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
146
Input
281
Total output
251
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
137
Input
295
Total output
282
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
127
Input
135
Total output
126
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
111
Input
128
Total output
120
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
222
Input
290
Total output
259
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
171
Input
294
Total output
267
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
275
Input
529
Total output
474
Reasoning within output
commit_messages f001
92.5%
Passed
Tokens
117
Input
174
Total output
168
Reasoning within output
commit_messages f002
82.5%
Passed
Tokens
233
Input
155
Total output
142
Reasoning within output
commit_messages f003
92.5%
Passed
Tokens
88
Input
111
Total output
100
Reasoning within output
commit_messages f004
93%
Passed
Tokens
125
Input
107
Total output
101
Reasoning within output
commit_messages f005
94%
Passed
Tokens
109
Input
199
Total output
192
Reasoning within output
commit_messages f006
82.5%
Passed
Tokens
156
Input
251
Total output
243
Reasoning within output
commit_messages f007
95%
Passed
Tokens
197
Input
176
Total output
167
Reasoning within output
commit_messages f008
92%
Passed
Tokens
81
Input
167
Total output
160
Reasoning within output
commit_messages f009
90%
Passed
Tokens
135
Input
166
Total output
154
Reasoning within output
commit_messages f010
92.5%
Passed
Tokens
305
Input
199
Total output
187
Reasoning within output
commit_messages f011
84%
Passed
Tokens
154
Input
342
Total output
327
Reasoning within output
commit_messages f012
91.5%
Passed
Tokens
135
Input
136
Total output
128
Reasoning within output
commit_squash f001
100%
Passed
Tokens
145
Input
364
Total output
349
Reasoning within output
commit_squash f002
100%
Passed
Tokens
123
Input
233
Total output
222
Reasoning within output
commit_squash f003
100%
Passed
Tokens
135
Input
252
Total output
237
Reasoning within output
commit_squash f004
100%
Passed
Tokens
126
Input
355
Total output
341
Reasoning within output
commit_squash f005
100%
Passed
Tokens
121
Input
250
Total output
240
Reasoning within output
commit_squash f006
100%
Passed
Tokens
104
Input
286
Total output
272
Reasoning within output
commit_squash f007
100%
Passed
Tokens
111
Input
217
Total output
202
Reasoning within output
commit_squash f008
100%
Passed
Tokens
124
Input
291
Total output
276
Reasoning within output
commit_squash f009
100%
Passed
Tokens
114
Input
229
Total output
215
Reasoning within output
commit_squash f010
100%
Passed
Tokens
131
Input
230
Total output
212
Reasoning within output
commit_squash f011
100%
Passed
Tokens
136
Input
216
Total output
198
Reasoning within output
commit_squash f012
100%
Passed
Tokens
137
Input
239
Total output
216
Reasoning within output
git_bisect f001
100%
Passed
Tokens
188
Input
263
Total output
180
Reasoning within output
git_bisect f002
100%
Passed
Tokens
220
Input
321
Total output
141
Reasoning within output
git_bisect f003
100%
Passed
Tokens
216
Input
333
Total output
193
Reasoning within output
git_bisect f004
100%
Passed
Tokens
220
Input
275
Total output
126
Reasoning within output
git_bisect f005
100%
Passed
Tokens
222
Input
249
Total output
176
Reasoning within output
git_bisect f006
100%
Passed
Tokens
248
Input
267
Total output
157
Reasoning within output
git_bisect f007
100%
Passed
Tokens
216
Input
294
Total output
123
Reasoning within output
git_bisect f008
100%
Passed
Tokens
214
Input
331
Total output
203
Reasoning within output
git_bisect f009
100%
Passed
Tokens
218
Input
291
Total output
159
Reasoning within output
git_bisect f010
100%
Passed
Tokens
224
Input
277
Total output
147
Reasoning within output
git_bisect f011
100%
Passed
Tokens
224
Input
269
Total output
166
Reasoning within output
git_bisect f012
100%
Passed
Tokens
248
Input
344
Total output
156
Reasoning within output
git_clean f001
100%
Passed
Tokens
55
Input
391
Total output
384
Reasoning within output
git_clean f002
100%
Passed
Tokens
66
Input
153
Total output
146
Reasoning within output
git_clean f003
100%
Passed
Tokens
65
Input
125
Total output
118
Reasoning within output
git_clean f004
0%
Failed
Tokens
62
Input
1,038
Total output
1,031
Reasoning within output
git_clean f005
100%
Passed
Tokens
54
Input
601
Total output
590
Reasoning within output
git_clean f006
100%
Passed
Tokens
79
Input
370
Total output
361
Reasoning within output
git_clean f007
100%
Passed
Tokens
70
Input
299
Total output
286
Reasoning within output
git_clean f008
100%
Passed
Tokens
82
Input
136
Total output
129
Reasoning within output
git_clean f009
100%
Passed
Tokens
73
Input
158
Total output
148
Reasoning within output
git_clean f010
100%
Passed
Tokens
68
Input
60
Total output
53
Reasoning within output
git_clean f011
100%
Passed
Tokens
66
Input
745
Total output
733
Reasoning within output
git_clean f012
50%
Failed
Tokens
68
Input
298
Total output
288
Reasoning within output
git_grep f001
100%
Passed
Tokens
54
Input
69
Total output
63
Reasoning within output
git_grep f002
100%
Passed
Tokens
69
Input
85
Total output
81
Reasoning within output
git_grep f003
100%
Passed
Tokens
89
Input
99
Total output
95
Reasoning within output
git_grep f004
100%
Passed
Tokens
78
Input
101
Total output
93
Reasoning within output
git_grep f005
100%
Passed
Tokens
119
Input
147
Total output
143
Reasoning within output
git_grep f006
100%
Passed
Tokens
43
Input
197
Total output
193
Reasoning within output
git_grep f007
100%
Passed
Tokens
171
Input
297
Total output
292
Reasoning within output
git_grep f008
100%
Passed
Tokens
60
Input
111
Total output
107
Reasoning within output
git_grep f009
100%
Passed
Tokens
56
Input
67
Total output
61
Reasoning within output
git_grep f010
100%
Passed
Tokens
66
Input
370
Total output
366
Reasoning within output
git_grep f011
100%
Passed
Tokens
114
Input
103
Total output
99
Reasoning within output
git_grep f012
100%
Passed
Tokens
67
Input
82
Total output
71
Reasoning within output
git_log_format f001
100%
Passed
Tokens
916
Input
117
Total output
113
Reasoning within output
git_log_format f002
100%
Passed
Tokens
899
Input
175
Total output
165
Reasoning within output
git_log_format f003
100%
Passed
Tokens
737
Input
74
Total output
62
Reasoning within output
git_log_format f004
100%
Passed
Tokens
911
Input
71
Total output
67
Reasoning within output
git_log_format f005
100%
Passed
Tokens
739
Input
193
Total output
185
Reasoning within output
git_log_format f006
100%
Passed
Tokens
913
Input
233
Total output
229
Reasoning within output
git_log_format f007
100%
Passed
Tokens
930
Input
110
Total output
101
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,240
Input
138
Total output
134
Reasoning within output
git_log_format f009
100%
Passed
Tokens
743
Input
65
Total output
61
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,424
Input
84
Total output
80
Reasoning within output
git_log_format f011
100%
Passed
Tokens
440
Input
131
Total output
126
Reasoning within output
git_log_format f012
100%
Passed
Tokens
397
Input
85
Total output
81
Reasoning within output
git_show f001
100%
Passed
Tokens
201
Input
108
Total output
102
Reasoning within output
git_show f002
0%
Failed
Tokens
205
Input
373
Total output
352
Reasoning within output
git_show f003
100%
Passed
Tokens
681
Input
118
Total output
109
Reasoning within output
git_show f004
100%
Passed
Tokens
476
Input
89
Total output
80
Reasoning within output
git_show f005
100%
Passed
Tokens
208
Input
201
Total output
196
Reasoning within output
git_show f006
100%
Passed
Tokens
216
Input
180
Total output
176
Reasoning within output
git_show f007
100%
Passed
Tokens
204
Input
122
Total output
115
Reasoning within output
git_show f008
100%
Passed
Tokens
210
Input
186
Total output
149
Reasoning within output
git_show f009
100%
Passed
Tokens
327
Input
222
Total output
218
Reasoning within output
git_show f010
100%
Passed
Tokens
198
Input
114
Total output
110
Reasoning within output
git_show f011
100%
Passed
Tokens
234
Input
65
Total output
60
Reasoning within output
git_show f012
100%
Passed
Tokens
347
Input
116
Total output
112
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
88
Input
187
Total output
180
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
106
Input
347
Total output
337
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
81
Input
263
Total output
256
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
148
Input
910
Total output
882
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
140
Input
190
Total output
164
Reasoning within output
merge_conflicts f006
0%
Failed
Tokens
132
Input
495
Total output
461
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
136
Input
255
Total output
242
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
108
Input
98
Total output
89
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
105
Input
198
Total output
190
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
185
Input
524
Total output
493
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
149
Input
278
Total output
251
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
240
Input
1,226
Total output
1,172
Reasoning within output
rebase f001
0%
Failed
Tokens
102
Input
599
Total output
592
Reasoning within output
rebase f002
100%
Passed
Tokens
127
Input
133
Total output
123
Reasoning within output
rebase f003
100%
Passed
Tokens
107
Input
172
Total output
166
Reasoning within output
rebase f004
100%
Passed
Tokens
163
Input
317
Total output
289
Reasoning within output
rebase f005
100%
Passed
Tokens
148
Input
263
Total output
240
Reasoning within output
rebase f006
100%
Passed
Tokens
147
Input
859
Total output
829
Reasoning within output
rebase f007
100%
Passed
Tokens
140
Input
190
Total output
177
Reasoning within output
rebase f008
100%
Passed
Tokens
124
Input
143
Total output
134
Reasoning within output
rebase f009
100%
Passed
Tokens
106
Input
176
Total output
164
Reasoning within output
rebase f010
100%
Passed
Tokens
212
Input
611
Total output
580
Reasoning within output
rebase f011
100%
Passed
Tokens
161
Input
904
Total output
872
Reasoning within output
rebase f012
0%
Failed
Tokens
275
Input
706
Total output
660
Reasoning within output
reflog f001
100%
Passed
Tokens
253
Input
399
Total output
360
Reasoning within output
reflog f002
100%
Passed
Tokens
261
Input
485
Total output
333
Reasoning within output
reflog f003
100%
Passed
Tokens
219
Input
823
Total output
349
Reasoning within output
reflog f004
100%
Passed
Tokens
367
Input
1,903
Total output
1,310
Reasoning within output
reflog f005
100%
Passed
Tokens
427
Input
1,510
Total output
1,219
Reasoning within output
reflog f006
100%
Passed
Tokens
264
Input
375
Total output
158
Reasoning within output
reflog f007
100%
Passed
Tokens
311
Input
525
Total output
361
Reasoning within output
reflog f008
100%
Passed
Tokens
416
Input
1,690
Total output
1,284
Reasoning within output
reflog f009
100%
Passed
Tokens
333
Input
1,732
Total output
1,281
Reasoning within output
reflog f010
100%
Passed
Tokens
298
Input
791
Total output
375
Reasoning within output
reflog f011
100%
Passed
Tokens
359
Input
2,011
Total output
1,501
Reasoning within output
reflog f012
100%
Passed
Tokens
365
Input
2,892
Total output
2,187
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
141
Input
156
Total output
93
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
311
Input
351
Total output
194
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
129
Input
177
Total output
82
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
124
Input
141
Total output
65
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
136
Input
184
Total output
106
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
188
Input
198
Total output
92
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
217
Input
98
Total output
79
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
186
Input
299
Total output
139
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
216
Input
263
Total output
162
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
133
Input
150
Total output
80
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
126
Input
190
Total output
95
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
139
Input
164
Total output
74
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
46
Input
77
Total output
66
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
106
Input
483
Total output
473
Reasoning within output
submodule_usage f003
75%
Failed
Tokens
112
Input
1,588
Total output
1,531
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
102
Input
46
Total output
40
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
53
Input
342
Total output
314
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
98
Input
153
Total output
147
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
53
Input
126
Total output
106
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
105
Input
329
Total output
319
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
103
Input
108
Total output
90
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
107
Input
236
Total output
227
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
109
Input
50
Total output
43
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
51
Input
137
Total output
123
Reasoning within output
tag_management f001
100%
Passed
Tokens
67
Input
95
Total output
86
Reasoning within output
tag_management f002
100%
Passed
Tokens
62
Input
114
Total output
94
Reasoning within output
tag_management f003
100%
Passed
Tokens
70
Input
53
Total output
41
Reasoning within output
tag_management f004
100%
Passed
Tokens
77
Input
54
Total output
49
Reasoning within output
tag_management f005
100%
Passed
Tokens
90
Input
76
Total output
66
Reasoning within output
tag_management f006
100%
Passed
Tokens
74
Input
138
Total output
121
Reasoning within output
tag_management f007
100%
Passed
Tokens
67
Input
181
Total output
167
Reasoning within output
tag_management f008
100%
Passed
Tokens
73
Input
153
Total output
127
Reasoning within output
tag_management f009
100%
Passed
Tokens
77
Input
109
Total output
91
Reasoning within output
tag_management f010
100%
Passed
Tokens
55
Input
59
Total output
49
Reasoning within output
tag_management f011
100%
Passed
Tokens
57
Input
70
Total output
62
Reasoning within output
tag_management f012
100%
Passed
Tokens
95
Input
417
Total output
406
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
146
Input
80
Total output
68
Reasoning within output
worktree_usage f002
0%
Failed
Tokens
158
Input
527
Total output
499
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
230
Input
131
Total output
120
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
232
Input
53
Total output
46
Reasoning within output
worktree_usage f005
33.3%
Failed
Tokens
144
Input
124
Total output
112
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
148
Input
191
Total output
176
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
150
Input
154
Total output
132
Reasoning within output
worktree_usage f008
100%
Passed
Tokens
170
Input
396
Total output
344
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
267
Input
96
Total output
89
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
242
Input
100
Total output
81
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
229
Input
79
Total output
68
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
146
Input
137
Total output
120
Reasoning within output