Nvidia / nemotron-3-super-120b-a12b
high
97.6%
199 / 204 fixtures · 1 run(s)
42,694 input / 44,186 total output / 37,256 reasoning within output tokens $0.02463064
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-4.9%
Text: 97.6% →
JSON: 92.7%
+74
Gained
JSON pass / text fail
−3
Lost
Text pass / JSON fail
115
Unchanged Pass
Both pass
12
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| branch_cleanup | 100% | 75% | -25% |
| merge_conflicts | 91.7% | 75% | -16.7% |
| rebase | 91.7% | 83.3% | -8.3% |
| commit_messages | 91.7% | 100% | + 8.3% |
| git_clean | 100% | 91.7% | -8.3% |
| git_log_format | 100% | 91.7% | -8.3% |
| reflog | 100% | 91.7% | -8.3% |
| submodule_usage | 100% | 91.7% | -8.3% |
| tag_management | 100% | 91.7% | -8.3% |
| blame_forensics | 100% | 100% | + 0% |
| cherry_pick | 91.7% | 91.7% | + 0% |
| commit_squash | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_grep | 100% | 100% | + 0% |
| git_show | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| worktree_usage | 91.7% | 91.7% | + 0% |
Changed Fixtures (77)
f001 -loss f003 -loss f008 -loss f001 +gain f002 +gain f003 +gain f004 +gain f005 +gain f010 +gain f011 +gain f002 +gain f004 +gain f005 +gain f006 +gain f007 +gain f008 +gain f010 +gain f012 +gain f004 +gain f001 +gain f002 +gain f003 +gain f004 +gain f005 +gain f006 +gain f007 +gain f005 +gain f007 +gain f008 +gain f009 +gain f010 +gain f012 +gain f001 +gain f002 +gain f003 +gain f004 +gain f005 +gain f006 +gain f007 +gain f008 +gain f009 +gain f010 +gain f011 +gain f001 +gain f003 +gain f004 +gain f005 +gain f007 +gain f008 +gain f002 +gain f003 +gain f004 +gain f005 +gain f006 +gain f007 +gain f008 +gain f009 +gain f010 +gain f011 +gain f001 +gain f002 +gain f003 +gain f005 +gain f006 +gain f007 +gain f008 +gain f002 +gain f003 +gain f004 +gain f010 +gain f011 +gain f002 +gain f004 +gain f009 +gain f010 +gain f011 +gain f012 +gain
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
261
Input
172
Total output
154
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
254
Input
271
Total output
232
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
290
Input
89
Total output
66
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
208
Input
77
Total output
81
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
283
Input
332
Total output
310
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
245
Input
129
Total output
114
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
236
Input
267
Total output
206
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
261
Input
396
Total output
343
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
211
Input
104
Total output
87
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
453
Input
279
Total output
204
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
259
Input
166
Total output
151
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
156
Input
83
Total output
80
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
120
Input
168
Total output
143
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
126
Input
67
Total output
57
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
108
Input
102
Total output
94
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
142
Input
177
Total output
167
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
118
Input
121
Total output
103
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
146
Input
70
Total output
61
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
117
Input
73
Total output
65
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
139
Input
73
Total output
59
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
92
Input
91
Total output
90
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
127
Input
151
Total output
119
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
81
Input
40
Total output
36
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
176
Input
125
Total output
113
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
110
Input
204
Total output
194
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
135
Input
134
Total output
120
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
102
Input
394
Total output
376
Reasoning within output
cherry_pick f004
100%
Passed
Tokens
178
Input
637
Total output
539
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
164
Input
99
Total output
77
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
156
Input
387
Total output
334
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
154
Input
182
Total output
150
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
137
Input
49
Total output
40
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
119
Input
37
Total output
32
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
241
Input
219
Total output
184
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
176
Input
213
Total output
163
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
296
Input
380
Total output
329
Reasoning within output
commit_messages f001
90%
Passed
Tokens
122
Input
392
Total output
363
Reasoning within output
commit_messages f002
92.3%
Passed
Tokens
239
Input
338
Total output
310
Reasoning within output
commit_messages f003
95.3%
Passed
Tokens
94
Input
301
Total output
247
Reasoning within output
commit_messages f004
0%
Failed
Tokens
131
Input
1,218
Total output
1,171
Reasoning within output
commit_messages f005
85%
Passed
Tokens
116
Input
91
Total output
92
Reasoning within output
commit_messages f006
89.3%
Passed
Tokens
162
Input
234
Total output
195
Reasoning within output
commit_messages f007
89.3%
Passed
Tokens
204
Input
264
Total output
233
Reasoning within output
commit_messages f008
91%
Passed
Tokens
87
Input
111
Total output
99
Reasoning within output
commit_messages f009
78.3%
Passed
Tokens
143
Input
437
Total output
344
Reasoning within output
commit_messages f010
93.3%
Passed
Tokens
311
Input
195
Total output
125
Reasoning within output
commit_messages f011
61.7%
Passed
Tokens
155
Input
325
Total output
222
Reasoning within output
commit_messages f012
91%
Passed
Tokens
134
Input
331
Total output
264
Reasoning within output
commit_squash f001
100%
Passed
Tokens
151
Input
366
Total output
343
Reasoning within output
commit_squash f002
100%
Passed
Tokens
130
Input
154
Total output
131
Reasoning within output
commit_squash f003
100%
Passed
Tokens
144
Input
221
Total output
196
Reasoning within output
commit_squash f004
100%
Passed
Tokens
134
Input
206
Total output
174
Reasoning within output
commit_squash f005
100%
Passed
Tokens
127
Input
121
Total output
105
Reasoning within output
commit_squash f006
100%
Passed
Tokens
110
Input
190
Total output
166
Reasoning within output
commit_squash f007
100%
Passed
Tokens
115
Input
250
Total output
233
Reasoning within output
commit_squash f008
100%
Passed
Tokens
128
Input
269
Total output
235
Reasoning within output
commit_squash f009
100%
Passed
Tokens
122
Input
260
Total output
223
Reasoning within output
commit_squash f010
100%
Passed
Tokens
134
Input
176
Total output
151
Reasoning within output
commit_squash f011
100%
Passed
Tokens
143
Input
164
Total output
141
Reasoning within output
commit_squash f012
100%
Passed
Tokens
145
Input
217
Total output
180
Reasoning within output
git_bisect f001
100%
Passed
Tokens
196
Input
125
Total output
103
Reasoning within output
git_bisect f002
100%
Passed
Tokens
220
Input
182
Total output
155
Reasoning within output
git_bisect f003
100%
Passed
Tokens
220
Input
230
Total output
180
Reasoning within output
git_bisect f004
100%
Passed
Tokens
230
Input
188
Total output
157
Reasoning within output
git_bisect f005
100%
Passed
Tokens
220
Input
114
Total output
96
Reasoning within output
git_bisect f006
100%
Passed
Tokens
246
Input
115
Total output
78
Reasoning within output
git_bisect f007
100%
Passed
Tokens
222
Input
239
Total output
176
Reasoning within output
git_bisect f008
100%
Passed
Tokens
226
Input
154
Total output
126
Reasoning within output
git_bisect f009
100%
Passed
Tokens
222
Input
176
Total output
134
Reasoning within output
git_bisect f010
100%
Passed
Tokens
222
Input
174
Total output
149
Reasoning within output
git_bisect f011
100%
Passed
Tokens
226
Input
111
Total output
86
Reasoning within output
git_bisect f012
100%
Passed
Tokens
252
Input
160
Total output
132
Reasoning within output
git_clean f001
100%
Passed
Tokens
61
Input
154
Total output
137
Reasoning within output
git_clean f002
100%
Passed
Tokens
71
Input
116
Total output
105
Reasoning within output
git_clean f003
100%
Passed
Tokens
67
Input
49
Total output
39
Reasoning within output
git_clean f004
100%
Passed
Tokens
69
Input
216
Total output
228
Reasoning within output
git_clean f005
100%
Passed
Tokens
59
Input
248
Total output
234
Reasoning within output
git_clean f006
100%
Passed
Tokens
86
Input
136
Total output
139
Reasoning within output
git_clean f007
100%
Passed
Tokens
81
Input
206
Total output
189
Reasoning within output
git_clean f008
100%
Passed
Tokens
85
Input
89
Total output
79
Reasoning within output
git_clean f009
100%
Passed
Tokens
76
Input
118
Total output
122
Reasoning within output
git_clean f010
100%
Passed
Tokens
73
Input
120
Total output
108
Reasoning within output
git_clean f011
100%
Passed
Tokens
72
Input
175
Total output
161
Reasoning within output
git_clean f012
100%
Passed
Tokens
75
Input
386
Total output
390
Reasoning within output
git_grep f001
100%
Passed
Tokens
62
Input
67
Total output
59
Reasoning within output
git_grep f002
100%
Passed
Tokens
77
Input
3,321
Total output
3,229
Reasoning within output
git_grep f003
100%
Passed
Tokens
95
Input
27
Total output
23
Reasoning within output
git_grep f004
100%
Passed
Tokens
85
Input
52
Total output
43
Reasoning within output
git_grep f005
100%
Passed
Tokens
119
Input
66
Total output
60
Reasoning within output
git_grep f006
100%
Passed
Tokens
49
Input
230
Total output
225
Reasoning within output
git_grep f007
100%
Passed
Tokens
169
Input
292
Total output
272
Reasoning within output
git_grep f008
100%
Passed
Tokens
68
Input
52
Total output
46
Reasoning within output
git_grep f009
100%
Passed
Tokens
62
Input
40
Total output
34
Reasoning within output
git_grep f010
100%
Passed
Tokens
72
Input
124
Total output
118
Reasoning within output
git_grep f011
100%
Passed
Tokens
117
Input
90
Total output
86
Reasoning within output
git_grep f012
100%
Passed
Tokens
73
Input
47
Total output
36
Reasoning within output
git_log_format f001
100%
Passed
Tokens
922
Input
94
Total output
82
Reasoning within output
git_log_format f002
100%
Passed
Tokens
890
Input
133
Total output
128
Reasoning within output
git_log_format f003
100%
Passed
Tokens
726
Input
83
Total output
68
Reasoning within output
git_log_format f004
100%
Passed
Tokens
906
Input
79
Total output
69
Reasoning within output
git_log_format f005
100%
Passed
Tokens
748
Input
394
Total output
338
Reasoning within output
git_log_format f006
100%
Passed
Tokens
927
Input
244
Total output
189
Reasoning within output
git_log_format f007
100%
Passed
Tokens
934
Input
67
Total output
51
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,217
Input
43
Total output
39
Reasoning within output
git_log_format f009
100%
Passed
Tokens
742
Input
58
Total output
52
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,380
Input
70
Total output
61
Reasoning within output
git_log_format f011
100%
Passed
Tokens
461
Input
74
Total output
66
Reasoning within output
git_log_format f012
100%
Passed
Tokens
406
Input
74
Total output
66
Reasoning within output
git_show f001
100%
Passed
Tokens
213
Input
98
Total output
68
Reasoning within output
git_show f002
100%
Passed
Tokens
210
Input
189
Total output
178
Reasoning within output
git_show f003
100%
Passed
Tokens
697
Input
109
Total output
86
Reasoning within output
git_show f004
100%
Passed
Tokens
480
Input
156
Total output
137
Reasoning within output
git_show f005
100%
Passed
Tokens
212
Input
126
Total output
117
Reasoning within output
git_show f006
100%
Passed
Tokens
220
Input
59
Total output
54
Reasoning within output
git_show f007
100%
Passed
Tokens
205
Input
87
Total output
68
Reasoning within output
git_show f008
100%
Passed
Tokens
219
Input
114
Total output
59
Reasoning within output
git_show f009
100%
Passed
Tokens
332
Input
139
Total output
112
Reasoning within output
git_show f010
100%
Passed
Tokens
206
Input
69
Total output
62
Reasoning within output
git_show f011
100%
Passed
Tokens
237
Input
75
Total output
70
Reasoning within output
git_show f012
100%
Passed
Tokens
348
Input
74
Total output
69
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
98
Input
326
Total output
315
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
122
Input
287
Total output
266
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
92
Input
264
Total output
293
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
163
Input
378
Total output
340
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
150
Input
76
Total output
69
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
143
Input
349
Total output
257
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
153
Input
300
Total output
261
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
119
Input
142
Total output
127
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
119
Input
274
Total output
259
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
202
Input
260
Total output
218
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
156
Input
166
Total output
121
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
257
Input
331
Total output
263
Reasoning within output
rebase f001
100%
Passed
Tokens
110
Input
304
Total output
324
Reasoning within output
rebase f002
100%
Passed
Tokens
142
Input
62
Total output
52
Reasoning within output
rebase f003
100%
Passed
Tokens
118
Input
160
Total output
153
Reasoning within output
rebase f004
100%
Passed
Tokens
177
Input
1,588
Total output
1,459
Reasoning within output
rebase f005
100%
Passed
Tokens
156
Input
659
Total output
615
Reasoning within output
rebase f006
100%
Passed
Tokens
158
Input
434
Total output
363
Reasoning within output
rebase f007
100%
Passed
Tokens
156
Input
202
Total output
166
Reasoning within output
rebase f008
100%
Passed
Tokens
131
Input
38
Total output
29
Reasoning within output
rebase f009
100%
Passed
Tokens
119
Input
107
Total output
98
Reasoning within output
rebase f010
100%
Passed
Tokens
225
Input
199
Total output
161
Reasoning within output
rebase f011
100%
Passed
Tokens
167
Input
177
Total output
150
Reasoning within output
rebase f012
0%
Failed
Tokens
292
Input
438
Total output
360
Reasoning within output
reflog f001
100%
Passed
Tokens
270
Input
307
Total output
177
Reasoning within output
reflog f002
100%
Passed
Tokens
253
Input
194
Total output
123
Reasoning within output
reflog f003
100%
Passed
Tokens
226
Input
97
Total output
41
Reasoning within output
reflog f004
100%
Passed
Tokens
352
Input
453
Total output
356
Reasoning within output
reflog f005
100%
Passed
Tokens
416
Input
552
Total output
281
Reasoning within output
reflog f006
100%
Passed
Tokens
273
Input
540
Total output
289
Reasoning within output
reflog f007
100%
Passed
Tokens
313
Input
140
Total output
74
Reasoning within output
reflog f008
100%
Passed
Tokens
403
Input
132
Total output
80
Reasoning within output
reflog f009
100%
Passed
Tokens
361
Input
552
Total output
272
Reasoning within output
reflog f010
100%
Passed
Tokens
298
Input
68
Total output
60
Reasoning within output
reflog f011
100%
Passed
Tokens
363
Input
1,111
Total output
703
Reasoning within output
reflog f012
100%
Passed
Tokens
359
Input
794
Total output
222
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
149
Input
94
Total output
83
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
319
Input
55
Total output
46
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
136
Input
60
Total output
54
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
132
Input
129
Total output
125
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
143
Input
77
Total output
47
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
195
Input
58
Total output
47
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
225
Input
68
Total output
54
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
194
Input
67
Total output
60
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
229
Input
283
Total output
222
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
141
Input
84
Total output
72
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
133
Input
95
Total output
81
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
150
Input
98
Total output
69
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
52
Input
64
Total output
50
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
113
Input
237
Total output
207
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
118
Input
489
Total output
423
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
100
Input
71
Total output
63
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
59
Input
102
Total output
68
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
103
Input
182
Total output
161
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
60
Input
174
Total output
142
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
109
Input
122
Total output
104
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
105
Input
91
Total output
77
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
113
Input
146
Total output
127
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
115
Input
33
Total output
26
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
59
Input
69
Total output
50
Reasoning within output
tag_management f001
100%
Passed
Tokens
69
Input
57
Total output
47
Reasoning within output
tag_management f002
100%
Passed
Tokens
65
Input
79
Total output
53
Reasoning within output
tag_management f003
100%
Passed
Tokens
74
Input
112
Total output
100
Reasoning within output
tag_management f004
100%
Passed
Tokens
80
Input
122
Total output
132
Reasoning within output
tag_management f005
100%
Passed
Tokens
91
Input
107
Total output
95
Reasoning within output
tag_management f006
100%
Passed
Tokens
74
Input
300
Total output
250
Reasoning within output
tag_management f007
100%
Passed
Tokens
73
Input
335
Total output
311
Reasoning within output
tag_management f008
100%
Passed
Tokens
79
Input
218
Total output
149
Reasoning within output
tag_management f009
100%
Passed
Tokens
80
Input
112
Total output
90
Reasoning within output
tag_management f010
100%
Passed
Tokens
58
Input
66
Total output
50
Reasoning within output
tag_management f011
100%
Passed
Tokens
59
Input
96
Total output
87
Reasoning within output
tag_management f012
100%
Passed
Tokens
98
Input
362
Total output
338
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
165
Input
199
Total output
187
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
167
Input
79
Total output
53
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
248
Input
154
Total output
156
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
243
Input
52
Total output
43
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
153
Input
118
Total output
109
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
158
Input
270
Total output
236
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
157
Input
378
Total output
335
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
182
Input
390
Total output
347
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
282
Input
93
Total output
80
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
248
Input
139
Total output
122
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
251
Input
327
Total output
283
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
155
Input
126
Total output
109
Reasoning within output