Ibm-granite / granite-4.2-8b
high
90.2%
184 / 204 fixtures · 1 run(s)
39,088 input / 355,218 total output / 314,090 reasoning within output tokens $0.08461104
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-26%
Text: 90.2% →
JSON: 64.2%
+7
Gained
JSON pass / text fail
−60
Lost
Text pass / JSON fail
124
Unchanged Pass
Both pass
13
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|---|---|---|
| f010 | 100% (1/1) | 0% (0/1) | +100% |
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| commit_squash | 100% | 0% | -100% |
| reflog | 100% | 8.3% | -91.7% |
| branch_cleanup | 100% | 33.3% | -66.7% |
| merge_conflicts | 83.3% | 41.7% | -41.7% |
| blame_forensics | 100% | 66.7% | -33.3% |
| git_bisect | 100% | 75% | -25% |
| git_log_format | 100% | 75% | -25% |
| git_clean | 66.7% | 41.7% | -25% |
| git_show | 100% | 83.3% | -16.7% |
| cherry_pick | 66.7% | 83.3% | + 16.7% |
| worktree_usage | 83.3% | 66.7% | -16.7% |
| tag_management | 91.7% | 83.3% | -8.3% |
| commit_messages | 100% | 91.7% | -8.3% |
| git_grep | 100% | 91.7% | -8.3% |
| submodule_usage | 66.7% | 75% | + 8.3% |
| rebase | 75% | 75% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
Changed Fixtures (67)
f002 -loss f005 -loss f008 -loss f010 -loss f001 -loss f002 -loss f003 -loss f005 -loss f006 -loss f009 -loss f011 -loss f012 -loss f001 +gain f002 -loss f004 +gain f006 +gain f010 -loss f001 -loss f002 -loss f003 -loss f004 -loss f005 -loss f006 -loss f007 -loss f008 -loss f009 -loss f010 -loss f011 -loss f012 -loss f004 -loss f010 -loss f011 -loss f005 -loss f006 -loss f007 -loss f008 -loss f012 +gain f006 -loss f004 -loss f005 -loss f006 -loss f001 -loss f005 -loss f001 -loss f003 -loss f004 -loss f006 -loss f010 -loss f010 +gain f011 -loss f001 -loss f002 -loss f003 -loss f004 -loss f005 -loss f006 -loss f007 -loss f008 -loss f009 -loss f010 -loss f011 -loss f008 +gain f006 -loss f007 +gain f008 -loss f006 -loss f007 -loss
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
250
Input
2,033
Total output
1,847
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
234
Input
1,789
Total output
1,719
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
253
Input
494
Total output
453
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
198
Input
929
Total output
900
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
247
Input
3,232
Total output
2,809
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
238
Input
2,095
Total output
2,007
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
202
Input
469
Total output
431
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
240
Input
1,644
Total output
1,540
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
203
Input
434
Total output
400
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
408
Input
756
Total output
734
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
240
Input
1,269
Total output
1,041
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
156
Input
408
Total output
382
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
110
Input
1,234
Total output
1,108
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
130
Input
841
Total output
793
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
104
Input
853
Total output
929
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
143
Input
1,447
Total output
1,433
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
121
Input
565
Total output
568
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
138
Input
431
Total output
410
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
121
Input
688
Total output
673
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
132
Input
1,728
Total output
1,631
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
92
Input
783
Total output
878
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
129
Input
1,837
Total output
1,727
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
81
Input
650
Total output
727
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
167
Input
646
Total output
582
Reasoning within output
cherry_pick f001
0%
Failed
Tokens
107
Input
1,224
Total output
1,346
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
127
Input
846
Total output
743
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
101
Input
620
Total output
630
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
164
Input
2,697
Total output
2,537
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
166
Input
519
Total output
524
Reasoning within output
cherry_pick f006
0%
Failed
Tokens
145
Input
1,867
Total output
1,767
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
140
Input
553
Total output
556
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
137
Input
379
Total output
358
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
117
Input
326
Total output
307
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
231
Input
914
Total output
869
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
179
Input
1,107
Total output
918
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
288
Input
858
Total output
669
Reasoning within output
commit_messages f001
92.5%
Passed
Tokens
118
Input
285
Total output
204
Reasoning within output
commit_messages f002
80%
Passed
Tokens
228
Input
6,405
Total output
3,839
Reasoning within output
commit_messages f003
96.5%
Passed
Tokens
98
Input
5,914
Total output
3,429
Reasoning within output
commit_messages f004
85%
Passed
Tokens
128
Input
469
Total output
369
Reasoning within output
commit_messages f005
67.5%
Passed
Tokens
117
Input
423
Total output
348
Reasoning within output
commit_messages f006
93%
Passed
Tokens
147
Input
1,762
Total output
1,263
Reasoning within output
commit_messages f007
92.5%
Passed
Tokens
205
Input
2,211
Total output
1,455
Reasoning within output
commit_messages f008
92.5%
Passed
Tokens
84
Input
410
Total output
341
Reasoning within output
commit_messages f009
77.5%
Passed
Tokens
141
Input
14,050
Total output
10,353
Reasoning within output
commit_messages f010
87.5%
Passed
Tokens
304
Input
5,417
Total output
4,024
Reasoning within output
commit_messages f011
84%
Passed
Tokens
163
Input
8,641
Total output
6,031
Reasoning within output
commit_messages f012
92.5%
Passed
Tokens
140
Input
955
Total output
764
Reasoning within output
commit_squash f001
100%
Passed
Tokens
146
Input
1,455
Total output
1,450
Reasoning within output
commit_squash f002
100%
Passed
Tokens
126
Input
1,176
Total output
1,072
Reasoning within output
commit_squash f003
100%
Passed
Tokens
141
Input
1,514
Total output
1,454
Reasoning within output
commit_squash f004
100%
Passed
Tokens
123
Input
3,352
Total output
3,362
Reasoning within output
commit_squash f005
100%
Passed
Tokens
120
Input
649
Total output
750
Reasoning within output
commit_squash f006
100%
Passed
Tokens
108
Input
2,182
Total output
2,329
Reasoning within output
commit_squash f007
100%
Passed
Tokens
110
Input
2,088
Total output
2,121
Reasoning within output
commit_squash f008
100%
Passed
Tokens
122
Input
3,508
Total output
3,523
Reasoning within output
commit_squash f009
100%
Passed
Tokens
112
Input
3,341
Total output
3,343
Reasoning within output
commit_squash f010
100%
Passed
Tokens
129
Input
2,150
Total output
2,065
Reasoning within output
commit_squash f011
100%
Passed
Tokens
137
Input
1,939
Total output
1,987
Reasoning within output
commit_squash f012
100%
Passed
Tokens
135
Input
3,820
Total output
3,879
Reasoning within output
git_bisect f001
100%
Passed
Tokens
185
Input
419
Total output
374
Reasoning within output
git_bisect f002
100%
Passed
Tokens
209
Input
1,374
Total output
1,167
Reasoning within output
git_bisect f003
100%
Passed
Tokens
213
Input
2,243
Total output
1,947
Reasoning within output
git_bisect f004
100%
Passed
Tokens
211
Input
1,224
Total output
1,096
Reasoning within output
git_bisect f005
100%
Passed
Tokens
211
Input
589
Total output
500
Reasoning within output
git_bisect f006
100%
Passed
Tokens
237
Input
1,351
Total output
1,088
Reasoning within output
git_bisect f007
100%
Passed
Tokens
211
Input
578
Total output
482
Reasoning within output
git_bisect f008
100%
Passed
Tokens
211
Input
1,464
Total output
1,237
Reasoning within output
git_bisect f009
100%
Passed
Tokens
205
Input
1,150
Total output
1,012
Reasoning within output
git_bisect f010
100%
Passed
Tokens
209
Input
1,809
Total output
1,886
Reasoning within output
git_bisect f011
100%
Passed
Tokens
207
Input
1,321
Total output
1,022
Reasoning within output
git_bisect f012
100%
Passed
Tokens
231
Input
1,145
Total output
976
Reasoning within output
git_clean f001
50%
Failed
Tokens
65
Input
1,976
Total output
2,115
Reasoning within output
git_clean f002
100%
Passed
Tokens
78
Input
1,425
Total output
1,509
Reasoning within output
git_clean f003
100%
Passed
Tokens
78
Input
4,764
Total output
4,957
Reasoning within output
git_clean f004
33.3%
Failed
Tokens
78
Input
11,905
Total output
12,291
Reasoning within output
git_clean f005
100%
Passed
Tokens
66
Input
3,230
Total output
3,268
Reasoning within output
git_clean f006
100%
Passed
Tokens
95
Input
8,759
Total output
9,061
Reasoning within output
git_clean f007
100%
Passed
Tokens
87
Input
5,184
Total output
4,946
Reasoning within output
git_clean f008
100%
Passed
Tokens
99
Input
675
Total output
636
Reasoning within output
git_clean f009
100%
Passed
Tokens
89
Input
3,665
Total output
3,673
Reasoning within output
git_clean f010
100%
Passed
Tokens
81
Input
2,997
Total output
2,968
Reasoning within output
git_clean f011
80%
Failed
Tokens
81
Input
2,515
Total output
2,582
Reasoning within output
git_clean f012
83.3%
Failed
Tokens
86
Input
2,603
Total output
2,439
Reasoning within output
git_grep f001
100%
Passed
Tokens
65
Input
147
Total output
137
Reasoning within output
git_grep f002
100%
Passed
Tokens
71
Input
387
Total output
376
Reasoning within output
git_grep f003
100%
Passed
Tokens
117
Input
200
Total output
178
Reasoning within output
git_grep f004
100%
Passed
Tokens
93
Input
141
Total output
110
Reasoning within output
git_grep f005
100%
Passed
Tokens
131
Input
712
Total output
689
Reasoning within output
git_grep f006
100%
Passed
Tokens
49
Input
2,572
Total output
2,698
Reasoning within output
git_grep f007
100%
Passed
Tokens
191
Input
1,005
Total output
892
Reasoning within output
git_grep f008
100%
Passed
Tokens
73
Input
164
Total output
171
Reasoning within output
git_grep f009
100%
Passed
Tokens
66
Input
82
Total output
64
Reasoning within output
git_grep f010
100%
Passed
Tokens
80
Input
1,891
Total output
1,635
Reasoning within output
git_grep f011
100%
Passed
Tokens
143
Input
195
Total output
167
Reasoning within output
git_grep f012
100%
Passed
Tokens
81
Input
230
Total output
193
Reasoning within output
git_log_format f001
100%
Passed
Tokens
745
Input
298
Total output
290
Reasoning within output
git_log_format f002
100%
Passed
Tokens
740
Input
4,270
Total output
4,399
Reasoning within output
git_log_format f003
100%
Passed
Tokens
619
Input
736
Total output
662
Reasoning within output
git_log_format f004
100%
Passed
Tokens
738
Input
312
Total output
223
Reasoning within output
git_log_format f005
100%
Passed
Tokens
613
Input
309
Total output
293
Reasoning within output
git_log_format f006
100%
Passed
Tokens
769
Input
560
Total output
418
Reasoning within output
git_log_format f007
100%
Passed
Tokens
777
Input
301
Total output
257
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,012
Input
158
Total output
129
Reasoning within output
git_log_format f009
100%
Passed
Tokens
622
Input
168
Total output
145
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,138
Input
204
Total output
177
Reasoning within output
git_log_format f011
100%
Passed
Tokens
386
Input
471
Total output
465
Reasoning within output
git_log_format f012
100%
Passed
Tokens
358
Input
152
Total output
132
Reasoning within output
git_show f001
100%
Passed
Tokens
194
Input
290
Total output
270
Reasoning within output
git_show f002
100%
Passed
Tokens
197
Input
3,616
Total output
3,859
Reasoning within output
git_show f003
100%
Passed
Tokens
629
Input
579
Total output
531
Reasoning within output
git_show f004
100%
Passed
Tokens
433
Input
156
Total output
135
Reasoning within output
git_show f005
100%
Passed
Tokens
200
Input
409
Total output
395
Reasoning within output
git_show f006
100%
Passed
Tokens
208
Input
115
Total output
109
Reasoning within output
git_show f007
100%
Passed
Tokens
190
Input
503
Total output
435
Reasoning within output
git_show f008
100%
Passed
Tokens
200
Input
1,280
Total output
1,042
Reasoning within output
git_show f009
100%
Passed
Tokens
288
Input
349
Total output
267
Reasoning within output
git_show f010
100%
Passed
Tokens
206
Input
2,289
Total output
1,972
Reasoning within output
git_show f011
100%
Passed
Tokens
224
Input
207
Total output
187
Reasoning within output
git_show f012
100%
Passed
Tokens
330
Input
328
Total output
328
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
97
Input
2,215
Total output
2,339
Reasoning within output
merge_conflicts f002
0%
Failed
Tokens
115
Input
1,063
Total output
961
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
90
Input
1,746
Total output
1,882
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
151
Input
2,990
Total output
2,749
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
153
Input
286
Total output
266
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
131
Input
2,296
Total output
2,141
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
146
Input
1,806
Total output
1,720
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
122
Input
119
Total output
108
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
114
Input
1,222
Total output
1,226
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
196
Input
1,700
Total output
1,639
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
158
Input
1,143
Total output
917
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
251
Input
1,250
Total output
1,038
Reasoning within output
rebase f001
0%
Failed
Tokens
107
Input
2,439
Total output
2,519
Reasoning within output
rebase f002
100%
Passed
Tokens
134
Input
397
Total output
340
Reasoning within output
rebase f003
100%
Passed
Tokens
113
Input
1,616
Total output
1,590
Reasoning within output
rebase f004
100%
Passed
Tokens
163
Input
1,458
Total output
1,306
Reasoning within output
rebase f005
100%
Passed
Tokens
158
Input
561
Total output
542
Reasoning within output
rebase f006
100%
Passed
Tokens
146
Input
2,519
Total output
2,197
Reasoning within output
rebase f007
100%
Passed
Tokens
143
Input
323
Total output
281
Reasoning within output
rebase f008
100%
Passed
Tokens
134
Input
286
Total output
262
Reasoning within output
rebase f009
100%
Passed
Tokens
112
Input
549
Total output
539
Reasoning within output
rebase f010
50%
Failed
Tokens
221
Input
3,600
Total output
3,398
Reasoning within output
rebase f011
100%
Passed
Tokens
167
Input
1,349
Total output
1,020
Reasoning within output
rebase f012
0%
Failed
Tokens
280
Input
1,324
Total output
1,114
Reasoning within output
reflog f001
100%
Passed
Tokens
219
Input
2,436
Total output
2,088
Reasoning within output
reflog f002
100%
Passed
Tokens
203
Input
2,274
Total output
1,584
Reasoning within output
reflog f003
100%
Passed
Tokens
189
Input
683
Total output
271
Reasoning within output
reflog f004
100%
Passed
Tokens
286
Input
2,943
Total output
1,941
Reasoning within output
reflog f005
100%
Passed
Tokens
321
Input
3,504
Total output
2,212
Reasoning within output
reflog f006
100%
Passed
Tokens
220
Input
566
Total output
218
Reasoning within output
reflog f007
100%
Passed
Tokens
250
Input
3,262
Total output
2,053
Reasoning within output
reflog f008
100%
Passed
Tokens
324
Input
11,501
Total output
8,990
Reasoning within output
reflog f009
100%
Passed
Tokens
278
Input
4,341
Total output
2,934
Reasoning within output
reflog f010
100%
Passed
Tokens
255
Input
1,371
Total output
435
Reasoning within output
reflog f011
100%
Passed
Tokens
303
Input
6,735
Total output
4,300
Reasoning within output
reflog f012
100%
Passed
Tokens
290
Input
12,101
Total output
8,663
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
146
Input
324
Total output
159
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
308
Input
7,588
Total output
5,797
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
137
Input
156
Total output
144
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
133
Input
414
Total output
369
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
143
Input
573
Total output
188
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
202
Input
221
Total output
207
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
223
Input
597
Total output
495
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
194
Input
302
Total output
190
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
229
Input
1,649
Total output
1,407
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
145
Input
303
Total output
140
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
132
Input
663
Total output
446
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
155
Input
351
Total output
137
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
52
Input
1,346
Total output
1,415
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
109
Input
2,759
Total output
3,066
Reasoning within output
submodule_usage f003
0%
Failed
Tokens
111
Input
7,641
Total output
8,118
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
102
Input
572
Total output
613
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
59
Input
1,719
Total output
1,818
Reasoning within output
submodule_usage f006
0%
Failed
Tokens
97
Input
805
Total output
912
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
59
Input
1,347
Total output
1,491
Reasoning within output
submodule_usage f008
33.3%
Failed
Tokens
107
Input
3,368
Total output
3,402
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
100
Input
507
Total output
522
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
103
Input
589
Total output
672
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
112
Input
114
Total output
120
Reasoning within output
submodule_usage f012
0%
Failed
Tokens
57
Input
673
Total output
720
Reasoning within output
tag_management f001
100%
Passed
Tokens
69
Input
541
Total output
476
Reasoning within output
tag_management f002
100%
Passed
Tokens
66
Input
613
Total output
590
Reasoning within output
tag_management f003
100%
Passed
Tokens
77
Input
210
Total output
160
Reasoning within output
tag_management f004
100%
Passed
Tokens
76
Input
643
Total output
656
Reasoning within output
tag_management f005
100%
Passed
Tokens
92
Input
3,144
Total output
3,075
Reasoning within output
tag_management f006
100%
Passed
Tokens
76
Input
352
Total output
282
Reasoning within output
tag_management f007
66.7%
Failed
Tokens
75
Input
2,591
Total output
2,198
Reasoning within output
tag_management f008
100%
Passed
Tokens
81
Input
551
Total output
422
Reasoning within output
tag_management f009
100%
Passed
Tokens
83
Input
719
Total output
681
Reasoning within output
tag_management f010
100%
Passed
Tokens
60
Input
177
Total output
138
Reasoning within output
tag_management f011
100%
Passed
Tokens
60
Input
713
Total output
747
Reasoning within output
tag_management f012
100%
Passed
Tokens
95
Input
2,799
Total output
2,406
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
143
Input
566
Total output
531
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
149
Input
2,984
Total output
2,905
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
210
Input
581
Total output
594
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
209
Input
182
Total output
186
Reasoning within output
worktree_usage f005
33.3%
Failed
Tokens
137
Input
2,690
Total output
2,781
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
138
Input
1,795
Total output
1,825
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
145
Input
1,504
Total output
1,249
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
165
Input
3,725
Total output
3,522
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
242
Input
2,346
Total output
2,263
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
217
Input
664
Total output
633
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
213
Input
486
Total output
460
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
135
Input
655
Total output
616
Reasoning within output