Ibm-granite / granite-4.2-8b
xhigh
90.7%
185 / 204 fixtures · 1 run(s)
39,214 input / 325,462 total output / 290,873 reasoning within output tokens $0.07800960
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-23.5%
Text: 90.7% →
JSON: 67.2%
+6
Gained
JSON pass / text fail
−54
Lost
Text pass / JSON fail
131
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% | 33.3% | -66.7% |
| branch_cleanup | 100% | 50% | -50% |
| git_clean | 75% | 33.3% | -41.7% |
| blame_forensics | 91.7% | 58.3% | -33.3% |
| stash_recovery | 100% | 75% | -25% |
| git_bisect | 100% | 83.3% | -16.7% |
| git_log_format | 100% | 83.3% | -16.7% |
| merge_conflicts | 75% | 58.3% | -16.7% |
| tag_management | 100% | 83.3% | -16.7% |
| rebase | 83.3% | 66.7% | -16.7% |
| cherry_pick | 75% | 83.3% | + 8.3% |
| commit_messages | 100% | 91.7% | -8.3% |
| git_grep | 100% | 91.7% | -8.3% |
| worktree_usage | 75% | 83.3% | + 8.3% |
| git_show | 91.7% | 91.7% | + 0% |
| submodule_usage | 75% | 75% | + 0% |
Changed Fixtures (60)
f001 -loss f002 +gain f005 -loss f008 -loss f010 -loss f011 -loss f001 -loss f003 -loss f004 -loss f006 -loss f009 -loss f011 -loss f001 -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 f001 -loss f003 -loss f005 -loss f006 -loss f007 +gain f008 -loss f012 -loss f006 -loss f004 -loss f005 -loss f002 +gain f005 -loss f003 -loss f010 -loss f005 -loss f006 -loss f001 -loss f004 -loss f005 -loss f006 -loss f007 -loss f008 -loss f011 -loss f012 -loss f002 -loss f007 -loss f009 -loss f006 -loss f008 -loss f003 +gain
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
254
Input
2,169
Total output
2,302
Reasoning within output
blame_forensics f002
0%
Failed
Tokens
233
Input
499
Total output
461
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
258
Input
99
Total output
84
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
204
Input
666
Total output
636
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
244
Input
1,820
Total output
1,606
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
234
Input
2,408
Total output
2,415
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
202
Input
712
Total output
607
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
237
Input
606
Total output
632
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
197
Input
317
Total output
337
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
416
Input
360
Total output
360
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
239
Input
846
Total output
759
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
152
Input
816
Total output
741
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
118
Input
1,609
Total output
1,530
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
134
Input
510
Total output
462
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
105
Input
1,504
Total output
1,617
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
141
Input
1,271
Total output
1,216
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
118
Input
572
Total output
571
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
137
Input
830
Total output
796
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
118
Input
1,153
Total output
1,177
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
132
Input
960
Total output
811
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
90
Input
598
Total output
650
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
129
Input
1,281
Total output
1,179
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
82
Input
1,670
Total output
1,705
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
166
Input
1,173
Total output
1,097
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
106
Input
2,824
Total output
3,011
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
126
Input
1,842
Total output
1,596
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
100
Input
774
Total output
808
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
165
Input
4,105
Total output
3,986
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
165
Input
549
Total output
558
Reasoning within output
cherry_pick f006
0%
Failed
Tokens
143
Input
900
Total output
834
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
140
Input
625
Total output
564
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
138
Input
313
Total output
303
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
117
Input
1,069
Total output
1,094
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
231
Input
891
Total output
901
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
179
Input
641
Total output
491
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
284
Input
982
Total output
760
Reasoning within output
commit_messages f001
94%
Passed
Tokens
118
Input
779
Total output
495
Reasoning within output
commit_messages f002
82.5%
Passed
Tokens
228
Input
3,326
Total output
2,323
Reasoning within output
commit_messages f003
97.5%
Passed
Tokens
98
Input
6,079
Total output
3,604
Reasoning within output
commit_messages f004
95%
Passed
Tokens
128
Input
880
Total output
626
Reasoning within output
commit_messages f005
50%
Passed
Tokens
117
Input
1,750
Total output
1,112
Reasoning within output
commit_messages f006
89%
Passed
Tokens
147
Input
2,839
Total output
1,981
Reasoning within output
commit_messages f007
95%
Passed
Tokens
205
Input
3,170
Total output
2,050
Reasoning within output
commit_messages f008
90%
Passed
Tokens
84
Input
881
Total output
637
Reasoning within output
commit_messages f009
92.5%
Passed
Tokens
141
Input
4,273
Total output
2,949
Reasoning within output
commit_messages f010
91.5%
Passed
Tokens
304
Input
1,922
Total output
1,669
Reasoning within output
commit_messages f011
74%
Passed
Tokens
163
Input
4,247
Total output
3,133
Reasoning within output
commit_messages f012
92.5%
Passed
Tokens
140
Input
1,388
Total output
1,057
Reasoning within output
commit_squash f001
100%
Passed
Tokens
143
Input
6,735
Total output
6,780
Reasoning within output
commit_squash f002
100%
Passed
Tokens
124
Input
584
Total output
595
Reasoning within output
commit_squash f003
100%
Passed
Tokens
138
Input
1,306
Total output
1,273
Reasoning within output
commit_squash f004
100%
Passed
Tokens
127
Input
3,646
Total output
3,706
Reasoning within output
commit_squash f005
100%
Passed
Tokens
125
Input
4,695
Total output
4,651
Reasoning within output
commit_squash f006
100%
Passed
Tokens
107
Input
1,648
Total output
1,714
Reasoning within output
commit_squash f007
100%
Passed
Tokens
109
Input
2,715
Total output
2,756
Reasoning within output
commit_squash f008
100%
Passed
Tokens
122
Input
2,493
Total output
2,429
Reasoning within output
commit_squash f009
100%
Passed
Tokens
117
Input
1,935
Total output
1,784
Reasoning within output
commit_squash f010
100%
Passed
Tokens
128
Input
2,689
Total output
2,815
Reasoning within output
commit_squash f011
100%
Passed
Tokens
134
Input
1,783
Total output
1,847
Reasoning within output
commit_squash f012
100%
Passed
Tokens
134
Input
3,126
Total output
3,194
Reasoning within output
git_bisect f001
100%
Passed
Tokens
189
Input
271
Total output
238
Reasoning within output
git_bisect f002
100%
Passed
Tokens
205
Input
1,008
Total output
927
Reasoning within output
git_bisect f003
100%
Passed
Tokens
211
Input
428
Total output
345
Reasoning within output
git_bisect f004
100%
Passed
Tokens
213
Input
1,140
Total output
1,019
Reasoning within output
git_bisect f005
100%
Passed
Tokens
221
Input
821
Total output
693
Reasoning within output
git_bisect f006
100%
Passed
Tokens
233
Input
1,838
Total output
1,540
Reasoning within output
git_bisect f007
100%
Passed
Tokens
211
Input
1,374
Total output
1,080
Reasoning within output
git_bisect f008
100%
Passed
Tokens
207
Input
808
Total output
738
Reasoning within output
git_bisect f009
100%
Passed
Tokens
203
Input
2,880
Total output
1,868
Reasoning within output
git_bisect f010
100%
Passed
Tokens
209
Input
1,692
Total output
1,422
Reasoning within output
git_bisect f011
100%
Passed
Tokens
205
Input
3,470
Total output
2,503
Reasoning within output
git_bisect f012
100%
Passed
Tokens
235
Input
857
Total output
882
Reasoning within output
git_clean f001
100%
Passed
Tokens
65
Input
3,208
Total output
3,277
Reasoning within output
git_clean f002
100%
Passed
Tokens
78
Input
4,971
Total output
5,125
Reasoning within output
git_clean f003
100%
Passed
Tokens
78
Input
732
Total output
742
Reasoning within output
git_clean f004
33.3%
Failed
Tokens
78
Input
6,751
Total output
6,926
Reasoning within output
git_clean f005
100%
Passed
Tokens
66
Input
1,779
Total output
1,796
Reasoning within output
git_clean f006
100%
Passed
Tokens
95
Input
4,701
Total output
4,837
Reasoning within output
git_clean f007
50%
Failed
Tokens
87
Input
6,429
Total output
6,401
Reasoning within output
git_clean f008
100%
Passed
Tokens
99
Input
1,566
Total output
1,545
Reasoning within output
git_clean f009
100%
Passed
Tokens
89
Input
6,419
Total output
7,011
Reasoning within output
git_clean f010
100%
Passed
Tokens
81
Input
4,809
Total output
4,896
Reasoning within output
git_clean f011
40%
Failed
Tokens
81
Input
3,133
Total output
3,236
Reasoning within output
git_clean f012
100%
Passed
Tokens
86
Input
5,159
Total output
5,094
Reasoning within output
git_grep f001
100%
Passed
Tokens
65
Input
205
Total output
186
Reasoning within output
git_grep f002
100%
Passed
Tokens
73
Input
211
Total output
213
Reasoning within output
git_grep f003
100%
Passed
Tokens
117
Input
65
Total output
50
Reasoning within output
git_grep f004
100%
Passed
Tokens
93
Input
90
Total output
62
Reasoning within output
git_grep f005
100%
Passed
Tokens
131
Input
311
Total output
296
Reasoning within output
git_grep f006
100%
Passed
Tokens
49
Input
1,376
Total output
1,415
Reasoning within output
git_grep f007
100%
Passed
Tokens
191
Input
2,144
Total output
1,601
Reasoning within output
git_grep f008
100%
Passed
Tokens
73
Input
177
Total output
177
Reasoning within output
git_grep f009
100%
Passed
Tokens
66
Input
99
Total output
76
Reasoning within output
git_grep f010
100%
Passed
Tokens
80
Input
607
Total output
562
Reasoning within output
git_grep f011
100%
Passed
Tokens
143
Input
272
Total output
247
Reasoning within output
git_grep f012
100%
Passed
Tokens
81
Input
289
Total output
246
Reasoning within output
git_log_format f001
100%
Passed
Tokens
761
Input
244
Total output
242
Reasoning within output
git_log_format f002
100%
Passed
Tokens
769
Input
592
Total output
648
Reasoning within output
git_log_format f003
100%
Passed
Tokens
615
Input
626
Total output
557
Reasoning within output
git_log_format f004
100%
Passed
Tokens
763
Input
443
Total output
349
Reasoning within output
git_log_format f005
100%
Passed
Tokens
613
Input
842
Total output
744
Reasoning within output
git_log_format f006
100%
Passed
Tokens
769
Input
1,043
Total output
735
Reasoning within output
git_log_format f007
100%
Passed
Tokens
776
Input
257
Total output
214
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,023
Input
296
Total output
262
Reasoning within output
git_log_format f009
100%
Passed
Tokens
605
Input
164
Total output
144
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,179
Input
147
Total output
123
Reasoning within output
git_log_format f011
100%
Passed
Tokens
393
Input
716
Total output
585
Reasoning within output
git_log_format f012
100%
Passed
Tokens
357
Input
158
Total output
148
Reasoning within output
git_show f001
100%
Passed
Tokens
195
Input
290
Total output
224
Reasoning within output
git_show f002
0%
Failed
Tokens
196
Input
2,154
Total output
2,084
Reasoning within output
git_show f003
100%
Passed
Tokens
641
Input
315
Total output
302
Reasoning within output
git_show f004
100%
Passed
Tokens
431
Input
247
Total output
180
Reasoning within output
git_show f005
100%
Passed
Tokens
200
Input
386
Total output
401
Reasoning within output
git_show f006
100%
Passed
Tokens
207
Input
144
Total output
120
Reasoning within output
git_show f007
100%
Passed
Tokens
190
Input
142
Total output
128
Reasoning within output
git_show f008
100%
Passed
Tokens
203
Input
717
Total output
367
Reasoning within output
git_show f009
100%
Passed
Tokens
292
Input
527
Total output
392
Reasoning within output
git_show f010
100%
Passed
Tokens
203
Input
216
Total output
204
Reasoning within output
git_show f011
100%
Passed
Tokens
220
Input
116
Total output
110
Reasoning within output
git_show f012
100%
Passed
Tokens
333
Input
301
Total output
298
Reasoning within output
merge_conflicts f001
0%
Failed
Tokens
97
Input
4,433
Total output
4,549
Reasoning within output
merge_conflicts f002
0%
Failed
Tokens
115
Input
2,250
Total output
2,088
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
90
Input
3,790
Total output
3,960
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
151
Input
2,649
Total output
2,487
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
153
Input
748
Total output
713
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
131
Input
3,802
Total output
3,260
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
146
Input
2,748
Total output
2,662
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
122
Input
303
Total output
272
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
114
Input
603
Total output
637
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
196
Input
1,726
Total output
1,642
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
158
Input
1,113
Total output
889
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
251
Input
1,526
Total output
1,263
Reasoning within output
rebase f001
0%
Failed
Tokens
109
Input
1,267
Total output
1,367
Reasoning within output
rebase f002
100%
Passed
Tokens
135
Input
755
Total output
652
Reasoning within output
rebase f003
100%
Passed
Tokens
113
Input
1,123
Total output
1,143
Reasoning within output
rebase f004
100%
Passed
Tokens
165
Input
2,835
Total output
2,662
Reasoning within output
rebase f005
100%
Passed
Tokens
159
Input
893
Total output
895
Reasoning within output
rebase f006
100%
Passed
Tokens
143
Input
1,802
Total output
1,523
Reasoning within output
rebase f007
100%
Passed
Tokens
144
Input
473
Total output
457
Reasoning within output
rebase f008
100%
Passed
Tokens
132
Input
666
Total output
661
Reasoning within output
rebase f009
100%
Passed
Tokens
113
Input
2,410
Total output
2,305
Reasoning within output
rebase f010
100%
Passed
Tokens
223
Input
913
Total output
827
Reasoning within output
rebase f011
100%
Passed
Tokens
167
Input
705
Total output
517
Reasoning within output
rebase f012
0%
Failed
Tokens
280
Input
1,341
Total output
1,078
Reasoning within output
reflog f001
100%
Passed
Tokens
207
Input
684
Total output
551
Reasoning within output
reflog f002
100%
Passed
Tokens
217
Input
711
Total output
301
Reasoning within output
reflog f003
100%
Passed
Tokens
189
Input
865
Total output
450
Reasoning within output
reflog f004
100%
Passed
Tokens
286
Input
2,960
Total output
2,079
Reasoning within output
reflog f005
100%
Passed
Tokens
324
Input
7,190
Total output
5,643
Reasoning within output
reflog f006
100%
Passed
Tokens
222
Input
817
Total output
334
Reasoning within output
reflog f007
100%
Passed
Tokens
267
Input
2,807
Total output
1,667
Reasoning within output
reflog f008
100%
Passed
Tokens
317
Input
2,601
Total output
1,272
Reasoning within output
reflog f009
100%
Passed
Tokens
272
Input
2,361
Total output
1,306
Reasoning within output
reflog f010
100%
Passed
Tokens
252
Input
1,903
Total output
804
Reasoning within output
reflog f011
100%
Passed
Tokens
291
Input
8,245
Total output
5,822
Reasoning within output
reflog f012
100%
Passed
Tokens
286
Input
5,327
Total output
3,439
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
149
Input
444
Total output
202
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
302
Input
7,259
Total output
5,855
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
137
Input
331
Total output
154
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
133
Input
260
Total output
137
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
145
Input
610
Total output
327
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
202
Input
292
Total output
128
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
225
Input
615
Total output
502
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
194
Input
261
Total output
126
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
229
Input
1,529
Total output
1,267
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
145
Input
334
Total output
139
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
132
Input
559
Total output
512
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
155
Input
216
Total output
198
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
52
Input
259
Total output
253
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
104
Input
2,230
Total output
2,381
Reasoning within output
submodule_usage f003
0%
Failed
Tokens
116
Input
6,177
Total output
6,434
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
104
Input
829
Total output
865
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
59
Input
1,195
Total output
1,251
Reasoning within output
submodule_usage f006
0%
Failed
Tokens
96
Input
499
Total output
552
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
59
Input
877
Total output
907
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
106
Input
5,771
Total output
6,175
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
102
Input
530
Total output
552
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
108
Input
637
Total output
734
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
111
Input
108
Total output
114
Reasoning within output
submodule_usage f012
0%
Failed
Tokens
57
Input
1,284
Total output
1,250
Reasoning within output
tag_management f001
100%
Passed
Tokens
71
Input
253
Total output
241
Reasoning within output
tag_management f002
100%
Passed
Tokens
67
Input
603
Total output
538
Reasoning within output
tag_management f003
100%
Passed
Tokens
76
Input
109
Total output
77
Reasoning within output
tag_management f004
100%
Passed
Tokens
79
Input
645
Total output
617
Reasoning within output
tag_management f005
100%
Passed
Tokens
89
Input
4,902
Total output
4,610
Reasoning within output
tag_management f006
100%
Passed
Tokens
75
Input
927
Total output
810
Reasoning within output
tag_management f007
100%
Passed
Tokens
75
Input
1,173
Total output
904
Reasoning within output
tag_management f008
100%
Passed
Tokens
79
Input
471
Total output
391
Reasoning within output
tag_management f009
100%
Passed
Tokens
83
Input
444
Total output
416
Reasoning within output
tag_management f010
100%
Passed
Tokens
60
Input
183
Total output
159
Reasoning within output
tag_management f011
100%
Passed
Tokens
60
Input
1,296
Total output
1,358
Reasoning within output
tag_management f012
100%
Passed
Tokens
93
Input
2,946
Total output
2,636
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
145
Input
667
Total output
578
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
153
Input
2,745
Total output
2,553
Reasoning within output
worktree_usage f003
0%
Failed
Tokens
209
Input
284
Total output
258
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
210
Input
558
Total output
498
Reasoning within output
worktree_usage f005
33.3%
Failed
Tokens
135
Input
931
Total output
931
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
137
Input
505
Total output
466
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
143
Input
1,575
Total output
1,459
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
164
Input
2,746
Total output
2,617
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
245
Input
714
Total output
683
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
221
Input
798
Total output
768
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
212
Input
692
Total output
655
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
138
Input
818
Total output
788
Reasoning within output