Ibm-granite / granite-4.2-8b
max
91.2%
186 / 204 fixtures · 1 run(s)
39,188 input / 334,289 total output / 297,382 reasoning within output tokens $0.07601581
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-25.5%
Text: 91.2% →
JSON: 65.7%
+4
Gained
JSON pass / text fail
−56
Lost
Text pass / JSON fail
130
Unchanged Pass
Both pass
14
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% | 41.7% | -58.3% |
| git_clean | 75% | 41.7% | -33.3% |
| blame_forensics | 100% | 75% | -25% |
| git_bisect | 100% | 75% | -25% |
| git_grep | 100% | 83.3% | -16.7% |
| git_log_format | 100% | 83.3% | -16.7% |
| stash_recovery | 100% | 83.3% | -16.7% |
| merge_conflicts | 83.3% | 66.7% | -16.7% |
| rebase | 83.3% | 66.7% | -16.7% |
| cherry_pick | 75% | 66.7% | -8.3% |
| commit_messages | 100% | 91.7% | -8.3% |
| git_show | 100% | 91.7% | -8.3% |
| submodule_usage | 66.7% | 75% | + 8.3% |
| tag_management | 100% | 91.7% | -8.3% |
| worktree_usage | 66.7% | 75% | + 8.3% |
Changed Fixtures (60)
f005 -loss f008 -loss f010 -loss f001 -loss f002 -loss f003 -loss f004 -loss f006 -loss f009 -loss f011 -loss f002 -loss f004 +gain f010 -loss 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 f006 -loss f010 -loss f012 -loss f005 -loss f007 -loss f008 -loss f011 -loss f006 -loss f007 -loss f004 -loss f005 -loss f005 -loss f001 -loss f004 -loss f004 -loss f011 -loss f001 -loss f002 -loss f003 -loss f004 -loss f005 -loss f006 -loss f007 -loss f008 -loss f009 -loss f011 -loss f012 -loss f007 -loss f009 -loss f008 +gain f008 -loss f003 +gain f007 -loss f010 +gain
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
249
Input
1,700
Total output
1,608
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
235
Input
2,193
Total output
1,917
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
252
Input
712
Total output
631
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
206
Input
573
Total output
546
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
242
Input
4,462
Total output
3,847
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
239
Input
2,060
Total output
1,979
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
203
Input
717
Total output
652
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
240
Input
1,118
Total output
1,009
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
200
Input
1,584
Total output
1,510
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
417
Input
2,264
Total output
2,043
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
241
Input
913
Total output
826
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
156
Input
624
Total output
594
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
115
Input
822
Total output
735
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
129
Input
1,227
Total output
1,131
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
106
Input
1,730
Total output
1,813
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
146
Input
598
Total output
582
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
118
Input
393
Total output
388
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
134
Input
395
Total output
356
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
118
Input
763
Total output
811
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
135
Input
1,727
Total output
1,713
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
92
Input
334
Total output
365
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
124
Input
1,201
Total output
1,080
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
82
Input
493
Total output
510
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
166
Input
1,486
Total output
1,422
Reasoning within output
cherry_pick f001
0%
Failed
Tokens
109
Input
1,706
Total output
1,777
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
125
Input
599
Total output
544
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
101
Input
1,037
Total output
1,130
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
163
Input
2,829
Total output
2,642
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
166
Input
499
Total output
492
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
144
Input
1,929
Total output
1,712
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
141
Input
465
Total output
420
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
138
Input
196
Total output
189
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
118
Input
316
Total output
303
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
231
Input
681
Total output
674
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
179
Input
775
Total output
595
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
286
Input
905
Total output
726
Reasoning within output
commit_messages f001
96.5%
Passed
Tokens
118
Input
1,222
Total output
894
Reasoning within output
commit_messages f002
82.5%
Passed
Tokens
228
Input
9,150
Total output
5,374
Reasoning within output
commit_messages f003
89%
Passed
Tokens
98
Input
2,403
Total output
1,765
Reasoning within output
commit_messages f004
90%
Passed
Tokens
128
Input
630
Total output
509
Reasoning within output
commit_messages f005
77.5%
Passed
Tokens
117
Input
486
Total output
346
Reasoning within output
commit_messages f006
92.5%
Passed
Tokens
147
Input
3,426
Total output
2,412
Reasoning within output
commit_messages f007
90%
Passed
Tokens
205
Input
3,541
Total output
2,887
Reasoning within output
commit_messages f008
94%
Passed
Tokens
84
Input
179
Total output
164
Reasoning within output
commit_messages f009
90%
Passed
Tokens
141
Input
1,924
Total output
1,518
Reasoning within output
commit_messages f010
92.5%
Passed
Tokens
304
Input
2,104
Total output
1,480
Reasoning within output
commit_messages f011
79%
Passed
Tokens
163
Input
1,881
Total output
1,300
Reasoning within output
commit_messages f012
92.5%
Passed
Tokens
140
Input
2,786
Total output
1,885
Reasoning within output
commit_squash f001
100%
Passed
Tokens
145
Input
4,038
Total output
4,134
Reasoning within output
commit_squash f002
100%
Passed
Tokens
129
Input
775
Total output
709
Reasoning within output
commit_squash f003
100%
Passed
Tokens
136
Input
2,132
Total output
2,061
Reasoning within output
commit_squash f004
100%
Passed
Tokens
125
Input
2,645
Total output
2,656
Reasoning within output
commit_squash f005
100%
Passed
Tokens
120
Input
2,083
Total output
2,215
Reasoning within output
commit_squash f006
100%
Passed
Tokens
112
Input
1,125
Total output
1,182
Reasoning within output
commit_squash f007
100%
Passed
Tokens
111
Input
1,951
Total output
1,979
Reasoning within output
commit_squash f008
100%
Passed
Tokens
119
Input
3,604
Total output
3,709
Reasoning within output
commit_squash f009
100%
Passed
Tokens
112
Input
874
Total output
784
Reasoning within output
commit_squash f010
100%
Passed
Tokens
128
Input
2,090
Total output
2,187
Reasoning within output
commit_squash f011
100%
Passed
Tokens
138
Input
1,525
Total output
1,348
Reasoning within output
commit_squash f012
100%
Passed
Tokens
133
Input
1,126
Total output
1,069
Reasoning within output
git_bisect f001
100%
Passed
Tokens
193
Input
462
Total output
380
Reasoning within output
git_bisect f002
100%
Passed
Tokens
209
Input
1,342
Total output
957
Reasoning within output
git_bisect f003
100%
Passed
Tokens
209
Input
1,176
Total output
1,038
Reasoning within output
git_bisect f004
100%
Passed
Tokens
209
Input
635
Total output
590
Reasoning within output
git_bisect f005
100%
Passed
Tokens
219
Input
1,047
Total output
914
Reasoning within output
git_bisect f006
100%
Passed
Tokens
231
Input
1,261
Total output
1,121
Reasoning within output
git_bisect f007
100%
Passed
Tokens
215
Input
1,881
Total output
1,541
Reasoning within output
git_bisect f008
100%
Passed
Tokens
211
Input
1,046
Total output
898
Reasoning within output
git_bisect f009
100%
Passed
Tokens
211
Input
1,933
Total output
1,790
Reasoning within output
git_bisect f010
100%
Passed
Tokens
217
Input
1,297
Total output
1,045
Reasoning within output
git_bisect f011
100%
Passed
Tokens
215
Input
1,083
Total output
874
Reasoning within output
git_bisect f012
100%
Passed
Tokens
229
Input
2,018
Total output
1,548
Reasoning within output
git_clean f001
100%
Passed
Tokens
65
Input
1,148
Total output
1,184
Reasoning within output
git_clean f002
100%
Passed
Tokens
78
Input
1,597
Total output
1,667
Reasoning within output
git_clean f003
100%
Passed
Tokens
78
Input
2,030
Total output
2,108
Reasoning within output
git_clean f004
66.7%
Failed
Tokens
78
Input
2,737
Total output
2,871
Reasoning within output
git_clean f005
100%
Passed
Tokens
66
Input
2,128
Total output
2,134
Reasoning within output
git_clean f006
75%
Failed
Tokens
95
Input
4,411
Total output
4,569
Reasoning within output
git_clean f007
100%
Passed
Tokens
87
Input
2,418
Total output
2,405
Reasoning within output
git_clean f008
100%
Passed
Tokens
99
Input
405
Total output
416
Reasoning within output
git_clean f009
100%
Passed
Tokens
89
Input
5,575
Total output
5,951
Reasoning within output
git_clean f010
100%
Passed
Tokens
81
Input
1,968
Total output
1,931
Reasoning within output
git_clean f011
100%
Passed
Tokens
81
Input
3,990
Total output
4,162
Reasoning within output
git_clean f012
66.7%
Failed
Tokens
86
Input
9,343
Total output
9,140
Reasoning within output
git_grep f001
100%
Passed
Tokens
65
Input
79
Total output
76
Reasoning within output
git_grep f002
100%
Passed
Tokens
74
Input
78
Total output
64
Reasoning within output
git_grep f003
100%
Passed
Tokens
117
Input
198
Total output
176
Reasoning within output
git_grep f004
100%
Passed
Tokens
93
Input
240
Total output
188
Reasoning within output
git_grep f005
100%
Passed
Tokens
131
Input
448
Total output
419
Reasoning within output
git_grep f006
100%
Passed
Tokens
49
Input
424
Total output
447
Reasoning within output
git_grep f007
100%
Passed
Tokens
191
Input
2,194
Total output
1,860
Reasoning within output
git_grep f008
100%
Passed
Tokens
73
Input
293
Total output
313
Reasoning within output
git_grep f009
100%
Passed
Tokens
66
Input
117
Total output
97
Reasoning within output
git_grep f010
100%
Passed
Tokens
80
Input
388
Total output
361
Reasoning within output
git_grep f011
100%
Passed
Tokens
143
Input
348
Total output
331
Reasoning within output
git_grep f012
100%
Passed
Tokens
81
Input
213
Total output
177
Reasoning within output
git_log_format f001
100%
Passed
Tokens
764
Input
219
Total output
208
Reasoning within output
git_log_format f002
100%
Passed
Tokens
754
Input
4,977
Total output
5,318
Reasoning within output
git_log_format f003
100%
Passed
Tokens
616
Input
1,755
Total output
1,612
Reasoning within output
git_log_format f004
100%
Passed
Tokens
729
Input
138
Total output
108
Reasoning within output
git_log_format f005
100%
Passed
Tokens
613
Input
3,917
Total output
4,005
Reasoning within output
git_log_format f006
100%
Passed
Tokens
769
Input
319
Total output
251
Reasoning within output
git_log_format f007
100%
Passed
Tokens
755
Input
216
Total output
183
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,009
Input
259
Total output
238
Reasoning within output
git_log_format f009
100%
Passed
Tokens
619
Input
85
Total output
80
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,147
Input
109
Total output
89
Reasoning within output
git_log_format f011
100%
Passed
Tokens
394
Input
440
Total output
411
Reasoning within output
git_log_format f012
100%
Passed
Tokens
358
Input
144
Total output
134
Reasoning within output
git_show f001
100%
Passed
Tokens
191
Input
885
Total output
881
Reasoning within output
git_show f002
100%
Passed
Tokens
199
Input
4,636
Total output
4,825
Reasoning within output
git_show f003
100%
Passed
Tokens
643
Input
296
Total output
271
Reasoning within output
git_show f004
100%
Passed
Tokens
437
Input
313
Total output
240
Reasoning within output
git_show f005
100%
Passed
Tokens
205
Input
1,604
Total output
1,566
Reasoning within output
git_show f006
100%
Passed
Tokens
207
Input
283
Total output
238
Reasoning within output
git_show f007
100%
Passed
Tokens
190
Input
490
Total output
482
Reasoning within output
git_show f008
100%
Passed
Tokens
196
Input
1,763
Total output
1,251
Reasoning within output
git_show f009
100%
Passed
Tokens
288
Input
386
Total output
346
Reasoning within output
git_show f010
100%
Passed
Tokens
205
Input
190
Total output
177
Reasoning within output
git_show f011
100%
Passed
Tokens
224
Input
235
Total output
189
Reasoning within output
git_show f012
100%
Passed
Tokens
334
Input
211
Total output
190
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
97
Input
2,655
Total output
2,602
Reasoning within output
merge_conflicts f002
0%
Failed
Tokens
115
Input
2,032
Total output
1,772
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
90
Input
2,183
Total output
2,269
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
151
Input
3,539
Total output
3,376
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
153
Input
678
Total output
652
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
131
Input
2,126
Total output
1,985
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
146
Input
839
Total output
840
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
122
Input
223
Total output
193
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
114
Input
1,008
Total output
1,027
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
196
Input
1,487
Total output
1,391
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
158
Input
1,197
Total output
959
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
251
Input
1,192
Total output
943
Reasoning within output
rebase f001
0%
Failed
Tokens
107
Input
1,785
Total output
1,796
Reasoning within output
rebase f002
100%
Passed
Tokens
134
Input
1,415
Total output
1,221
Reasoning within output
rebase f003
100%
Passed
Tokens
113
Input
2,154
Total output
2,190
Reasoning within output
rebase f004
100%
Passed
Tokens
162
Input
1,429
Total output
1,247
Reasoning within output
rebase f005
100%
Passed
Tokens
157
Input
647
Total output
612
Reasoning within output
rebase f006
100%
Passed
Tokens
143
Input
2,992
Total output
2,619
Reasoning within output
rebase f007
100%
Passed
Tokens
144
Input
353
Total output
330
Reasoning within output
rebase f008
100%
Passed
Tokens
134
Input
399
Total output
397
Reasoning within output
rebase f009
100%
Passed
Tokens
113
Input
1,772
Total output
1,785
Reasoning within output
rebase f010
100%
Passed
Tokens
221
Input
2,971
Total output
2,838
Reasoning within output
rebase f011
100%
Passed
Tokens
167
Input
1,678
Total output
1,310
Reasoning within output
rebase f012
0%
Failed
Tokens
278
Input
1,081
Total output
822
Reasoning within output
reflog f001
100%
Passed
Tokens
209
Input
853
Total output
642
Reasoning within output
reflog f002
100%
Passed
Tokens
211
Input
1,796
Total output
1,150
Reasoning within output
reflog f003
100%
Passed
Tokens
187
Input
480
Total output
200
Reasoning within output
reflog f004
100%
Passed
Tokens
292
Input
3,727
Total output
2,612
Reasoning within output
reflog f005
100%
Passed
Tokens
339
Input
2,858
Total output
1,924
Reasoning within output
reflog f006
100%
Passed
Tokens
226
Input
1,544
Total output
807
Reasoning within output
reflog f007
100%
Passed
Tokens
248
Input
2,972
Total output
1,875
Reasoning within output
reflog f008
100%
Passed
Tokens
329
Input
5,144
Total output
4,090
Reasoning within output
reflog f009
100%
Passed
Tokens
286
Input
2,003
Total output
595
Reasoning within output
reflog f010
100%
Passed
Tokens
246
Input
780
Total output
275
Reasoning within output
reflog f011
100%
Passed
Tokens
302
Input
6,775
Total output
4,133
Reasoning within output
reflog f012
100%
Passed
Tokens
294
Input
13,268
Total output
10,566
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
149
Input
257
Total output
238
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
305
Input
9,608
Total output
7,270
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
137
Input
242
Total output
243
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
133
Input
452
Total output
264
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
142
Input
540
Total output
275
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
202
Input
322
Total output
137
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
223
Input
701
Total output
343
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
194
Input
374
Total output
178
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
229
Input
1,607
Total output
1,401
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
145
Input
161
Total output
150
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
132
Input
602
Total output
325
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
155
Input
509
Total output
221
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
52
Input
299
Total output
296
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
106
Input
1,741
Total output
1,862
Reasoning within output
submodule_usage f003
25%
Failed
Tokens
114
Input
8,489
Total output
8,653
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
99
Input
272
Total output
300
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
59
Input
1,242
Total output
1,345
Reasoning within output
submodule_usage f006
0%
Failed
Tokens
101
Input
1,014
Total output
1,056
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
59
Input
368
Total output
341
Reasoning within output
submodule_usage f008
33.3%
Failed
Tokens
110
Input
5,374
Total output
5,852
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
100
Input
2,121
Total output
2,115
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
108
Input
426
Total output
459
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
114
Input
113
Total output
118
Reasoning within output
submodule_usage f012
0%
Failed
Tokens
57
Input
2,156
Total output
2,351
Reasoning within output
tag_management f001
100%
Passed
Tokens
71
Input
315
Total output
313
Reasoning within output
tag_management f002
100%
Passed
Tokens
67
Input
1,036
Total output
996
Reasoning within output
tag_management f003
100%
Passed
Tokens
73
Input
341
Total output
295
Reasoning within output
tag_management f004
100%
Passed
Tokens
78
Input
193
Total output
182
Reasoning within output
tag_management f005
100%
Passed
Tokens
90
Input
1,240
Total output
1,153
Reasoning within output
tag_management f006
100%
Passed
Tokens
74
Input
974
Total output
831
Reasoning within output
tag_management f007
100%
Passed
Tokens
75
Input
865
Total output
782
Reasoning within output
tag_management f008
100%
Passed
Tokens
80
Input
476
Total output
369
Reasoning within output
tag_management f009
100%
Passed
Tokens
81
Input
313
Total output
284
Reasoning within output
tag_management f010
100%
Passed
Tokens
60
Input
215
Total output
183
Reasoning within output
tag_management f011
100%
Passed
Tokens
59
Input
287
Total output
303
Reasoning within output
tag_management f012
100%
Passed
Tokens
92
Input
5,894
Total output
4,709
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
145
Input
420
Total output
397
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
146
Input
3,305
Total output
3,094
Reasoning within output
worktree_usage f003
0%
Failed
Tokens
208
Input
502
Total output
485
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
216
Input
443
Total output
480
Reasoning within output
worktree_usage f005
33.3%
Failed
Tokens
136
Input
3,895
Total output
3,819
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
138
Input
3,103
Total output
2,879
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
144
Input
5,071
Total output
4,349
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
167
Input
2,149
Total output
2,021
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
244
Input
1,176
Total output
1,169
Reasoning within output
worktree_usage f010
0%
Failed
Tokens
216
Input
4,825
Total output
4,972
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
213
Input
319
Total output
292
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
137
Input
360
Total output
312
Reasoning within output