Inception / mercury-2.5
xhigh
94.6%
193 / 204 fixtures · 1 run(s)
37,552 input / 147,865 total output / 143,905 reasoning within output tokens $0.02368183
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-2.5%
Text: 94.6% →
JSON: 92.2%
+4
Gained
JSON pass / text fail
−9
Lost
Text pass / JSON fail
184
Unchanged Pass
Both pass
7
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| branch_cleanup | 100% | 75% | -25% |
| cherry_pick | 83.3% | 66.7% | -16.7% |
| worktree_usage | 83.3% | 91.7% | + 8.3% |
| commit_squash | 100% | 91.7% | -8.3% |
| git_clean | 91.7% | 100% | + 8.3% |
| git_show | 100% | 91.7% | -8.3% |
| blame_forensics | 91.7% | 91.7% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_grep | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| merge_conflicts | 83.3% | 83.3% | + 0% |
| rebase | 83.3% | 83.3% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 91.7% | 91.7% | + 0% |
| tag_management | 100% | 100% | + 0% |
Changed Fixtures (13)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
235
Input
759
Total output
750
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
239
Input
930
Total output
919
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
268
Input
604
Total output
594
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
191
Input
761
Total output
749
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
254
Input
1,250
Total output
1,241
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
229
Input
1,053
Total output
1,046
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
201
Input
601
Total output
594
Reasoning within output
blame_forensics f008
0%
Failed
blame_forensics f009
100%
Passed
Tokens
193
Input
646
Total output
639
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
426
Input
822
Total output
812
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
240
Input
733
Total output
723
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
134
Input
679
Total output
669
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
100
Input
551
Total output
543
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
109
Input
746
Total output
737
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
89
Input
609
Total output
599
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
123
Input
638
Total output
629
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
101
Input
656
Total output
649
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
115
Input
525
Total output
514
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
99
Input
461
Total output
451
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
112
Input
470
Total output
461
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
76
Input
535
Total output
526
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
107
Input
633
Total output
623
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
62
Input
415
Total output
409
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
147
Input
584
Total output
573
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
82
Input
1,611
Total output
1,603
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
104
Input
752
Total output
743
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
76
Input
718
Total output
710
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
147
Input
2,286
Total output
2,257
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
137
Input
658
Total output
633
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
131
Input
1,740
Total output
1,713
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
123
Input
654
Total output
642
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
108
Input
546
Total output
536
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
98
Input
394
Total output
384
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
199
Input
917
Total output
887
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
155
Input
921
Total output
896
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
261
Input
1,850
Total output
1,803
Reasoning within output
commit_messages f001
92.5%
Passed
Tokens
103
Input
800
Total output
791
Reasoning within output
commit_messages f002
83%
Passed
Tokens
210
Input
599
Total output
590
Reasoning within output
commit_messages f003
96%
Passed
Tokens
73
Input
766
Total output
754
Reasoning within output
commit_messages f004
91.5%
Passed
Tokens
108
Input
365
Total output
358
Reasoning within output
commit_messages f005
90%
Passed
Tokens
95
Input
476
Total output
466
Reasoning within output
commit_messages f006
92.5%
Passed
Tokens
138
Input
436
Total output
425
Reasoning within output
commit_messages f007
96%
Passed
Tokens
181
Input
1,063
Total output
1,049
Reasoning within output
commit_messages f008
90%
Passed
Tokens
68
Input
475
Total output
467
Reasoning within output
commit_messages f009
87.5%
Passed
Tokens
118
Input
758
Total output
749
Reasoning within output
commit_messages f010
82.5%
Passed
Tokens
278
Input
900
Total output
890
Reasoning within output
commit_messages f011
70%
Passed
Tokens
135
Input
978
Total output
961
Reasoning within output
commit_messages f012
91.5%
Passed
Tokens
119
Input
533
Total output
522
Reasoning within output
commit_squash f001
100%
Passed
Tokens
132
Input
1,259
Total output
1,242
Reasoning within output
commit_squash f002
100%
Passed
Tokens
110
Input
639
Total output
628
Reasoning within output
commit_squash f003
100%
Passed
Tokens
121
Input
931
Total output
913
Reasoning within output
commit_squash f004
100%
Passed
Tokens
110
Input
1,646
Total output
1,632
Reasoning within output
commit_squash f005
100%
Passed
Tokens
103
Input
645
Total output
632
Reasoning within output
commit_squash f006
100%
Passed
Tokens
93
Input
521
Total output
503
Reasoning within output
commit_squash f007
100%
Passed
Tokens
95
Input
767
Total output
752
Reasoning within output
commit_squash f008
100%
Passed
Tokens
104
Input
487
Total output
475
Reasoning within output
commit_squash f009
100%
Passed
Tokens
100
Input
593
Total output
581
Reasoning within output
commit_squash f010
100%
Passed
Tokens
115
Input
501
Total output
483
Reasoning within output
commit_squash f011
100%
Passed
Tokens
124
Input
488
Total output
470
Reasoning within output
commit_squash f012
100%
Passed
Tokens
121
Input
764
Total output
742
Reasoning within output
git_bisect f001
100%
Passed
Tokens
178
Input
479
Total output
470
Reasoning within output
git_bisect f002
100%
Passed
Tokens
201
Input
588
Total output
575
Reasoning within output
git_bisect f003
100%
Passed
Tokens
194
Input
578
Total output
570
Reasoning within output
git_bisect f004
100%
Passed
Tokens
207
Input
682
Total output
673
Reasoning within output
git_bisect f005
100%
Passed
Tokens
204
Input
593
Total output
582
Reasoning within output
git_bisect f006
100%
Passed
Tokens
221
Input
597
Total output
589
Reasoning within output
git_bisect f007
100%
Passed
Tokens
195
Input
521
Total output
512
Reasoning within output
git_bisect f008
100%
Passed
Tokens
206
Input
663
Total output
650
Reasoning within output
git_bisect f009
100%
Passed
Tokens
203
Input
581
Total output
571
Reasoning within output
git_bisect f010
100%
Passed
Tokens
206
Input
566
Total output
555
Reasoning within output
git_bisect f011
100%
Passed
Tokens
204
Input
657
Total output
646
Reasoning within output
git_bisect f012
100%
Passed
Tokens
222
Input
647
Total output
638
Reasoning within output
git_clean f001
100%
Passed
Tokens
41
Input
1,547
Total output
1,537
Reasoning within output
git_clean f002
100%
Passed
Tokens
53
Input
452
Total output
441
Reasoning within output
git_clean f003
100%
Passed
Tokens
52
Input
539
Total output
529
Reasoning within output
git_clean f004
33.3%
Failed
Tokens
48
Input
796
Total output
787
Reasoning within output
git_clean f005
100%
Passed
Tokens
41
Input
756
Total output
746
Reasoning within output
git_clean f006
100%
Passed
Tokens
65
Input
673
Total output
663
Reasoning within output
git_clean f007
100%
Passed
Tokens
57
Input
970
Total output
953
Reasoning within output
git_clean f008
100%
Passed
Tokens
66
Input
387
Total output
376
Reasoning within output
git_clean f009
100%
Passed
Tokens
59
Input
929
Total output
916
Reasoning within output
git_clean f010
100%
Passed
Tokens
53
Input
512
Total output
503
Reasoning within output
git_clean f011
100%
Passed
Tokens
53
Input
657
Total output
648
Reasoning within output
git_clean f012
100%
Passed
Tokens
54
Input
679
Total output
665
Reasoning within output
git_grep f001
100%
Passed
Tokens
41
Input
346
Total output
337
Reasoning within output
git_grep f002
100%
Passed
Tokens
54
Input
291
Total output
282
Reasoning within output
git_grep f003
100%
Passed
Tokens
76
Input
345
Total output
337
Reasoning within output
git_grep f004
100%
Passed
Tokens
62
Input
306
Total output
297
Reasoning within output
git_grep f005
100%
Passed
Tokens
102
Input
370
Total output
362
Reasoning within output
git_grep f006
100%
Passed
Tokens
30
Input
644
Total output
637
Reasoning within output
git_grep f007
100%
Passed
Tokens
156
Input
991
Total output
983
Reasoning within output
git_grep f008
100%
Passed
Tokens
45
Input
268
Total output
260
Reasoning within output
git_grep f009
100%
Passed
Tokens
43
Input
206
Total output
199
Reasoning within output
git_grep f010
100%
Passed
Tokens
52
Input
420
Total output
412
Reasoning within output
git_grep f011
100%
Passed
Tokens
98
Input
330
Total output
324
Reasoning within output
git_grep f012
100%
Passed
Tokens
52
Input
283
Total output
273
Reasoning within output
git_log_format f001
100%
Passed
Tokens
864
Input
416
Total output
408
Reasoning within output
git_log_format f002
100%
Passed
Tokens
883
Input
641
Total output
628
Reasoning within output
git_log_format f003
100%
Passed
Tokens
689
Input
392
Total output
379
Reasoning within output
git_log_format f004
100%
Passed
Tokens
870
Input
500
Total output
492
Reasoning within output
git_log_format f005
100%
Passed
Tokens
695
Input
647
Total output
638
Reasoning within output
git_log_format f006
100%
Passed
Tokens
884
Input
569
Total output
560
Reasoning within output
git_log_format f007
100%
Passed
Tokens
874
Input
439
Total output
431
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,171
Input
352
Total output
343
Reasoning within output
git_log_format f009
100%
Passed
Tokens
731
Input
475
Total output
470
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,391
Input
503
Total output
494
Reasoning within output
git_log_format f011
100%
Passed
Tokens
418
Input
602
Total output
594
Reasoning within output
git_log_format f012
100%
Passed
Tokens
399
Input
273
Total output
266
Reasoning within output
git_show f001
100%
Passed
Tokens
185
Input
336
Total output
328
Reasoning within output
git_show f002
100%
Passed
Tokens
184
Input
4,005
Total output
3,998
Reasoning within output
git_show f003
100%
Passed
Tokens
663
Input
566
Total output
554
Reasoning within output
git_show f004
100%
Passed
Tokens
452
Input
362
Total output
349
Reasoning within output
git_show f005
100%
Passed
Tokens
186
Input
519
Total output
510
Reasoning within output
git_show f006
100%
Passed
Tokens
191
Input
339
Total output
332
Reasoning within output
git_show f007
100%
Passed
Tokens
190
Input
379
Total output
371
Reasoning within output
git_show f008
100%
Passed
Tokens
200
Input
545
Total output
506
Reasoning within output
git_show f009
100%
Passed
Tokens
308
Input
524
Total output
514
Reasoning within output
git_show f010
100%
Passed
Tokens
182
Input
499
Total output
490
Reasoning within output
git_show f011
100%
Passed
Tokens
216
Input
363
Total output
353
Reasoning within output
git_show f012
100%
Passed
Tokens
320
Input
372
Total output
365
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
72
Input
1,416
Total output
1,409
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
90
Input
1,709
Total output
1,699
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
68
Input
1,305
Total output
1,297
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
133
Input
1,363
Total output
1,336
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
127
Input
951
Total output
933
Reasoning within output
merge_conflicts f006
0%
Failed
Tokens
114
Input
1,528
Total output
1,496
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
121
Input
496
Total output
479
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
92
Input
479
Total output
466
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
91
Input
556
Total output
545
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
171
Input
789
Total output
754
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
132
Input
802
Total output
775
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
225
Input
1,428
Total output
1,379
Reasoning within output
rebase f001
0%
Failed
Tokens
84
Input
1,866
Total output
1,859
Reasoning within output
rebase f002
100%
Passed
Tokens
114
Input
624
Total output
614
Reasoning within output
rebase f003
100%
Passed
Tokens
95
Input
1,200
Total output
1,191
Reasoning within output
rebase f004
100%
Passed
Tokens
146
Input
1,103
Total output
1,077
Reasoning within output
rebase f005
100%
Passed
Tokens
135
Input
764
Total output
749
Reasoning within output
rebase f006
100%
Passed
Tokens
133
Input
1,725
Total output
1,700
Reasoning within output
rebase f007
100%
Passed
Tokens
124
Input
516
Total output
502
Reasoning within output
rebase f008
100%
Passed
Tokens
107
Input
471
Total output
458
Reasoning within output
rebase f009
100%
Passed
Tokens
90
Input
547
Total output
536
Reasoning within output
rebase f010
100%
Passed
Tokens
204
Input
792
Total output
761
Reasoning within output
rebase f011
100%
Passed
Tokens
147
Input
1,266
Total output
1,236
Reasoning within output
rebase f012
0%
Failed
Tokens
261
Input
1,344
Total output
1,297
Reasoning within output
reflog f001
100%
Passed
Tokens
231
Input
701
Total output
664
Reasoning within output
reflog f002
100%
Passed
Tokens
236
Input
1,016
Total output
896
Reasoning within output
reflog f003
100%
Passed
Tokens
196
Input
914
Total output
837
Reasoning within output
reflog f004
100%
Passed
Tokens
323
Input
1,357
Total output
1,195
Reasoning within output
reflog f005
100%
Passed
Tokens
385
Input
1,267
Total output
1,197
Reasoning within output
reflog f006
100%
Passed
Tokens
244
Input
1,149
Total output
1,042
Reasoning within output
reflog f007
100%
Passed
Tokens
287
Input
1,501
Total output
1,384
Reasoning within output
reflog f008
100%
Passed
Tokens
363
Input
1,090
Total output
972
Reasoning within output
reflog f009
100%
Passed
Tokens
348
Input
1,371
Total output
1,256
Reasoning within output
reflog f010
100%
Passed
Tokens
283
Input
1,174
Total output
1,042
Reasoning within output
reflog f011
100%
Passed
Tokens
334
Input
1,417
Total output
1,285
Reasoning within output
reflog f012
100%
Passed
Tokens
340
Input
1,273
Total output
1,107
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
124
Input
495
Total output
467
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
282
Input
871
Total output
862
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
114
Input
399
Total output
386
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
111
Input
519
Total output
502
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
115
Input
683
Total output
671
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
168
Input
403
Total output
388
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
202
Input
613
Total output
596
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
167
Input
672
Total output
661
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
200
Input
566
Total output
548
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
117
Input
347
Total output
335
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
113
Input
469
Total output
454
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
125
Input
717
Total output
699
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
33
Input
305
Total output
295
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
90
Input
885
Total output
872
Reasoning within output
submodule_usage f003
75%
Failed
Tokens
100
Input
1,230
Total output
1,175
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
86
Input
420
Total output
411
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
40
Input
787
Total output
759
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
86
Input
596
Total output
587
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
39
Input
444
Total output
427
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
88
Input
1,360
Total output
1,351
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
85
Input
397
Total output
387
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
92
Input
855
Total output
846
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
102
Input
329
Total output
318
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
38
Input
486
Total output
469
Reasoning within output
tag_management f001
100%
Passed
Tokens
52
Input
402
Total output
393
Reasoning within output
tag_management f002
100%
Passed
Tokens
48
Input
441
Total output
419
Reasoning within output
tag_management f003
100%
Passed
Tokens
54
Input
709
Total output
696
Reasoning within output
tag_management f004
100%
Passed
Tokens
61
Input
417
Total output
408
Reasoning within output
tag_management f005
100%
Passed
Tokens
76
Input
402
Total output
391
Reasoning within output
tag_management f006
100%
Passed
Tokens
58
Input
789
Total output
775
Reasoning within output
tag_management f007
100%
Passed
Tokens
55
Input
449
Total output
437
Reasoning within output
tag_management f008
100%
Passed
Tokens
58
Input
972
Total output
948
Reasoning within output
tag_management f009
100%
Passed
Tokens
62
Input
478
Total output
456
Reasoning within output
tag_management f010
100%
Passed
Tokens
41
Input
384
Total output
370
Reasoning within output
tag_management f011
100%
Passed
Tokens
42
Input
582
Total output
572
Reasoning within output
tag_management f012
100%
Passed
Tokens
83
Input
633
Total output
621
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
131
Input
364
Total output
352
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
142
Input
574
Total output
548
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
210
Input
347
Total output
337
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
214
Input
331
Total output
321
Reasoning within output
worktree_usage f005
33.3%
Failed
Tokens
125
Input
378
Total output
363
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
130
Input
321
Total output
307
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
122
Input
651
Total output
629
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
152
Input
980
Total output
939
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
250
Input
482
Total output
473
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
219
Input
356
Total output
341
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
217
Input
345
Total output
335
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
122
Input
395
Total output
380
Reasoning within output