Inception / mercury-2.5
medium
93.6%
191 / 204 fixtures · 1 run(s)
37,292 input / 148,864 total output / 145,164 reasoning within output tokens $0.02382128
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-3.4%
Text: 93.6% →
JSON: 90.2%
+5
Gained
JSON pass / text fail
−12
Lost
Text pass / JSON fail
179
Unchanged Pass
Both pass
8
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% |
| blame_forensics | 83.3% | 91.7% | + 8.3% |
| commit_squash | 100% | 91.7% | -8.3% |
| git_grep | 91.7% | 100% | + 8.3% |
| merge_conflicts | 75% | 66.7% | -8.3% |
| rebase | 83.3% | 75% | -8.3% |
| submodule_usage | 100% | 91.7% | -8.3% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_clean | 91.7% | 91.7% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 91.7% | 91.7% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
| worktree_usage | 91.7% | 91.7% | + 0% |
Changed Fixtures (17)
Fixture Gallery (204)
blame_forensics f001
0%
Failed
blame_forensics f002
100%
Passed
Tokens
233
Input
754
Total output
744
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
256
Input
586
Total output
576
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
186
Input
789
Total output
780
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
258
Input
586
Total output
575
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
219
Input
607
Total output
600
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
211
Input
522
Total output
511
Reasoning within output
blame_forensics f008
0%
Failed
blame_forensics f009
100%
Passed
Tokens
189
Input
551
Total output
541
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
430
Input
785
Total output
775
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
243
Input
485
Total output
475
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
137
Input
526
Total output
516
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
93
Input
549
Total output
543
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
110
Input
553
Total output
543
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
88
Input
518
Total output
514
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
124
Input
623
Total output
614
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
100
Input
659
Total output
651
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
124
Input
568
Total output
558
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
99
Input
526
Total output
516
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
119
Input
655
Total output
643
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
75
Input
620
Total output
611
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
115
Input
501
Total output
491
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
63
Input
402
Total output
395
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
151
Input
632
Total output
620
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
86
Input
2,005
Total output
1,995
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
101
Input
2,138
Total output
2,129
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
79
Input
775
Total output
764
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
149
Input
1,277
Total output
1,254
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
141
Input
426
Total output
404
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
130
Input
1,679
Total output
1,656
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
123
Input
505
Total output
492
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
113
Input
420
Total output
410
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
95
Input
343
Total output
334
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
203
Input
1,038
Total output
1,010
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
154
Input
637
Total output
612
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
257
Input
1,483
Total output
1,440
Reasoning within output
commit_messages f001
74%
Passed
Tokens
102
Input
637
Total output
627
Reasoning within output
commit_messages f002
83%
Passed
Tokens
212
Input
1,178
Total output
1,165
Reasoning within output
commit_messages f003
94%
Passed
Tokens
72
Input
745
Total output
734
Reasoning within output
commit_messages f004
92.5%
Passed
Tokens
109
Input
494
Total output
484
Reasoning within output
commit_messages f005
92.5%
Passed
Tokens
92
Input
488
Total output
481
Reasoning within output
commit_messages f006
92.5%
Passed
Tokens
141
Input
746
Total output
734
Reasoning within output
commit_messages f007
91.5%
Passed
Tokens
181
Input
777
Total output
767
Reasoning within output
commit_messages f008
95%
Passed
Tokens
67
Input
490
Total output
480
Reasoning within output
commit_messages f009
85%
Passed
Tokens
121
Input
987
Total output
976
Reasoning within output
commit_messages f010
95%
Passed
Tokens
278
Input
1,422
Total output
1,410
Reasoning within output
commit_messages f011
72.5%
Passed
Tokens
137
Input
554
Total output
544
Reasoning within output
commit_messages f012
92.5%
Passed
Tokens
117
Input
683
Total output
674
Reasoning within output
commit_squash f001
100%
Passed
Tokens
132
Input
1,682
Total output
1,663
Reasoning within output
commit_squash f002
100%
Passed
Tokens
110
Input
543
Total output
534
Reasoning within output
commit_squash f003
100%
Passed
Tokens
122
Input
1,574
Total output
1,557
Reasoning within output
commit_squash f004
100%
Passed
Tokens
108
Input
1,004
Total output
989
Reasoning within output
commit_squash f005
100%
Passed
Tokens
108
Input
620
Total output
610
Reasoning within output
commit_squash f006
100%
Passed
Tokens
93
Input
542
Total output
525
Reasoning within output
commit_squash f007
100%
Passed
Tokens
99
Input
458
Total output
443
Reasoning within output
commit_squash f008
100%
Passed
Tokens
106
Input
546
Total output
531
Reasoning within output
commit_squash f009
100%
Passed
Tokens
97
Input
1,504
Total output
1,490
Reasoning within output
commit_squash f010
100%
Passed
Tokens
112
Input
642
Total output
622
Reasoning within output
commit_squash f011
100%
Passed
Tokens
123
Input
484
Total output
466
Reasoning within output
commit_squash f012
100%
Passed
Tokens
120
Input
854
Total output
831
Reasoning within output
git_bisect f001
100%
Passed
Tokens
175
Input
543
Total output
532
Reasoning within output
git_bisect f002
100%
Passed
Tokens
211
Input
662
Total output
653
Reasoning within output
git_bisect f003
100%
Passed
Tokens
191
Input
598
Total output
589
Reasoning within output
git_bisect f004
100%
Passed
Tokens
194
Input
634
Total output
624
Reasoning within output
git_bisect f005
100%
Passed
Tokens
192
Input
562
Total output
552
Reasoning within output
git_bisect f006
100%
Passed
Tokens
232
Input
898
Total output
889
Reasoning within output
git_bisect f007
100%
Passed
Tokens
200
Input
554
Total output
545
Reasoning within output
git_bisect f008
100%
Passed
Tokens
204
Input
537
Total output
528
Reasoning within output
git_bisect f009
100%
Passed
Tokens
201
Input
743
Total output
730
Reasoning within output
git_bisect f010
100%
Passed
Tokens
199
Input
613
Total output
603
Reasoning within output
git_bisect f011
100%
Passed
Tokens
195
Input
569
Total output
562
Reasoning within output
git_bisect f012
100%
Passed
Tokens
224
Input
628
Total output
619
Reasoning within output
git_clean f001
100%
Passed
Tokens
42
Input
1,339
Total output
1,330
Reasoning within output
git_clean f002
100%
Passed
Tokens
52
Input
290
Total output
281
Reasoning within output
git_clean f003
100%
Passed
Tokens
52
Input
407
Total output
397
Reasoning within output
git_clean f004
66.7%
Failed
Tokens
48
Input
1,011
Total output
998
Reasoning within output
git_clean f005
100%
Passed
Tokens
41
Input
723
Total output
714
Reasoning within output
git_clean f006
100%
Passed
Tokens
65
Input
555
Total output
545
Reasoning within output
git_clean f007
100%
Passed
Tokens
55
Input
482
Total output
472
Reasoning within output
git_clean f008
100%
Passed
Tokens
66
Input
478
Total output
468
Reasoning within output
git_clean f009
100%
Passed
Tokens
60
Input
980
Total output
970
Reasoning within output
git_clean f010
100%
Passed
Tokens
53
Input
575
Total output
566
Reasoning within output
git_clean f011
100%
Passed
Tokens
52
Input
1,155
Total output
1,143
Reasoning within output
git_clean f012
100%
Passed
Tokens
53
Input
523
Total output
514
Reasoning within output
git_grep f001
100%
Passed
Tokens
41
Input
332
Total output
321
Reasoning within output
git_grep f002
100%
Passed
Tokens
54
Input
305
Total output
296
Reasoning within output
git_grep f003
100%
Passed
Tokens
73
Input
281
Total output
276
Reasoning within output
git_grep f004
0%
Failed
Tokens
64
Input
786
Total output
773
Reasoning within output
git_grep f005
100%
Passed
Tokens
102
Input
373
Total output
370
Reasoning within output
git_grep f006
100%
Passed
Tokens
30
Input
401
Total output
390
Reasoning within output
git_grep f007
100%
Passed
Tokens
157
Input
941
Total output
933
Reasoning within output
git_grep f008
100%
Passed
Tokens
47
Input
288
Total output
277
Reasoning within output
git_grep f009
100%
Passed
Tokens
42
Input
251
Total output
242
Reasoning within output
git_grep f010
100%
Passed
Tokens
52
Input
439
Total output
434
Reasoning within output
git_grep f011
100%
Passed
Tokens
101
Input
336
Total output
330
Reasoning within output
git_grep f012
100%
Passed
Tokens
54
Input
286
Total output
273
Reasoning within output
git_log_format f001
100%
Passed
Tokens
838
Input
418
Total output
410
Reasoning within output
git_log_format f002
100%
Passed
Tokens
864
Input
523
Total output
511
Reasoning within output
git_log_format f003
100%
Passed
Tokens
677
Input
511
Total output
501
Reasoning within output
git_log_format f004
100%
Passed
Tokens
855
Input
497
Total output
494
Reasoning within output
git_log_format f005
100%
Passed
Tokens
695
Input
654
Total output
642
Reasoning within output
git_log_format f006
100%
Passed
Tokens
894
Input
630
Total output
620
Reasoning within output
git_log_format f007
100%
Passed
Tokens
859
Input
435
Total output
424
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,186
Input
501
Total output
494
Reasoning within output
git_log_format f009
100%
Passed
Tokens
715
Input
389
Total output
380
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,386
Input
509
Total output
500
Reasoning within output
git_log_format f011
100%
Passed
Tokens
422
Input
672
Total output
662
Reasoning within output
git_log_format f012
100%
Passed
Tokens
401
Input
572
Total output
564
Reasoning within output
git_show f001
100%
Passed
Tokens
179
Input
352
Total output
343
Reasoning within output
git_show f002
0%
Failed
Tokens
183
Input
2,469
Total output
2,461
Reasoning within output
git_show f003
100%
Passed
Tokens
673
Input
577
Total output
566
Reasoning within output
git_show f004
100%
Passed
Tokens
449
Input
352
Total output
342
Reasoning within output
git_show f005
100%
Passed
Tokens
188
Input
479
Total output
470
Reasoning within output
git_show f006
100%
Passed
Tokens
190
Input
316
Total output
310
Reasoning within output
git_show f007
100%
Passed
Tokens
185
Input
430
Total output
420
Reasoning within output
git_show f008
100%
Passed
Tokens
189
Input
472
Total output
434
Reasoning within output
git_show f009
100%
Passed
Tokens
304
Input
610
Total output
601
Reasoning within output
git_show f010
100%
Passed
Tokens
184
Input
448
Total output
440
Reasoning within output
git_show f011
100%
Passed
Tokens
216
Input
300
Total output
290
Reasoning within output
git_show f012
100%
Passed
Tokens
334
Input
443
Total output
434
Reasoning within output
merge_conflicts f001
0%
Failed
Tokens
72
Input
1,027
Total output
1,020
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
92
Input
1,475
Total output
1,465
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
67
Input
1,022
Total output
1,014
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
135
Input
1,528
Total output
1,502
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
124
Input
578
Total output
560
Reasoning within output
merge_conflicts f006
0%
Failed
Tokens
116
Input
2,468
Total output
2,442
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
119
Input
651
Total output
639
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
94
Input
565
Total output
555
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
91
Input
560
Total output
551
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
169
Input
980
Total output
949
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
133
Input
1,029
Total output
1,003
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
220
Input
1,851
Total output
1,806
Reasoning within output
rebase f001
0%
Failed
Tokens
84
Input
1,986
Total output
1,979
Reasoning within output
rebase f002
100%
Passed
Tokens
111
Input
546
Total output
537
Reasoning within output
rebase f003
100%
Passed
Tokens
93
Input
939
Total output
930
Reasoning within output
rebase f004
100%
Passed
Tokens
147
Input
833
Total output
803
Reasoning within output
rebase f005
100%
Passed
Tokens
129
Input
949
Total output
930
Reasoning within output
rebase f006
100%
Passed
Tokens
132
Input
1,724
Total output
1,695
Reasoning within output
rebase f007
100%
Passed
Tokens
120
Input
462
Total output
449
Reasoning within output
rebase f008
100%
Passed
Tokens
110
Input
596
Total output
586
Reasoning within output
rebase f009
100%
Passed
Tokens
90
Input
794
Total output
785
Reasoning within output
rebase f010
100%
Passed
Tokens
197
Input
832
Total output
804
Reasoning within output
rebase f011
100%
Passed
Tokens
146
Input
934
Total output
905
Reasoning within output
rebase f012
0%
Failed
Tokens
256
Input
1,922
Total output
1,876
Reasoning within output
reflog f001
100%
Passed
Tokens
238
Input
916
Total output
878
Reasoning within output
reflog f002
100%
Passed
Tokens
233
Input
888
Total output
828
Reasoning within output
reflog f003
100%
Passed
Tokens
197
Input
728
Total output
660
Reasoning within output
reflog f004
100%
Passed
Tokens
343
Input
1,410
Total output
1,271
Reasoning within output
reflog f005
100%
Passed
Tokens
389
Input
1,235
Total output
1,179
Reasoning within output
reflog f006
100%
Passed
Tokens
247
Input
1,056
Total output
956
Reasoning within output
reflog f007
100%
Passed
Tokens
293
Input
1,020
Total output
908
Reasoning within output
reflog f008
100%
Passed
Tokens
371
Input
862
Total output
747
Reasoning within output
reflog f009
100%
Passed
Tokens
338
Input
1,092
Total output
977
Reasoning within output
reflog f010
100%
Passed
Tokens
291
Input
1,007
Total output
897
Reasoning within output
reflog f011
100%
Passed
Tokens
334
Input
1,053
Total output
941
Reasoning within output
reflog f012
100%
Passed
Tokens
352
Input
1,566
Total output
1,416
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
123
Input
394
Total output
382
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
295
Input
663
Total output
655
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
112
Input
621
Total output
606
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
111
Input
429
Total output
416
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
117
Input
396
Total output
385
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
175
Input
623
Total output
612
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
203
Input
477
Total output
465
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
167
Input
675
Total output
660
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
200
Input
395
Total output
383
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
119
Input
476
Total output
465
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
109
Input
586
Total output
571
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
123
Input
510
Total output
493
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
32
Input
469
Total output
459
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
88
Input
644
Total output
632
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
98
Input
924
Total output
888
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
84
Input
472
Total output
461
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
40
Input
624
Total output
598
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
85
Input
848
Total output
840
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
39
Input
464
Total output
445
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
94
Input
813
Total output
801
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
85
Input
796
Total output
786
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
93
Input
1,053
Total output
1,043
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
94
Input
366
Total output
357
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
38
Input
387
Total output
369
Reasoning within output
tag_management f001
100%
Passed
Tokens
52
Input
409
Total output
400
Reasoning within output
tag_management f002
100%
Passed
Tokens
49
Input
518
Total output
498
Reasoning within output
tag_management f003
100%
Passed
Tokens
57
Input
677
Total output
665
Reasoning within output
tag_management f004
100%
Passed
Tokens
62
Input
361
Total output
353
Reasoning within output
tag_management f005
100%
Passed
Tokens
73
Input
554
Total output
545
Reasoning within output
tag_management f006
100%
Passed
Tokens
60
Input
579
Total output
559
Reasoning within output
tag_management f007
100%
Passed
Tokens
56
Input
1,064
Total output
1,049
Reasoning within output
tag_management f008
100%
Passed
Tokens
59
Input
1,456
Total output
1,427
Reasoning within output
tag_management f009
100%
Passed
Tokens
60
Input
764
Total output
743
Reasoning within output
tag_management f010
100%
Passed
Tokens
41
Input
336
Total output
327
Reasoning within output
tag_management f011
100%
Passed
Tokens
42
Input
556
Total output
547
Reasoning within output
tag_management f012
100%
Passed
Tokens
82
Input
1,183
Total output
1,170
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
136
Input
429
Total output
415
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
142
Input
998
Total output
971
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
215
Input
817
Total output
807
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
211
Input
380
Total output
373
Reasoning within output
worktree_usage f005
33.3%
Failed
Tokens
130
Input
502
Total output
488
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
131
Input
552
Total output
534
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
126
Input
756
Total output
734
Reasoning within output
worktree_usage f008
100%
Passed
Tokens
155
Input
1,064
Total output
1,013
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
238
Input
361
Total output
351
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
230
Input
586
Total output
571
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
212
Input
375
Total output
362
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
123
Input
384
Total output
366
Reasoning within output