Inception / mercury-2.5
high
94.6%
193 / 204 fixtures · 1 run(s)
37,360 input / 151,322 total output / 147,612 reasoning within output tokens $0.02419270
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-3.9%
Text: 94.6% →
JSON: 90.7%
+4
Gained
JSON pass / text fail
−12
Lost
Text pass / JSON fail
181
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% |
| commit_squash | 100% | 83.3% | -16.7% |
| merge_conflicts | 83.3% | 66.7% | -16.7% |
| blame_forensics | 83.3% | 91.7% | + 8.3% |
| rebase | 91.7% | 83.3% | -8.3% |
| worktree_usage | 91.7% | 83.3% | -8.3% |
| cherry_pick | 83.3% | 75% | -8.3% |
| git_clean | 91.7% | 100% | + 8.3% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_grep | 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% |
| submodule_usage | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
Changed Fixtures (16)
Fixture Gallery (204)
blame_forensics f001
0%
Failed
blame_forensics f002
100%
Passed
Tokens
234
Input
778
Total output
771
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
275
Input
659
Total output
649
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
191
Input
648
Total output
636
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
249
Input
856
Total output
848
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
232
Input
1,192
Total output
1,183
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
208
Input
458
Total output
449
Reasoning within output
blame_forensics f008
0%
Failed
blame_forensics f009
100%
Passed
Tokens
192
Input
589
Total output
579
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
425
Input
961
Total output
951
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
238
Input
554
Total output
548
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
140
Input
551
Total output
542
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
94
Input
493
Total output
485
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
108
Input
585
Total output
576
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
90
Input
514
Total output
506
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
127
Input
627
Total output
617
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
97
Input
519
Total output
513
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
120
Input
515
Total output
500
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
96
Input
407
Total output
397
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
119
Input
558
Total output
545
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
72
Input
531
Total output
522
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
108
Input
554
Total output
544
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
64
Input
367
Total output
361
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
149
Input
696
Total output
681
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
86
Input
2,107
Total output
2,099
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
103
Input
2,137
Total output
2,126
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
79
Input
872
Total output
864
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
147
Input
2,111
Total output
2,088
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
141
Input
1,022
Total output
999
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
129
Input
1,849
Total output
1,826
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
121
Input
792
Total output
777
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
109
Input
485
Total output
474
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
96
Input
389
Total output
378
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
206
Input
821
Total output
790
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
154
Input
844
Total output
818
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
264
Input
1,643
Total output
1,594
Reasoning within output
commit_messages f001
92.5%
Passed
Tokens
104
Input
554
Total output
545
Reasoning within output
commit_messages f002
80%
Passed
Tokens
213
Input
1,263
Total output
1,249
Reasoning within output
commit_messages f003
92.5%
Passed
Tokens
72
Input
686
Total output
675
Reasoning within output
commit_messages f004
95%
Passed
Tokens
108
Input
479
Total output
470
Reasoning within output
commit_messages f005
84%
Passed
Tokens
92
Input
674
Total output
667
Reasoning within output
commit_messages f006
92.5%
Passed
Tokens
142
Input
520
Total output
510
Reasoning within output
commit_messages f007
94%
Passed
Tokens
184
Input
1,107
Total output
1,098
Reasoning within output
commit_messages f008
92.5%
Passed
Tokens
67
Input
438
Total output
427
Reasoning within output
commit_messages f009
82.5%
Passed
Tokens
121
Input
733
Total output
718
Reasoning within output
commit_messages f010
87.5%
Passed
Tokens
288
Input
903
Total output
892
Reasoning within output
commit_messages f011
62.5%
Passed
Tokens
140
Input
1,004
Total output
993
Reasoning within output
commit_messages f012
92.5%
Passed
Tokens
119
Input
501
Total output
491
Reasoning within output
commit_squash f001
100%
Passed
Tokens
130
Input
1,421
Total output
1,406
Reasoning within output
commit_squash f002
100%
Passed
Tokens
107
Input
784
Total output
770
Reasoning within output
commit_squash f003
100%
Passed
Tokens
122
Input
1,237
Total output
1,225
Reasoning within output
commit_squash f004
100%
Passed
Tokens
111
Input
2,359
Total output
2,346
Reasoning within output
commit_squash f005
100%
Passed
Tokens
105
Input
559
Total output
549
Reasoning within output
commit_squash f006
100%
Passed
Tokens
94
Input
627
Total output
616
Reasoning within output
commit_squash f007
100%
Passed
Tokens
96
Input
557
Total output
542
Reasoning within output
commit_squash f008
100%
Passed
Tokens
106
Input
496
Total output
481
Reasoning within output
commit_squash f009
100%
Passed
Tokens
103
Input
1,647
Total output
1,633
Reasoning within output
commit_squash f010
100%
Passed
Tokens
119
Input
531
Total output
509
Reasoning within output
commit_squash f011
100%
Passed
Tokens
122
Input
527
Total output
508
Reasoning within output
commit_squash f012
100%
Passed
Tokens
123
Input
572
Total output
549
Reasoning within output
git_bisect f001
100%
Passed
Tokens
175
Input
540
Total output
531
Reasoning within output
git_bisect f002
100%
Passed
Tokens
199
Input
634
Total output
625
Reasoning within output
git_bisect f003
100%
Passed
Tokens
199
Input
808
Total output
799
Reasoning within output
git_bisect f004
100%
Passed
Tokens
200
Input
568
Total output
559
Reasoning within output
git_bisect f005
100%
Passed
Tokens
206
Input
680
Total output
670
Reasoning within output
git_bisect f006
100%
Passed
Tokens
231
Input
570
Total output
560
Reasoning within output
git_bisect f007
100%
Passed
Tokens
200
Input
544
Total output
536
Reasoning within output
git_bisect f008
100%
Passed
Tokens
201
Input
609
Total output
599
Reasoning within output
git_bisect f009
100%
Passed
Tokens
198
Input
780
Total output
771
Reasoning within output
git_bisect f010
100%
Passed
Tokens
202
Input
594
Total output
584
Reasoning within output
git_bisect f011
100%
Passed
Tokens
208
Input
595
Total output
582
Reasoning within output
git_bisect f012
100%
Passed
Tokens
225
Input
603
Total output
593
Reasoning within output
git_clean f001
100%
Passed
Tokens
42
Input
1,334
Total output
1,324
Reasoning within output
git_clean f002
100%
Passed
Tokens
52
Input
431
Total output
421
Reasoning within output
git_clean f003
100%
Passed
Tokens
52
Input
499
Total output
489
Reasoning within output
git_clean f004
33.3%
Failed
Tokens
49
Input
795
Total output
786
Reasoning within output
git_clean f005
100%
Passed
Tokens
41
Input
1,157
Total output
1,148
Reasoning within output
git_clean f006
100%
Passed
Tokens
66
Input
735
Total output
724
Reasoning within output
git_clean f007
100%
Passed
Tokens
57
Input
1,612
Total output
1,601
Reasoning within output
git_clean f008
100%
Passed
Tokens
69
Input
357
Total output
346
Reasoning within output
git_clean f009
100%
Passed
Tokens
60
Input
458
Total output
445
Reasoning within output
git_clean f010
100%
Passed
Tokens
53
Input
415
Total output
405
Reasoning within output
git_clean f011
100%
Passed
Tokens
53
Input
650
Total output
639
Reasoning within output
git_clean f012
100%
Passed
Tokens
54
Input
630
Total output
620
Reasoning within output
git_grep f001
100%
Passed
Tokens
41
Input
332
Total output
322
Reasoning within output
git_grep f002
100%
Passed
Tokens
56
Input
323
Total output
314
Reasoning within output
git_grep f003
100%
Passed
Tokens
74
Input
269
Total output
261
Reasoning within output
git_grep f004
0%
Failed
Tokens
64
Input
339
Total output
326
Reasoning within output
git_grep f005
100%
Passed
Tokens
103
Input
375
Total output
368
Reasoning within output
git_grep f006
100%
Passed
Tokens
30
Input
613
Total output
605
Reasoning within output
git_grep f007
100%
Passed
Tokens
156
Input
802
Total output
793
Reasoning within output
git_grep f008
100%
Passed
Tokens
47
Input
293
Total output
282
Reasoning within output
git_grep f009
100%
Passed
Tokens
42
Input
260
Total output
251
Reasoning within output
git_grep f010
100%
Passed
Tokens
52
Input
412
Total output
404
Reasoning within output
git_grep f011
100%
Passed
Tokens
98
Input
396
Total output
388
Reasoning within output
git_grep f012
100%
Passed
Tokens
54
Input
287
Total output
275
Reasoning within output
git_log_format f001
100%
Passed
Tokens
845
Input
449
Total output
441
Reasoning within output
git_log_format f002
100%
Passed
Tokens
884
Input
439
Total output
426
Reasoning within output
git_log_format f003
100%
Passed
Tokens
690
Input
553
Total output
542
Reasoning within output
git_log_format f004
100%
Passed
Tokens
850
Input
486
Total output
480
Reasoning within output
git_log_format f005
100%
Passed
Tokens
695
Input
711
Total output
702
Reasoning within output
git_log_format f006
100%
Passed
Tokens
871
Input
734
Total output
727
Reasoning within output
git_log_format f007
100%
Passed
Tokens
895
Input
528
Total output
518
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,186
Input
322
Total output
318
Reasoning within output
git_log_format f009
100%
Passed
Tokens
730
Input
476
Total output
465
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,351
Input
516
Total output
507
Reasoning within output
git_log_format f011
100%
Passed
Tokens
394
Input
518
Total output
510
Reasoning within output
git_log_format f012
100%
Passed
Tokens
395
Input
593
Total output
586
Reasoning within output
git_show f001
100%
Passed
Tokens
189
Input
340
Total output
331
Reasoning within output
git_show f002
0%
Failed
Tokens
188
Input
2,611
Total output
2,605
Reasoning within output
git_show f003
100%
Passed
Tokens
660
Input
492
Total output
480
Reasoning within output
git_show f004
100%
Passed
Tokens
460
Input
377
Total output
364
Reasoning within output
git_show f005
100%
Passed
Tokens
184
Input
517
Total output
512
Reasoning within output
git_show f006
100%
Passed
Tokens
195
Input
301
Total output
294
Reasoning within output
git_show f007
100%
Passed
Tokens
190
Input
515
Total output
505
Reasoning within output
git_show f008
100%
Passed
Tokens
196
Input
484
Total output
445
Reasoning within output
git_show f009
100%
Passed
Tokens
297
Input
479
Total output
472
Reasoning within output
git_show f010
100%
Passed
Tokens
184
Input
606
Total output
600
Reasoning within output
git_show f011
100%
Passed
Tokens
215
Input
331
Total output
321
Reasoning within output
git_show f012
100%
Passed
Tokens
324
Input
518
Total output
510
Reasoning within output
merge_conflicts f001
0%
Failed
Tokens
72
Input
1,523
Total output
1,517
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
90
Input
1,172
Total output
1,160
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
68
Input
1,257
Total output
1,248
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
133
Input
1,928
Total output
1,899
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
124
Input
830
Total output
805
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
119
Input
1,495
Total output
1,467
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
121
Input
479
Total output
467
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
92
Input
659
Total output
649
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
91
Input
819
Total output
809
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
171
Input
1,092
Total output
1,058
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
130
Input
1,007
Total output
978
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
218
Input
960
Total output
917
Reasoning within output
rebase f001
100%
Passed
Tokens
88
Input
2,180
Total output
2,173
Reasoning within output
rebase f002
100%
Passed
Tokens
113
Input
770
Total output
760
Reasoning within output
rebase f003
100%
Passed
Tokens
92
Input
886
Total output
879
Reasoning within output
rebase f004
100%
Passed
Tokens
150
Input
872
Total output
845
Reasoning within output
rebase f005
100%
Passed
Tokens
131
Input
1,158
Total output
1,138
Reasoning within output
rebase f006
100%
Passed
Tokens
126
Input
1,166
Total output
1,138
Reasoning within output
rebase f007
100%
Passed
Tokens
122
Input
456
Total output
442
Reasoning within output
rebase f008
100%
Passed
Tokens
108
Input
497
Total output
484
Reasoning within output
rebase f009
100%
Passed
Tokens
94
Input
771
Total output
762
Reasoning within output
rebase f010
100%
Passed
Tokens
200
Input
684
Total output
656
Reasoning within output
rebase f011
100%
Passed
Tokens
147
Input
1,090
Total output
1,064
Reasoning within output
rebase f012
0%
Failed
Tokens
255
Input
1,547
Total output
1,503
Reasoning within output
reflog f001
100%
Passed
Tokens
234
Input
808
Total output
770
Reasoning within output
reflog f002
100%
Passed
Tokens
225
Input
1,029
Total output
962
Reasoning within output
reflog f003
100%
Passed
Tokens
201
Input
831
Total output
779
Reasoning within output
reflog f004
100%
Passed
Tokens
330
Input
1,346
Total output
1,219
Reasoning within output
reflog f005
100%
Passed
Tokens
387
Input
974
Total output
921
Reasoning within output
reflog f006
100%
Passed
Tokens
252
Input
916
Total output
792
Reasoning within output
reflog f007
100%
Passed
Tokens
299
Input
1,561
Total output
1,465
Reasoning within output
reflog f008
100%
Passed
Tokens
383
Input
1,131
Total output
1,018
Reasoning within output
reflog f009
100%
Passed
Tokens
341
Input
1,493
Total output
1,355
Reasoning within output
reflog f010
100%
Passed
Tokens
280
Input
1,238
Total output
1,173
Reasoning within output
reflog f011
100%
Passed
Tokens
350
Input
2,055
Total output
1,927
Reasoning within output
reflog f012
100%
Passed
Tokens
331
Input
966
Total output
834
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
125
Input
471
Total output
448
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
286
Input
594
Total output
586
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
115
Input
348
Total output
333
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
110
Input
601
Total output
590
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
117
Input
604
Total output
584
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
171
Input
627
Total output
612
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
207
Input
712
Total output
694
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
168
Input
439
Total output
422
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
197
Input
534
Total output
514
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
117
Input
497
Total output
478
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
111
Input
531
Total output
511
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
126
Input
585
Total output
567
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
33
Input
426
Total output
417
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
94
Input
673
Total output
664
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
99
Input
779
Total output
740
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
86
Input
490
Total output
481
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
39
Input
683
Total output
661
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
82
Input
985
Total output
977
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
39
Input
504
Total output
484
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
89
Input
531
Total output
523
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
86
Input
847
Total output
840
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
91
Input
672
Total output
661
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
98
Input
371
Total output
361
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
37
Input
377
Total output
362
Reasoning within output
tag_management f001
100%
Passed
Tokens
49
Input
401
Total output
391
Reasoning within output
tag_management f002
100%
Passed
Tokens
48
Input
538
Total output
519
Reasoning within output
tag_management f003
100%
Passed
Tokens
55
Input
471
Total output
456
Reasoning within output
tag_management f004
100%
Passed
Tokens
63
Input
402
Total output
393
Reasoning within output
tag_management f005
100%
Passed
Tokens
75
Input
508
Total output
495
Reasoning within output
tag_management f006
100%
Passed
Tokens
56
Input
801
Total output
787
Reasoning within output
tag_management f007
100%
Passed
Tokens
56
Input
547
Total output
535
Reasoning within output
tag_management f008
100%
Passed
Tokens
60
Input
1,056
Total output
1,026
Reasoning within output
tag_management f009
100%
Passed
Tokens
63
Input
655
Total output
635
Reasoning within output
tag_management f010
100%
Passed
Tokens
42
Input
450
Total output
440
Reasoning within output
tag_management f011
100%
Passed
Tokens
43
Input
398
Total output
387
Reasoning within output
tag_management f012
100%
Passed
Tokens
83
Input
1,166
Total output
1,152
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
137
Input
452
Total output
440
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
130
Input
661
Total output
635
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
215
Input
538
Total output
526
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
215
Input
456
Total output
446
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
123
Input
450
Total output
433
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
129
Input
628
Total output
615
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
133
Input
615
Total output
593
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
153
Input
942
Total output
901
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
241
Input
312
Total output
302
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
222
Input
474
Total output
459
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
219
Input
397
Total output
387
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
131
Input
419
Total output
404
Reasoning within output