Inception / mercury-2.5
max
94.1%
192 / 204 fixtures · 1 run(s)
37,557 input / 148,719 total output / 144,833 reasoning within output tokens $0.02381013
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-3.4%
Text: 94.1% →
JSON: 90.7%
+3
Gained
JSON pass / text fail
−10
Lost
Text pass / JSON fail
182
Unchanged Pass
Both pass
9
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 | 66.7% | 83.3% | + 16.7% |
| blame_forensics | 91.7% | 83.3% | -8.3% |
| cherry_pick | 91.7% | 83.3% | -8.3% |
| rebase | 91.7% | 83.3% | -8.3% |
| git_clean | 75% | 83.3% | + 8.3% |
| git_grep | 100% | 91.7% | -8.3% |
| submodule_usage | 100% | 91.7% | -8.3% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 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 (13)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
230
Input
739
Total output
732
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
239
Input
717
Total output
707
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
264
Input
612
Total output
602
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
182
Input
717
Total output
705
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
250
Input
950
Total output
940
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
233
Input
1,050
Total output
1,041
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
212
Input
529
Total output
519
Reasoning within output
blame_forensics f008
0%
Failed
blame_forensics f009
100%
Passed
Tokens
197
Input
602
Total output
593
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
427
Input
865
Total output
857
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
236
Input
543
Total output
534
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
130
Input
624
Total output
612
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
94
Input
512
Total output
502
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
107
Input
610
Total output
601
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
86
Input
575
Total output
569
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
127
Input
513
Total output
503
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
98
Input
624
Total output
615
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
124
Input
494
Total output
479
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
96
Input
431
Total output
420
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
115
Input
533
Total output
519
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
74
Input
549
Total output
538
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
110
Input
507
Total output
497
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
61
Input
322
Total output
315
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
152
Input
556
Total output
541
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
86
Input
1,497
Total output
1,488
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
104
Input
1,225
Total output
1,215
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
81
Input
617
Total output
608
Reasoning within output
cherry_pick f004
100%
Passed
Tokens
149
Input
1,992
Total output
1,966
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
135
Input
920
Total output
898
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
135
Input
1,264
Total output
1,236
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
124
Input
516
Total output
506
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
115
Input
531
Total output
521
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
94
Input
425
Total output
413
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
202
Input
938
Total output
905
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
156
Input
712
Total output
683
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
261
Input
2,229
Total output
2,179
Reasoning within output
commit_messages f001
70%
Passed
Tokens
104
Input
788
Total output
777
Reasoning within output
commit_messages f002
82.5%
Passed
Tokens
212
Input
767
Total output
755
Reasoning within output
commit_messages f003
94%
Passed
Tokens
73
Input
499
Total output
486
Reasoning within output
commit_messages f004
89%
Passed
Tokens
108
Input
588
Total output
580
Reasoning within output
commit_messages f005
85%
Passed
Tokens
94
Input
725
Total output
716
Reasoning within output
commit_messages f006
91.5%
Passed
Tokens
141
Input
1,003
Total output
992
Reasoning within output
commit_messages f007
91.5%
Passed
Tokens
184
Input
1,172
Total output
1,163
Reasoning within output
commit_messages f008
95%
Passed
Tokens
67
Input
494
Total output
484
Reasoning within output
commit_messages f009
85%
Passed
Tokens
117
Input
892
Total output
883
Reasoning within output
commit_messages f010
92.5%
Passed
Tokens
278
Input
745
Total output
733
Reasoning within output
commit_messages f011
84%
Passed
Tokens
140
Input
826
Total output
807
Reasoning within output
commit_messages f012
92.5%
Passed
Tokens
116
Input
448
Total output
436
Reasoning within output
commit_squash f001
100%
Passed
Tokens
130
Input
1,353
Total output
1,338
Reasoning within output
commit_squash f002
100%
Passed
Tokens
110
Input
582
Total output
567
Reasoning within output
commit_squash f003
100%
Passed
Tokens
118
Input
1,191
Total output
1,173
Reasoning within output
commit_squash f004
100%
Passed
Tokens
106
Input
1,310
Total output
1,295
Reasoning within output
commit_squash f005
100%
Passed
Tokens
105
Input
769
Total output
756
Reasoning within output
commit_squash f006
100%
Passed
Tokens
91
Input
522
Total output
507
Reasoning within output
commit_squash f007
100%
Passed
Tokens
94
Input
573
Total output
558
Reasoning within output
commit_squash f008
100%
Passed
Tokens
103
Input
567
Total output
555
Reasoning within output
commit_squash f009
100%
Passed
Tokens
100
Input
1,210
Total output
1,192
Reasoning within output
commit_squash f010
100%
Passed
Tokens
114
Input
869
Total output
847
Reasoning within output
commit_squash f011
100%
Passed
Tokens
120
Input
444
Total output
429
Reasoning within output
commit_squash f012
100%
Passed
Tokens
126
Input
596
Total output
571
Reasoning within output
git_bisect f001
100%
Passed
Tokens
176
Input
488
Total output
479
Reasoning within output
git_bisect f002
100%
Passed
Tokens
203
Input
558
Total output
549
Reasoning within output
git_bisect f003
100%
Passed
Tokens
195
Input
630
Total output
621
Reasoning within output
git_bisect f004
100%
Passed
Tokens
203
Input
790
Total output
779
Reasoning within output
git_bisect f005
100%
Passed
Tokens
203
Input
575
Total output
562
Reasoning within output
git_bisect f006
100%
Passed
Tokens
233
Input
621
Total output
609
Reasoning within output
git_bisect f007
100%
Passed
Tokens
207
Input
689
Total output
680
Reasoning within output
git_bisect f008
100%
Passed
Tokens
204
Input
577
Total output
567
Reasoning within output
git_bisect f009
100%
Passed
Tokens
196
Input
542
Total output
532
Reasoning within output
git_bisect f010
100%
Passed
Tokens
206
Input
889
Total output
877
Reasoning within output
git_bisect f011
100%
Passed
Tokens
195
Input
613
Total output
600
Reasoning within output
git_bisect f012
100%
Passed
Tokens
234
Input
611
Total output
600
Reasoning within output
git_clean f001
50%
Failed
Tokens
42
Input
756
Total output
744
Reasoning within output
git_clean f002
100%
Passed
Tokens
52
Input
383
Total output
372
Reasoning within output
git_clean f003
100%
Passed
Tokens
51
Input
328
Total output
318
Reasoning within output
git_clean f004
100%
Passed
Tokens
47
Input
864
Total output
852
Reasoning within output
git_clean f005
75%
Failed
Tokens
41
Input
717
Total output
707
Reasoning within output
git_clean f006
100%
Passed
Tokens
65
Input
393
Total output
382
Reasoning within output
git_clean f007
100%
Passed
Tokens
57
Input
1,107
Total output
1,097
Reasoning within output
git_clean f008
100%
Passed
Tokens
68
Input
291
Total output
282
Reasoning within output
git_clean f009
100%
Passed
Tokens
60
Input
769
Total output
759
Reasoning within output
git_clean f010
100%
Passed
Tokens
53
Input
590
Total output
581
Reasoning within output
git_clean f011
40%
Failed
Tokens
51
Input
1,097
Total output
1,086
Reasoning within output
git_clean f012
100%
Passed
Tokens
53
Input
668
Total output
658
Reasoning within output
git_grep f001
100%
Passed
Tokens
40
Input
288
Total output
280
Reasoning within output
git_grep f002
100%
Passed
Tokens
57
Input
328
Total output
322
Reasoning within output
git_grep f003
100%
Passed
Tokens
76
Input
273
Total output
268
Reasoning within output
git_grep f004
100%
Passed
Tokens
64
Input
328
Total output
320
Reasoning within output
git_grep f005
100%
Passed
Tokens
103
Input
347
Total output
341
Reasoning within output
git_grep f006
100%
Passed
Tokens
30
Input
569
Total output
561
Reasoning within output
git_grep f007
100%
Passed
Tokens
151
Input
914
Total output
906
Reasoning within output
git_grep f008
100%
Passed
Tokens
47
Input
279
Total output
273
Reasoning within output
git_grep f009
100%
Passed
Tokens
42
Input
274
Total output
265
Reasoning within output
git_grep f010
100%
Passed
Tokens
52
Input
544
Total output
535
Reasoning within output
git_grep f011
100%
Passed
Tokens
98
Input
326
Total output
320
Reasoning within output
git_grep f012
100%
Passed
Tokens
52
Input
307
Total output
293
Reasoning within output
git_log_format f001
100%
Passed
Tokens
859
Input
386
Total output
382
Reasoning within output
git_log_format f002
100%
Passed
Tokens
858
Input
546
Total output
535
Reasoning within output
git_log_format f003
100%
Passed
Tokens
711
Input
452
Total output
439
Reasoning within output
git_log_format f004
100%
Passed
Tokens
868
Input
477
Total output
467
Reasoning within output
git_log_format f005
100%
Passed
Tokens
726
Input
691
Total output
682
Reasoning within output
git_log_format f006
100%
Passed
Tokens
874
Input
650
Total output
642
Reasoning within output
git_log_format f007
100%
Passed
Tokens
883
Input
475
Total output
463
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,145
Input
388
Total output
384
Reasoning within output
git_log_format f009
100%
Passed
Tokens
705
Input
352
Total output
341
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,378
Input
570
Total output
563
Reasoning within output
git_log_format f011
100%
Passed
Tokens
435
Input
567
Total output
557
Reasoning within output
git_log_format f012
100%
Passed
Tokens
399
Input
318
Total output
313
Reasoning within output
git_show f001
100%
Passed
Tokens
185
Input
339
Total output
328
Reasoning within output
git_show f002
0%
Failed
Tokens
183
Input
3,109
Total output
3,101
Reasoning within output
git_show f003
100%
Passed
Tokens
647
Input
456
Total output
444
Reasoning within output
git_show f004
100%
Passed
Tokens
463
Input
404
Total output
395
Reasoning within output
git_show f005
100%
Passed
Tokens
190
Input
424
Total output
414
Reasoning within output
git_show f006
100%
Passed
Tokens
198
Input
268
Total output
261
Reasoning within output
git_show f007
100%
Passed
Tokens
190
Input
495
Total output
485
Reasoning within output
git_show f008
100%
Passed
Tokens
199
Input
468
Total output
430
Reasoning within output
git_show f009
100%
Passed
Tokens
303
Input
582
Total output
578
Reasoning within output
git_show f010
100%
Passed
Tokens
191
Input
454
Total output
448
Reasoning within output
git_show f011
100%
Passed
Tokens
219
Input
362
Total output
354
Reasoning within output
git_show f012
100%
Passed
Tokens
316
Input
386
Total output
379
Reasoning within output
merge_conflicts f001
0%
Failed
Tokens
73
Input
1,487
Total output
1,477
Reasoning within output
merge_conflicts f002
0%
Failed
Tokens
92
Input
1,530
Total output
1,521
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
67
Input
886
Total output
877
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
132
Input
956
Total output
930
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
125
Input
873
Total output
850
Reasoning within output
merge_conflicts f006
0%
Failed
Tokens
116
Input
2,958
Total output
2,940
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
121
Input
566
Total output
552
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
95
Input
470
Total output
460
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
88
Input
593
Total output
584
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
170
Input
698
Total output
670
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
132
Input
756
Total output
729
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
216
Input
1,340
Total output
1,295
Reasoning within output
rebase f001
100%
Passed
Tokens
86
Input
2,198
Total output
2,189
Reasoning within output
rebase f002
100%
Passed
Tokens
111
Input
736
Total output
724
Reasoning within output
rebase f003
100%
Passed
Tokens
92
Input
838
Total output
828
Reasoning within output
rebase f004
100%
Passed
Tokens
149
Input
1,000
Total output
974
Reasoning within output
rebase f005
100%
Passed
Tokens
132
Input
886
Total output
866
Reasoning within output
rebase f006
100%
Passed
Tokens
133
Input
1,198
Total output
1,172
Reasoning within output
rebase f007
100%
Passed
Tokens
127
Input
637
Total output
626
Reasoning within output
rebase f008
100%
Passed
Tokens
107
Input
513
Total output
502
Reasoning within output
rebase f009
100%
Passed
Tokens
92
Input
994
Total output
983
Reasoning within output
rebase f010
100%
Passed
Tokens
196
Input
1,204
Total output
1,171
Reasoning within output
rebase f011
100%
Passed
Tokens
143
Input
1,044
Total output
1,013
Reasoning within output
rebase f012
0%
Failed
Tokens
252
Input
2,093
Total output
2,047
Reasoning within output
reflog f001
100%
Passed
Tokens
250
Input
880
Total output
842
Reasoning within output
reflog f002
100%
Passed
Tokens
228
Input
923
Total output
855
Reasoning within output
reflog f003
100%
Passed
Tokens
202
Input
732
Total output
658
Reasoning within output
reflog f004
100%
Passed
Tokens
332
Input
1,493
Total output
1,369
Reasoning within output
reflog f005
100%
Passed
Tokens
398
Input
1,106
Total output
1,051
Reasoning within output
reflog f006
100%
Passed
Tokens
259
Input
1,136
Total output
1,028
Reasoning within output
reflog f007
100%
Passed
Tokens
287
Input
1,379
Total output
1,251
Reasoning within output
reflog f008
100%
Passed
Tokens
375
Input
994
Total output
871
Reasoning within output
reflog f009
100%
Passed
Tokens
326
Input
1,032
Total output
981
Reasoning within output
reflog f010
100%
Passed
Tokens
289
Input
950
Total output
816
Reasoning within output
reflog f011
100%
Passed
Tokens
335
Input
1,568
Total output
1,384
Reasoning within output
reflog f012
100%
Passed
Tokens
341
Input
1,597
Total output
1,418
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
124
Input
416
Total output
407
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
289
Input
777
Total output
763
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
115
Input
483
Total output
465
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
107
Input
493
Total output
471
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
119
Input
412
Total output
403
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
171
Input
545
Total output
534
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
199
Input
652
Total output
637
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
168
Input
453
Total output
443
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
200
Input
629
Total output
590
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
117
Input
302
Total output
292
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
109
Input
520
Total output
513
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
124
Input
489
Total output
475
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
32
Input
320
Total output
309
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
90
Input
1,242
Total output
1,232
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
101
Input
1,535
Total output
1,473
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
83
Input
304
Total output
293
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
40
Input
1,127
Total output
1,102
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
84
Input
1,939
Total output
1,930
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
39
Input
455
Total output
432
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
88
Input
570
Total output
558
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
84
Input
437
Total output
429
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
91
Input
617
Total output
607
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
93
Input
382
Total output
375
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
37
Input
575
Total output
560
Reasoning within output
tag_management f001
100%
Passed
Tokens
53
Input
363
Total output
354
Reasoning within output
tag_management f002
100%
Passed
Tokens
48
Input
310
Total output
290
Reasoning within output
tag_management f003
100%
Passed
Tokens
50
Input
660
Total output
648
Reasoning within output
tag_management f004
100%
Passed
Tokens
62
Input
359
Total output
348
Reasoning within output
tag_management f005
100%
Passed
Tokens
74
Input
308
Total output
300
Reasoning within output
tag_management f006
100%
Passed
Tokens
57
Input
706
Total output
693
Reasoning within output
tag_management f007
100%
Passed
Tokens
57
Input
473
Total output
458
Reasoning within output
tag_management f008
100%
Passed
Tokens
60
Input
926
Total output
899
Reasoning within output
tag_management f009
100%
Passed
Tokens
63
Input
512
Total output
494
Reasoning within output
tag_management f010
100%
Passed
Tokens
42
Input
403
Total output
392
Reasoning within output
tag_management f011
100%
Passed
Tokens
44
Input
435
Total output
424
Reasoning within output
tag_management f012
100%
Passed
Tokens
80
Input
1,284
Total output
1,274
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
134
Input
325
Total output
316
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
140
Input
571
Total output
548
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
210
Input
395
Total output
385
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
211
Input
404
Total output
394
Reasoning within output
worktree_usage f005
33.3%
Failed
Tokens
127
Input
376
Total output
367
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
126
Input
426
Total output
407
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
133
Input
761
Total output
741
Reasoning within output
worktree_usage f008
100%
Passed
Tokens
154
Input
1,201
Total output
1,148
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
238
Input
309
Total output
299
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
211
Input
405
Total output
390
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
209
Input
547
Total output
537
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
132
Input
427
Total output
409
Reasoning within output