Tencent / hy3
high
96.1%
196 / 204 fixtures · 1 run(s)
35,980 input / 216,319 total output / 210,627 reasoning within output tokens $0.13526066
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-2.4%
Text: 96.1% →
JSON: 93.6%
+1
Gained
JSON pass / text fail
−10
Lost
Text pass / JSON fail
186
Unchanged Pass
Both pass
7
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| rebase | 83.3% | 66.7% | -16.7% |
| blame_forensics | 100% | 91.7% | -8.3% |
| branch_cleanup | 100% | 91.7% | -8.3% |
| cherry_pick | 83.3% | 75% | -8.3% |
| commit_messages | 100% | 100% | + 0% |
| commit_squash | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_clean | 100% | 100% | + 0% |
| git_grep | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 100% | 100% | + 0% |
| merge_conflicts | 83.3% | 83.3% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
| worktree_usage | 83.3% | 83.3% | + 0% |
Changed Fixtures (11)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
218
Input
1,020
Total output
1,116
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
205
Input
444
Total output
438
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
226
Input
148
Total output
140
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
172
Input
638
Total output
655
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
233
Input
6,739
Total output
6,734
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
208
Input
1,633
Total output
1,628
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
188
Input
564
Total output
557
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
212
Input
740
Total output
735
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
180
Input
533
Total output
528
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
381
Input
532
Total output
527
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
211
Input
449
Total output
444
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
129
Input
480
Total output
474
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
109
Input
480
Total output
474
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
119
Input
579
Total output
572
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
98
Input
328
Total output
325
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
136
Input
493
Total output
485
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
108
Input
392
Total output
387
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
124
Input
311
Total output
302
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
103
Input
504
Total output
497
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
126
Input
546
Total output
534
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
86
Input
442
Total output
439
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
122
Input
877
Total output
870
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
77
Input
253
Total output
250
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
157
Input
427
Total output
413
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
98
Input
3,574
Total output
3,568
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
121
Input
5,094
Total output
5,085
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
93
Input
1,162
Total output
1,156
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
149
Input
2,240
Total output
2,219
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
152
Input
782
Total output
764
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
136
Input
1,845
Total output
1,824
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
133
Input
457
Total output
449
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
128
Input
580
Total output
572
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
113
Input
375
Total output
368
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
212
Input
1,515
Total output
1,488
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
167
Input
650
Total output
626
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
267
Input
2,176
Total output
2,136
Reasoning within output
commit_messages f001
95%
Passed
Tokens
107
Input
1,051
Total output
1,046
Reasoning within output
commit_messages f002
86%
Passed
Tokens
201
Input
840
Total output
829
Reasoning within output
commit_messages f003
93.3%
Passed
Tokens
89
Input
832
Total output
821
Reasoning within output
commit_messages f004
93.3%
Passed
Tokens
111
Input
330
Total output
305
Reasoning within output
commit_messages f005
80%
Passed
Tokens
103
Input
434
Total output
429
Reasoning within output
commit_messages f006
91.3%
Passed
Tokens
137
Input
932
Total output
924
Reasoning within output
commit_messages f007
88.3%
Passed
Tokens
186
Input
593
Total output
491
Reasoning within output
commit_messages f008
94.3%
Passed
Tokens
74
Input
587
Total output
581
Reasoning within output
commit_messages f009
86.7%
Passed
Tokens
130
Input
1,122
Total output
888
Reasoning within output
commit_messages f010
94%
Passed
Tokens
268
Input
1,577
Total output
1,312
Reasoning within output
commit_messages f011
86.7%
Passed
Tokens
144
Input
2,371
Total output
2,360
Reasoning within output
commit_messages f012
91.7%
Passed
Tokens
127
Input
1,178
Total output
900
Reasoning within output
commit_squash f001
100%
Passed
Tokens
140
Input
1,133
Total output
1,119
Reasoning within output
commit_squash f002
100%
Passed
Tokens
117
Input
333
Total output
331
Reasoning within output
commit_squash f003
100%
Passed
Tokens
129
Input
517
Total output
503
Reasoning within output
commit_squash f004
100%
Passed
Tokens
117
Input
859
Total output
846
Reasoning within output
commit_squash f005
100%
Passed
Tokens
111
Input
446
Total output
485
Reasoning within output
commit_squash f006
100%
Passed
Tokens
101
Input
422
Total output
441
Reasoning within output
commit_squash f007
100%
Passed
Tokens
100
Input
371
Total output
357
Reasoning within output
commit_squash f008
100%
Passed
Tokens
116
Input
259
Total output
245
Reasoning within output
commit_squash f009
100%
Passed
Tokens
107
Input
753
Total output
740
Reasoning within output
commit_squash f010
100%
Passed
Tokens
121
Input
429
Total output
412
Reasoning within output
commit_squash f011
100%
Passed
Tokens
130
Input
801
Total output
784
Reasoning within output
commit_squash f012
100%
Passed
Tokens
128
Input
442
Total output
420
Reasoning within output
git_bisect f001
100%
Passed
Tokens
176
Input
453
Total output
447
Reasoning within output
git_bisect f002
100%
Passed
Tokens
193
Input
527
Total output
521
Reasoning within output
git_bisect f003
100%
Passed
Tokens
191
Input
476
Total output
471
Reasoning within output
git_bisect f004
100%
Passed
Tokens
199
Input
535
Total output
528
Reasoning within output
git_bisect f005
100%
Passed
Tokens
193
Input
926
Total output
920
Reasoning within output
git_bisect f006
100%
Passed
Tokens
216
Input
445
Total output
438
Reasoning within output
git_bisect f007
100%
Passed
Tokens
193
Input
530
Total output
525
Reasoning within output
git_bisect f008
100%
Passed
Tokens
197
Input
526
Total output
520
Reasoning within output
git_bisect f009
100%
Passed
Tokens
199
Input
570
Total output
565
Reasoning within output
git_bisect f010
100%
Passed
Tokens
201
Input
553
Total output
547
Reasoning within output
git_bisect f011
100%
Passed
Tokens
195
Input
564
Total output
558
Reasoning within output
git_bisect f012
100%
Passed
Tokens
224
Input
521
Total output
515
Reasoning within output
git_clean f001
100%
Passed
Tokens
53
Input
453
Total output
444
Reasoning within output
git_clean f002
100%
Passed
Tokens
64
Input
341
Total output
335
Reasoning within output
git_clean f003
100%
Passed
Tokens
62
Input
367
Total output
361
Reasoning within output
git_clean f004
100%
Passed
Tokens
61
Input
1,189
Total output
1,182
Reasoning within output
git_clean f005
100%
Passed
Tokens
53
Input
636
Total output
630
Reasoning within output
git_clean f006
100%
Passed
Tokens
79
Input
1,906
Total output
1,898
Reasoning within output
git_clean f007
100%
Passed
Tokens
75
Input
516
Total output
505
Reasoning within output
git_clean f008
100%
Passed
Tokens
77
Input
298
Total output
292
Reasoning within output
git_clean f009
100%
Passed
Tokens
71
Input
963
Total output
955
Reasoning within output
git_clean f010
100%
Passed
Tokens
68
Input
966
Total output
960
Reasoning within output
git_clean f011
100%
Passed
Tokens
66
Input
736
Total output
729
Reasoning within output
git_clean f012
100%
Passed
Tokens
69
Input
1,619
Total output
1,610
Reasoning within output
git_grep f001
100%
Passed
Tokens
57
Input
198
Total output
213
Reasoning within output
git_grep f002
100%
Passed
Tokens
69
Input
133
Total output
130
Reasoning within output
git_grep f003
100%
Passed
Tokens
91
Input
130
Total output
135
Reasoning within output
git_grep f004
100%
Passed
Tokens
80
Input
172
Total output
165
Reasoning within output
git_grep f005
100%
Passed
Tokens
114
Input
212
Total output
209
Reasoning within output
git_grep f006
100%
Passed
Tokens
45
Input
386
Total output
383
Reasoning within output
git_grep f007
100%
Passed
Tokens
162
Input
4,114
Total output
4,111
Reasoning within output
git_grep f008
100%
Passed
Tokens
64
Input
152
Total output
149
Reasoning within output
git_grep f009
100%
Passed
Tokens
58
Input
80
Total output
75
Reasoning within output
git_grep f010
100%
Passed
Tokens
68
Input
277
Total output
274
Reasoning within output
git_grep f011
100%
Passed
Tokens
112
Input
242
Total output
235
Reasoning within output
git_grep f012
100%
Passed
Tokens
69
Input
145
Total output
132
Reasoning within output
git_log_format f001
100%
Passed
Tokens
694
Input
95
Total output
84
Reasoning within output
git_log_format f002
100%
Passed
Tokens
708
Input
188
Total output
179
Reasoning within output
git_log_format f003
100%
Passed
Tokens
550
Input
261
Total output
250
Reasoning within output
git_log_format f004
100%
Passed
Tokens
736
Input
131
Total output
128
Reasoning within output
git_log_format f005
100%
Passed
Tokens
581
Input
822
Total output
815
Reasoning within output
git_log_format f006
100%
Passed
Tokens
720
Input
225
Total output
222
Reasoning within output
git_log_format f007
100%
Passed
Tokens
742
Input
73
Total output
66
Reasoning within output
git_log_format f008
100%
Passed
Tokens
969
Input
107
Total output
104
Reasoning within output
git_log_format f009
100%
Passed
Tokens
585
Input
100
Total output
97
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,049
Input
94
Total output
91
Reasoning within output
git_log_format f011
100%
Passed
Tokens
365
Input
127
Total output
123
Reasoning within output
git_log_format f012
100%
Passed
Tokens
337
Input
102
Total output
99
Reasoning within output
git_show f001
100%
Passed
Tokens
173
Input
156
Total output
150
Reasoning within output
git_show f002
100%
Passed
Tokens
173
Input
884
Total output
880
Reasoning within output
git_show f003
100%
Passed
Tokens
575
Input
239
Total output
231
Reasoning within output
git_show f004
100%
Passed
Tokens
391
Input
150
Total output
142
Reasoning within output
git_show f005
100%
Passed
Tokens
176
Input
543
Total output
593
Reasoning within output
git_show f006
100%
Passed
Tokens
187
Input
221
Total output
218
Reasoning within output
git_show f007
100%
Passed
Tokens
169
Input
208
Total output
202
Reasoning within output
git_show f008
100%
Passed
Tokens
191
Input
145
Total output
81
Reasoning within output
git_show f009
100%
Passed
Tokens
272
Input
369
Total output
366
Reasoning within output
git_show f010
100%
Passed
Tokens
178
Input
268
Total output
265
Reasoning within output
git_show f011
100%
Passed
Tokens
205
Input
107
Total output
103
Reasoning within output
git_show f012
100%
Passed
Tokens
297
Input
171
Total output
168
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
90
Input
5,081
Total output
5,075
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
110
Input
1,491
Total output
1,374
Reasoning within output
merge_conflicts f003
0%
Failed
Tokens
85
Input
3,134
Total output
3,124
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
138
Input
6,211
Total output
6,187
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
141
Input
544
Total output
526
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
125
Input
2,040
Total output
1,940
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
136
Input
346
Total output
335
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
112
Input
428
Total output
420
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
110
Input
389
Total output
382
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
181
Input
1,744
Total output
1,717
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
149
Input
294
Total output
270
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
232
Input
3,184
Total output
3,144
Reasoning within output
rebase f001
100%
Passed
Tokens
101
Input
2,422
Total output
2,416
Reasoning within output
rebase f002
100%
Passed
Tokens
129
Input
789
Total output
780
Reasoning within output
rebase f003
100%
Passed
Tokens
108
Input
695
Total output
690
Reasoning within output
rebase f004
0%
Failed
Tokens
149
Input
8,451
Total output
8,430
Reasoning within output
rebase f005
100%
Passed
Tokens
144
Input
1,052
Total output
1,037
Reasoning within output
rebase f006
100%
Passed
Tokens
137
Input
2,482
Total output
2,461
Reasoning within output
rebase f007
100%
Passed
Tokens
137
Input
433
Total output
422
Reasoning within output
rebase f008
100%
Passed
Tokens
124
Input
323
Total output
315
Reasoning within output
rebase f009
100%
Passed
Tokens
106
Input
791
Total output
784
Reasoning within output
rebase f010
100%
Passed
Tokens
202
Input
2,147
Total output
2,121
Reasoning within output
rebase f011
100%
Passed
Tokens
159
Input
1,074
Total output
1,051
Reasoning within output
rebase f012
0%
Failed
Tokens
259
Input
6,235
Total output
6,195
Reasoning within output
reflog f001
100%
Passed
Tokens
207
Input
327
Total output
301
Reasoning within output
reflog f002
100%
Passed
Tokens
205
Input
606
Total output
500
Reasoning within output
reflog f003
100%
Passed
Tokens
186
Input
462
Total output
296
Reasoning within output
reflog f004
100%
Passed
Tokens
292
Input
3,212
Total output
2,973
Reasoning within output
reflog f005
100%
Passed
Tokens
323
Input
992
Total output
896
Reasoning within output
reflog f006
100%
Passed
Tokens
227
Input
678
Total output
473
Reasoning within output
reflog f007
100%
Passed
Tokens
233
Input
1,545
Total output
1,401
Reasoning within output
reflog f008
100%
Passed
Tokens
294
Input
1,406
Total output
1,157
Reasoning within output
reflog f009
100%
Passed
Tokens
260
Input
7,308
Total output
7,089
Reasoning within output
reflog f010
100%
Passed
Tokens
240
Input
1,358
Total output
929
Reasoning within output
reflog f011
100%
Passed
Tokens
277
Input
5,667
Total output
5,401
Reasoning within output
reflog f012
100%
Passed
Tokens
270
Input
4,135
Total output
3,745
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
133
Input
151
Total output
143
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
279
Input
350
Total output
233
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
121
Input
147
Total output
139
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
119
Input
241
Total output
216
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
131
Input
170
Total output
149
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
176
Input
179
Total output
150
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
204
Input
240
Total output
214
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
171
Input
363
Total output
344
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
207
Input
328
Total output
273
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
127
Input
176
Total output
158
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
119
Input
2,338
Total output
2,273
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
137
Input
182
Total output
108
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
47
Input
260
Total output
250
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
95
Input
1,324
Total output
1,313
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
102
Input
9,488
Total output
9,465
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
91
Input
307
Total output
345
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
54
Input
1,841
Total output
1,814
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
85
Input
1,045
Total output
1,127
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
54
Input
549
Total output
530
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
95
Input
1,170
Total output
1,229
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
92
Input
522
Total output
556
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
96
Input
1,089
Total output
1,082
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
101
Input
188
Total output
182
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
52
Input
426
Total output
417
Reasoning within output
tag_management f001
100%
Passed
Tokens
60
Input
205
Total output
197
Reasoning within output
tag_management f002
100%
Passed
Tokens
58
Input
479
Total output
460
Reasoning within output
tag_management f003
100%
Passed
Tokens
64
Input
575
Total output
526
Reasoning within output
tag_management f004
100%
Passed
Tokens
67
Input
150
Total output
146
Reasoning within output
tag_management f005
100%
Passed
Tokens
79
Input
277
Total output
267
Reasoning within output
tag_management f006
100%
Passed
Tokens
68
Input
1,613
Total output
1,592
Reasoning within output
tag_management f007
100%
Passed
Tokens
68
Input
2,195
Total output
2,182
Reasoning within output
tag_management f008
100%
Passed
Tokens
73
Input
1,144
Total output
1,119
Reasoning within output
tag_management f009
100%
Passed
Tokens
73
Input
666
Total output
648
Reasoning within output
tag_management f010
100%
Passed
Tokens
52
Input
168
Total output
159
Reasoning within output
tag_management f011
100%
Passed
Tokens
52
Input
249
Total output
242
Reasoning within output
tag_management f012
100%
Passed
Tokens
86
Input
1,427
Total output
1,221
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
134
Input
790
Total output
779
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
137
Input
4,169
Total output
4,145
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
193
Input
1,449
Total output
1,439
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
194
Input
290
Total output
284
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
125
Input
486
Total output
471
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
126
Input
1,994
Total output
1,977
Reasoning within output
worktree_usage f007
0%
Failed
Tokens
125
Input
1,611
Total output
1,586
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
154
Input
5,439
Total output
5,386
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
226
Input
101
Total output
95
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
203
Input
385
Total output
368
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
198
Input
148
Total output
138
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
121
Input
502
Total output
461
Reasoning within output