Tencent / hy3
low
95.6%
195 / 204 fixtures · 1 run(s)
36,033 input / 127,486 total output / 119,296 reasoning within output tokens $0.08771152
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-2.9%
Text: 95.6% →
JSON: 92.7%
+2
Gained
JSON pass / text fail
−10
Lost
Text pass / JSON fail
185
Unchanged Pass
Both pass
7
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| merge_conflicts | 91.7% | 66.7% | -25% |
| reflog | 100% | 83.3% | -16.7% |
| git_clean | 83.3% | 91.7% | + 8.3% |
| blame_forensics | 100% | 91.7% | -8.3% |
| worktree_usage | 83.3% | 75% | -8.3% |
| branch_cleanup | 100% | 100% | + 0% |
| cherry_pick | 83.3% | 83.3% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| commit_squash | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_grep | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 100% | 100% | + 0% |
| rebase | 83.3% | 83.3% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
Changed Fixtures (12)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
218
Input
718
Total output
712
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
212
Input
458
Total output
425
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
226
Input
300
Total output
292
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
172
Input
209
Total output
202
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
235
Input
3,155
Total output
3,150
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
207
Input
1,186
Total output
1,181
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
188
Input
347
Total output
340
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
214
Input
423
Total output
418
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
184
Input
263
Total output
258
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
368
Input
643
Total output
638
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
211
Input
257
Total output
224
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
133
Input
331
Total output
325
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
107
Input
347
Total output
341
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
120
Input
614
Total output
607
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
96
Input
309
Total output
306
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
129
Input
403
Total output
398
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
111
Input
350
Total output
365
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
124
Input
318
Total output
313
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
106
Input
304
Total output
297
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
131
Input
491
Total output
398
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
89
Input
328
Total output
325
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
122
Input
478
Total output
427
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
77
Input
262
Total output
276
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
152
Input
358
Total output
324
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
97
Input
1,269
Total output
1,263
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
122
Input
1,760
Total output
1,751
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
94
Input
1,776
Total output
1,899
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
149
Input
984
Total output
963
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
152
Input
504
Total output
486
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
138
Input
499
Total output
477
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
138
Input
402
Total output
391
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
129
Input
286
Total output
278
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
114
Input
279
Total output
272
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
212
Input
888
Total output
862
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
167
Input
655
Total output
631
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
265
Input
3,517
Total output
3,477
Reasoning within output
commit_messages f001
85.7%
Passed
Tokens
107
Input
797
Total output
751
Reasoning within output
commit_messages f002
84.7%
Passed
Tokens
201
Input
679
Total output
667
Reasoning within output
commit_messages f003
91.7%
Passed
Tokens
89
Input
522
Total output
357
Reasoning within output
commit_messages f004
91%
Passed
Tokens
111
Input
398
Total output
333
Reasoning within output
commit_messages f005
91.7%
Passed
Tokens
103
Input
390
Total output
384
Reasoning within output
commit_messages f006
85%
Passed
Tokens
137
Input
768
Total output
760
Reasoning within output
commit_messages f007
88.3%
Passed
Tokens
186
Input
406
Total output
345
Reasoning within output
commit_messages f008
89.3%
Passed
Tokens
74
Input
414
Total output
408
Reasoning within output
commit_messages f009
55%
Passed
Tokens
130
Input
780
Total output
566
Reasoning within output
commit_messages f010
90.3%
Passed
Tokens
268
Input
1,034
Total output
842
Reasoning within output
commit_messages f011
60.7%
Passed
Tokens
144
Input
1,104
Total output
1,088
Reasoning within output
commit_messages f012
89.3%
Passed
Tokens
127
Input
777
Total output
770
Reasoning within output
commit_squash f001
100%
Passed
Tokens
141
Input
549
Total output
535
Reasoning within output
commit_squash f002
100%
Passed
Tokens
117
Input
300
Total output
290
Reasoning within output
commit_squash f003
100%
Passed
Tokens
126
Input
482
Total output
468
Reasoning within output
commit_squash f004
100%
Passed
Tokens
119
Input
552
Total output
539
Reasoning within output
commit_squash f005
100%
Passed
Tokens
113
Input
648
Total output
639
Reasoning within output
commit_squash f006
100%
Passed
Tokens
101
Input
284
Total output
270
Reasoning within output
commit_squash f007
100%
Passed
Tokens
102
Input
469
Total output
455
Reasoning within output
commit_squash f008
100%
Passed
Tokens
116
Input
347
Total output
333
Reasoning within output
commit_squash f009
100%
Passed
Tokens
106
Input
263
Total output
250
Reasoning within output
commit_squash f010
100%
Passed
Tokens
121
Input
224
Total output
207
Reasoning within output
commit_squash f011
100%
Passed
Tokens
133
Input
322
Total output
305
Reasoning within output
commit_squash f012
100%
Passed
Tokens
126
Input
315
Total output
293
Reasoning within output
git_bisect f001
100%
Passed
Tokens
172
Input
436
Total output
430
Reasoning within output
git_bisect f002
100%
Passed
Tokens
193
Input
386
Total output
380
Reasoning within output
git_bisect f003
100%
Passed
Tokens
201
Input
326
Total output
319
Reasoning within output
git_bisect f004
100%
Passed
Tokens
197
Input
457
Total output
451
Reasoning within output
git_bisect f005
100%
Passed
Tokens
197
Input
609
Total output
527
Reasoning within output
git_bisect f006
100%
Passed
Tokens
220
Input
516
Total output
510
Reasoning within output
git_bisect f007
100%
Passed
Tokens
195
Input
327
Total output
320
Reasoning within output
git_bisect f008
100%
Passed
Tokens
199
Input
294
Total output
283
Reasoning within output
git_bisect f009
100%
Passed
Tokens
195
Input
413
Total output
349
Reasoning within output
git_bisect f010
100%
Passed
Tokens
199
Input
386
Total output
378
Reasoning within output
git_bisect f011
100%
Passed
Tokens
189
Input
277
Total output
258
Reasoning within output
git_bisect f012
100%
Passed
Tokens
222
Input
307
Total output
251
Reasoning within output
git_clean f001
100%
Passed
Tokens
53
Input
370
Total output
361
Reasoning within output
git_clean f002
100%
Passed
Tokens
64
Input
378
Total output
372
Reasoning within output
git_clean f003
100%
Passed
Tokens
62
Input
375
Total output
369
Reasoning within output
git_clean f004
66.7%
Failed
Tokens
61
Input
614
Total output
644
Reasoning within output
git_clean f005
100%
Passed
Tokens
53
Input
664
Total output
654
Reasoning within output
git_clean f006
100%
Passed
Tokens
79
Input
1,208
Total output
1,200
Reasoning within output
git_clean f007
100%
Passed
Tokens
75
Input
542
Total output
531
Reasoning within output
git_clean f008
100%
Passed
Tokens
77
Input
138
Total output
130
Reasoning within output
git_clean f009
100%
Passed
Tokens
71
Input
848
Total output
840
Reasoning within output
git_clean f010
100%
Passed
Tokens
68
Input
177
Total output
170
Reasoning within output
git_clean f011
60%
Failed
Tokens
66
Input
1,174
Total output
1,167
Reasoning within output
git_clean f012
100%
Passed
Tokens
69
Input
761
Total output
753
Reasoning within output
git_grep f001
100%
Passed
Tokens
57
Input
117
Total output
112
Reasoning within output
git_grep f002
100%
Passed
Tokens
66
Input
135
Total output
132
Reasoning within output
git_grep f003
100%
Passed
Tokens
91
Input
126
Total output
123
Reasoning within output
git_grep f004
100%
Passed
Tokens
80
Input
96
Total output
89
Reasoning within output
git_grep f005
100%
Passed
Tokens
114
Input
259
Total output
256
Reasoning within output
git_grep f006
100%
Passed
Tokens
45
Input
360
Total output
357
Reasoning within output
git_grep f007
100%
Passed
Tokens
162
Input
957
Total output
954
Reasoning within output
git_grep f008
100%
Passed
Tokens
64
Input
98
Total output
95
Reasoning within output
git_grep f009
100%
Passed
Tokens
58
Input
136
Total output
131
Reasoning within output
git_grep f010
100%
Passed
Tokens
68
Input
396
Total output
393
Reasoning within output
git_grep f011
100%
Passed
Tokens
112
Input
161
Total output
158
Reasoning within output
git_grep f012
100%
Passed
Tokens
69
Input
94
Total output
84
Reasoning within output
git_log_format f001
100%
Passed
Tokens
724
Input
101
Total output
98
Reasoning within output
git_log_format f002
100%
Passed
Tokens
706
Input
226
Total output
217
Reasoning within output
git_log_format f003
100%
Passed
Tokens
569
Input
211
Total output
197
Reasoning within output
git_log_format f004
100%
Passed
Tokens
719
Input
76
Total output
64
Reasoning within output
git_log_format f005
100%
Passed
Tokens
581
Input
252
Total output
197
Reasoning within output
git_log_format f006
100%
Passed
Tokens
720
Input
173
Total output
102
Reasoning within output
git_log_format f007
100%
Passed
Tokens
721
Input
131
Total output
126
Reasoning within output
git_log_format f008
100%
Passed
Tokens
956
Input
99
Total output
96
Reasoning within output
git_log_format f009
100%
Passed
Tokens
588
Input
133
Total output
130
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,091
Input
108
Total output
105
Reasoning within output
git_log_format f011
100%
Passed
Tokens
354
Input
150
Total output
146
Reasoning within output
git_log_format f012
100%
Passed
Tokens
337
Input
103
Total output
94
Reasoning within output
git_show f001
100%
Passed
Tokens
176
Input
103
Total output
97
Reasoning within output
git_show f002
100%
Passed
Tokens
171
Input
461
Total output
457
Reasoning within output
git_show f003
100%
Passed
Tokens
565
Input
132
Total output
124
Reasoning within output
git_show f004
100%
Passed
Tokens
393
Input
157
Total output
149
Reasoning within output
git_show f005
100%
Passed
Tokens
179
Input
293
Total output
295
Reasoning within output
git_show f006
100%
Passed
Tokens
189
Input
198
Total output
195
Reasoning within output
git_show f007
100%
Passed
Tokens
169
Input
209
Total output
203
Reasoning within output
git_show f008
100%
Passed
Tokens
186
Input
148
Total output
122
Reasoning within output
git_show f009
100%
Passed
Tokens
267
Input
230
Total output
227
Reasoning within output
git_show f010
100%
Passed
Tokens
185
Input
167
Total output
164
Reasoning within output
git_show f011
100%
Passed
Tokens
204
Input
164
Total output
160
Reasoning within output
git_show f012
100%
Passed
Tokens
299
Input
168
Total output
165
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
90
Input
983
Total output
1,035
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
110
Input
1,718
Total output
1,489
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
85
Input
2,072
Total output
2,220
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
138
Input
1,169
Total output
1,145
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
141
Input
380
Total output
362
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
125
Input
1,130
Total output
1,108
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
136
Input
443
Total output
424
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
112
Input
452
Total output
444
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
110
Input
540
Total output
533
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
181
Input
762
Total output
749
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
149
Input
335
Total output
311
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
232
Input
946
Total output
906
Reasoning within output
rebase f001
100%
Passed
Tokens
98
Input
1,702
Total output
1,696
Reasoning within output
rebase f002
100%
Passed
Tokens
129
Input
275
Total output
266
Reasoning within output
rebase f003
100%
Passed
Tokens
107
Input
435
Total output
466
Reasoning within output
rebase f004
0%
Failed
Tokens
149
Input
2,621
Total output
2,600
Reasoning within output
rebase f005
100%
Passed
Tokens
144
Input
892
Total output
877
Reasoning within output
rebase f006
100%
Passed
Tokens
137
Input
1,177
Total output
1,156
Reasoning within output
rebase f007
100%
Passed
Tokens
137
Input
437
Total output
426
Reasoning within output
rebase f008
100%
Passed
Tokens
125
Input
285
Total output
306
Reasoning within output
rebase f009
100%
Passed
Tokens
106
Input
530
Total output
523
Reasoning within output
rebase f010
100%
Passed
Tokens
204
Input
1,599
Total output
1,573
Reasoning within output
rebase f011
100%
Passed
Tokens
160
Input
802
Total output
779
Reasoning within output
rebase f012
0%
Failed
Tokens
263
Input
4,585
Total output
4,545
Reasoning within output
reflog f001
100%
Passed
Tokens
203
Input
292
Total output
264
Reasoning within output
reflog f002
100%
Passed
Tokens
210
Input
569
Total output
453
Reasoning within output
reflog f003
100%
Passed
Tokens
179
Input
811
Total output
584
Reasoning within output
reflog f004
100%
Passed
Tokens
280
Input
2,771
Total output
2,122
Reasoning within output
reflog f005
100%
Passed
Tokens
328
Input
1,120
Total output
740
Reasoning within output
reflog f006
100%
Passed
Tokens
223
Input
1,566
Total output
1,362
Reasoning within output
reflog f007
100%
Passed
Tokens
249
Input
1,578
Total output
1,079
Reasoning within output
reflog f008
100%
Passed
Tokens
307
Input
1,647
Total output
1,503
Reasoning within output
reflog f009
100%
Passed
Tokens
274
Input
2,050
Total output
1,476
Reasoning within output
reflog f010
100%
Passed
Tokens
231
Input
2,160
Total output
1,853
Reasoning within output
reflog f011
100%
Passed
Tokens
286
Input
3,756
Total output
2,855
Reasoning within output
reflog f012
100%
Passed
Tokens
277
Input
3,004
Total output
2,647
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
133
Input
137
Total output
130
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
279
Input
275
Total output
144
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
121
Input
171
Total output
164
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
119
Input
332
Total output
280
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
130
Input
212
Total output
191
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
176
Input
224
Total output
192
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
200
Input
327
Total output
247
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
171
Input
526
Total output
505
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
207
Input
506
Total output
415
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
127
Input
175
Total output
142
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
120
Input
690
Total output
612
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
137
Input
217
Total output
198
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
47
Input
89
Total output
79
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
97
Input
680
Total output
669
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
98
Input
841
Total output
818
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
84
Input
317
Total output
312
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
54
Input
429
Total output
402
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
87
Input
1,008
Total output
1,003
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
54
Input
305
Total output
286
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
91
Input
751
Total output
744
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
92
Input
208
Total output
203
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
96
Input
868
Total output
860
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
99
Input
94
Total output
88
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
52
Input
208
Total output
195
Reasoning within output
tag_management f001
100%
Passed
Tokens
61
Input
205
Total output
197
Reasoning within output
tag_management f002
100%
Passed
Tokens
62
Input
348
Total output
292
Reasoning within output
tag_management f003
100%
Passed
Tokens
63
Input
303
Total output
292
Reasoning within output
tag_management f004
100%
Passed
Tokens
71
Input
379
Total output
375
Reasoning within output
tag_management f005
100%
Passed
Tokens
83
Input
349
Total output
294
Reasoning within output
tag_management f006
100%
Passed
Tokens
66
Input
615
Total output
602
Reasoning within output
tag_management f007
100%
Passed
Tokens
69
Input
728
Total output
559
Reasoning within output
tag_management f008
100%
Passed
Tokens
71
Input
1,075
Total output
1,052
Reasoning within output
tag_management f009
100%
Passed
Tokens
75
Input
292
Total output
263
Reasoning within output
tag_management f010
100%
Passed
Tokens
53
Input
192
Total output
183
Reasoning within output
tag_management f011
100%
Passed
Tokens
49
Input
205
Total output
213
Reasoning within output
tag_management f012
100%
Passed
Tokens
89
Input
629
Total output
523
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
131
Input
595
Total output
584
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
134
Input
472
Total output
450
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
194
Input
384
Total output
374
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
191
Input
674
Total output
668
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
126
Input
294
Total output
279
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
134
Input
953
Total output
854
Reasoning within output
worktree_usage f007
0%
Failed
Tokens
126
Input
1,747
Total output
1,722
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
149
Input
860
Total output
807
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
215
Input
594
Total output
588
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
200
Input
258
Total output
241
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
192
Input
340
Total output
330
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
124
Input
205
Total output
190
Reasoning within output