Tencent / hy3
medium
95.6%
195 / 204 fixtures · 1 run(s)
35,995 input / 131,418 total output / 124,996 reasoning within output tokens $0.08921480
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-0.5%
Text: 95.6% →
JSON: 95.1%
+2
Gained
JSON pass / text fail
−3
Lost
Text pass / JSON fail
192
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% | 75% | -16.7% |
| blame_forensics | 91.7% | 100% | + 8.3% |
| cherry_pick | 75% | 83.3% | + 8.3% |
| rebase | 83.3% | 75% | -8.3% |
| branch_cleanup | 100% | 100% | + 0% |
| 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% |
| 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 (5)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
219
Input
649
Total output
690
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
205
Input
537
Total output
531
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
226
Input
263
Total output
255
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
174
Input
210
Total output
224
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
234
Input
3,656
Total output
3,648
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
207
Input
1,303
Total output
1,298
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
191
Input
313
Total output
306
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
213
Input
726
Total output
749
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
180
Input
255
Total output
250
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
380
Input
603
Total output
560
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
213
Input
187
Total output
182
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
133
Input
372
Total output
378
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
112
Input
357
Total output
351
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
118
Input
425
Total output
418
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
95
Input
280
Total output
277
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
130
Input
351
Total output
336
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
108
Input
388
Total output
383
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
127
Input
256
Total output
247
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
109
Input
333
Total output
326
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
130
Input
442
Total output
373
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
86
Input
420
Total output
417
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
121
Input
468
Total output
461
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
76
Input
238
Total output
235
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
154
Input
357
Total output
343
Reasoning within output
cherry_pick f001
0%
Failed
Tokens
99
Input
1,272
Total output
1,272
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
122
Input
1,549
Total output
1,540
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
93
Input
815
Total output
809
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
150
Input
1,789
Total output
1,768
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
153
Input
448
Total output
460
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
136
Input
1,152
Total output
1,015
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
136
Input
336
Total output
299
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
129
Input
204
Total output
196
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
114
Input
367
Total output
386
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
214
Input
605
Total output
578
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
168
Input
671
Total output
647
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
265
Input
1,543
Total output
1,503
Reasoning within output
commit_messages f001
93.3%
Passed
Tokens
107
Input
590
Total output
585
Reasoning within output
commit_messages f002
84%
Passed
Tokens
201
Input
890
Total output
879
Reasoning within output
commit_messages f003
93.3%
Passed
Tokens
89
Input
495
Total output
484
Reasoning within output
commit_messages f004
96%
Passed
Tokens
111
Input
351
Total output
346
Reasoning within output
commit_messages f005
90%
Passed
Tokens
103
Input
360
Total output
323
Reasoning within output
commit_messages f006
93.7%
Passed
Tokens
137
Input
577
Total output
569
Reasoning within output
commit_messages f007
91%
Passed
Tokens
186
Input
569
Total output
561
Reasoning within output
commit_messages f008
93.3%
Passed
Tokens
74
Input
357
Total output
351
Reasoning within output
commit_messages f009
83.3%
Passed
Tokens
130
Input
498
Total output
489
Reasoning within output
commit_messages f010
96%
Passed
Tokens
268
Input
644
Total output
633
Reasoning within output
commit_messages f011
62.7%
Passed
Tokens
144
Input
1,647
Total output
1,632
Reasoning within output
commit_messages f012
88.3%
Passed
Tokens
127
Input
460
Total output
453
Reasoning within output
commit_squash f001
100%
Passed
Tokens
140
Input
891
Total output
877
Reasoning within output
commit_squash f002
100%
Passed
Tokens
118
Input
313
Total output
303
Reasoning within output
commit_squash f003
100%
Passed
Tokens
131
Input
813
Total output
799
Reasoning within output
commit_squash f004
100%
Passed
Tokens
119
Input
625
Total output
612
Reasoning within output
commit_squash f005
100%
Passed
Tokens
113
Input
450
Total output
441
Reasoning within output
commit_squash f006
100%
Passed
Tokens
104
Input
262
Total output
251
Reasoning within output
commit_squash f007
100%
Passed
Tokens
102
Input
390
Total output
376
Reasoning within output
commit_squash f008
100%
Passed
Tokens
116
Input
508
Total output
494
Reasoning within output
commit_squash f009
100%
Passed
Tokens
108
Input
336
Total output
323
Reasoning within output
commit_squash f010
100%
Passed
Tokens
120
Input
254
Total output
237
Reasoning within output
commit_squash f011
100%
Passed
Tokens
133
Input
367
Total output
319
Reasoning within output
commit_squash f012
100%
Passed
Tokens
127
Input
243
Total output
195
Reasoning within output
git_bisect f001
100%
Passed
Tokens
180
Input
263
Total output
257
Reasoning within output
git_bisect f002
100%
Passed
Tokens
197
Input
446
Total output
440
Reasoning within output
git_bisect f003
100%
Passed
Tokens
197
Input
311
Total output
306
Reasoning within output
git_bisect f004
100%
Passed
Tokens
199
Input
312
Total output
301
Reasoning within output
git_bisect f005
100%
Passed
Tokens
189
Input
1,735
Total output
1,730
Reasoning within output
git_bisect f006
100%
Passed
Tokens
222
Input
437
Total output
430
Reasoning within output
git_bisect f007
100%
Passed
Tokens
203
Input
340
Total output
333
Reasoning within output
git_bisect f008
100%
Passed
Tokens
199
Input
406
Total output
400
Reasoning within output
git_bisect f009
100%
Passed
Tokens
193
Input
301
Total output
295
Reasoning within output
git_bisect f010
100%
Passed
Tokens
195
Input
306
Total output
300
Reasoning within output
git_bisect f011
100%
Passed
Tokens
189
Input
245
Total output
239
Reasoning within output
git_bisect f012
100%
Passed
Tokens
214
Input
399
Total output
340
Reasoning within output
git_clean f001
100%
Passed
Tokens
53
Input
620
Total output
611
Reasoning within output
git_clean f002
100%
Passed
Tokens
64
Input
203
Total output
197
Reasoning within output
git_clean f003
100%
Passed
Tokens
62
Input
430
Total output
452
Reasoning within output
git_clean f004
100%
Passed
Tokens
61
Input
746
Total output
752
Reasoning within output
git_clean f005
100%
Passed
Tokens
53
Input
677
Total output
716
Reasoning within output
git_clean f006
100%
Passed
Tokens
79
Input
933
Total output
925
Reasoning within output
git_clean f007
100%
Passed
Tokens
75
Input
433
Total output
422
Reasoning within output
git_clean f008
100%
Passed
Tokens
77
Input
382
Total output
376
Reasoning within output
git_clean f009
100%
Passed
Tokens
71
Input
609
Total output
601
Reasoning within output
git_clean f010
100%
Passed
Tokens
68
Input
367
Total output
361
Reasoning within output
git_clean f011
100%
Passed
Tokens
66
Input
615
Total output
608
Reasoning within output
git_clean f012
100%
Passed
Tokens
69
Input
821
Total output
812
Reasoning within output
git_grep f001
100%
Passed
Tokens
57
Input
136
Total output
131
Reasoning within output
git_grep f002
100%
Passed
Tokens
66
Input
157
Total output
154
Reasoning within output
git_grep f003
100%
Passed
Tokens
91
Input
149
Total output
146
Reasoning within output
git_grep f004
100%
Passed
Tokens
80
Input
145
Total output
128
Reasoning within output
git_grep f005
100%
Passed
Tokens
114
Input
196
Total output
193
Reasoning within output
git_grep f006
100%
Passed
Tokens
45
Input
437
Total output
458
Reasoning within output
git_grep f007
100%
Passed
Tokens
162
Input
843
Total output
840
Reasoning within output
git_grep f008
100%
Passed
Tokens
64
Input
149
Total output
160
Reasoning within output
git_grep f009
100%
Passed
Tokens
58
Input
112
Total output
101
Reasoning within output
git_grep f010
100%
Passed
Tokens
68
Input
386
Total output
383
Reasoning within output
git_grep f011
100%
Passed
Tokens
112
Input
189
Total output
186
Reasoning within output
git_grep f012
100%
Passed
Tokens
69
Input
112
Total output
102
Reasoning within output
git_log_format f001
100%
Passed
Tokens
724
Input
98
Total output
95
Reasoning within output
git_log_format f002
100%
Passed
Tokens
707
Input
215
Total output
206
Reasoning within output
git_log_format f003
100%
Passed
Tokens
566
Input
205
Total output
194
Reasoning within output
git_log_format f004
100%
Passed
Tokens
712
Input
119
Total output
84
Reasoning within output
git_log_format f005
100%
Passed
Tokens
581
Input
319
Total output
312
Reasoning within output
git_log_format f006
100%
Passed
Tokens
720
Input
200
Total output
197
Reasoning within output
git_log_format f007
100%
Passed
Tokens
715
Input
141
Total output
136
Reasoning within output
git_log_format f008
100%
Passed
Tokens
949
Input
91
Total output
75
Reasoning within output
git_log_format f009
100%
Passed
Tokens
593
Input
126
Total output
118
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,064
Input
125
Total output
122
Reasoning within output
git_log_format f011
100%
Passed
Tokens
344
Input
162
Total output
160
Reasoning within output
git_log_format f012
100%
Passed
Tokens
332
Input
104
Total output
101
Reasoning within output
git_show f001
100%
Passed
Tokens
172
Input
170
Total output
164
Reasoning within output
git_show f002
100%
Passed
Tokens
172
Input
430
Total output
426
Reasoning within output
git_show f003
100%
Passed
Tokens
569
Input
312
Total output
304
Reasoning within output
git_show f004
100%
Passed
Tokens
387
Input
226
Total output
218
Reasoning within output
git_show f005
100%
Passed
Tokens
176
Input
406
Total output
420
Reasoning within output
git_show f006
100%
Passed
Tokens
182
Input
198
Total output
195
Reasoning within output
git_show f007
100%
Passed
Tokens
169
Input
190
Total output
158
Reasoning within output
git_show f008
100%
Passed
Tokens
188
Input
230
Total output
144
Reasoning within output
git_show f009
100%
Passed
Tokens
265
Input
252
Total output
249
Reasoning within output
git_show f010
100%
Passed
Tokens
179
Input
137
Total output
134
Reasoning within output
git_show f011
100%
Passed
Tokens
204
Input
177
Total output
173
Reasoning within output
git_show f012
100%
Passed
Tokens
295
Input
150
Total output
147
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
90
Input
2,295
Total output
2,424
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
110
Input
791
Total output
726
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
85
Input
1,214
Total output
1,285
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
138
Input
3,792
Total output
3,763
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
141
Input
739
Total output
721
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
125
Input
712
Total output
690
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
136
Input
464
Total output
453
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
112
Input
321
Total output
313
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
110
Input
574
Total output
567
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
181
Input
1,112
Total output
1,086
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
149
Input
558
Total output
535
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
232
Input
807
Total output
767
Reasoning within output
rebase f001
100%
Passed
Tokens
100
Input
1,554
Total output
1,548
Reasoning within output
rebase f002
100%
Passed
Tokens
129
Input
674
Total output
665
Reasoning within output
rebase f003
100%
Passed
Tokens
106
Input
502
Total output
497
Reasoning within output
rebase f004
0%
Failed
Tokens
151
Input
1,805
Total output
1,784
Reasoning within output
rebase f005
100%
Passed
Tokens
146
Input
890
Total output
875
Reasoning within output
rebase f006
100%
Passed
Tokens
136
Input
1,193
Total output
1,057
Reasoning within output
rebase f007
100%
Passed
Tokens
137
Input
523
Total output
496
Reasoning within output
rebase f008
100%
Passed
Tokens
124
Input
418
Total output
410
Reasoning within output
rebase f009
100%
Passed
Tokens
108
Input
428
Total output
435
Reasoning within output
rebase f010
100%
Passed
Tokens
206
Input
1,257
Total output
1,262
Reasoning within output
rebase f011
100%
Passed
Tokens
160
Input
513
Total output
490
Reasoning within output
rebase f012
0%
Failed
Tokens
261
Input
3,211
Total output
3,171
Reasoning within output
reflog f001
100%
Passed
Tokens
212
Input
292
Total output
267
Reasoning within output
reflog f002
100%
Passed
Tokens
196
Input
880
Total output
772
Reasoning within output
reflog f003
100%
Passed
Tokens
180
Input
1,299
Total output
882
Reasoning within output
reflog f004
100%
Passed
Tokens
278
Input
2,336
Total output
1,962
Reasoning within output
reflog f005
100%
Passed
Tokens
326
Input
1,986
Total output
1,804
Reasoning within output
reflog f006
100%
Passed
Tokens
226
Input
1,472
Total output
1,198
Reasoning within output
reflog f007
100%
Passed
Tokens
242
Input
2,007
Total output
1,860
Reasoning within output
reflog f008
100%
Passed
Tokens
325
Input
1,364
Total output
1,230
Reasoning within output
reflog f009
100%
Passed
Tokens
280
Input
2,518
Total output
1,874
Reasoning within output
reflog f010
100%
Passed
Tokens
242
Input
1,400
Total output
1,149
Reasoning within output
reflog f011
100%
Passed
Tokens
277
Input
3,219
Total output
2,510
Reasoning within output
reflog f012
100%
Passed
Tokens
278
Input
3,551
Total output
3,101
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
135
Input
172
Total output
156
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
279
Input
311
Total output
291
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
121
Input
192
Total output
174
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
119
Input
381
Total output
348
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
128
Input
288
Total output
267
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
176
Input
243
Total output
169
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
200
Input
371
Total output
352
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
171
Input
1,045
Total output
1,005
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
207
Input
471
Total output
376
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
127
Input
265
Total output
180
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
118
Input
819
Total output
748
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
137
Input
256
Total output
235
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
47
Input
150
Total output
140
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
99
Input
673
Total output
662
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
104
Input
1,450
Total output
1,417
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
93
Input
393
Total output
388
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
54
Input
628
Total output
601
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
89
Input
722
Total output
809
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
54
Input
333
Total output
314
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
93
Input
555
Total output
548
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
89
Input
286
Total output
281
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
98
Input
768
Total output
760
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
97
Input
192
Total output
186
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
52
Input
169
Total output
156
Reasoning within output
tag_management f001
100%
Passed
Tokens
61
Input
99
Total output
91
Reasoning within output
tag_management f002
100%
Passed
Tokens
60
Input
146
Total output
127
Reasoning within output
tag_management f003
100%
Passed
Tokens
67
Input
410
Total output
399
Reasoning within output
tag_management f004
100%
Passed
Tokens
68
Input
269
Total output
265
Reasoning within output
tag_management f005
100%
Passed
Tokens
82
Input
199
Total output
189
Reasoning within output
tag_management f006
100%
Passed
Tokens
69
Input
303
Total output
287
Reasoning within output
tag_management f007
100%
Passed
Tokens
67
Input
1,314
Total output
1,050
Reasoning within output
tag_management f008
100%
Passed
Tokens
74
Input
987
Total output
962
Reasoning within output
tag_management f009
100%
Passed
Tokens
76
Input
126
Total output
108
Reasoning within output
tag_management f010
100%
Passed
Tokens
51
Input
150
Total output
141
Reasoning within output
tag_management f011
100%
Passed
Tokens
54
Input
273
Total output
266
Reasoning within output
tag_management f012
100%
Passed
Tokens
88
Input
843
Total output
832
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
132
Input
1,684
Total output
1,673
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
133
Input
999
Total output
977
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
195
Input
368
Total output
353
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
187
Input
949
Total output
943
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
128
Input
302
Total output
287
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
124
Input
491
Total output
474
Reasoning within output
worktree_usage f007
0%
Failed
Tokens
126
Input
1,588
Total output
1,563
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
152
Input
1,787
Total output
1,740
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
219
Input
317
Total output
311
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
193
Input
279
Total output
264
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
191
Input
315
Total output
301
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
122
Input
255
Total output
240
Reasoning within output