Inception / mercury-2.5
low
87.3%
178 / 204 fixtures · 1 run(s)
37,692 input / 54,792 total output / 50,817 reasoning within output tokens $0.00972648
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-1%
Text: 87.3% →
JSON: 86.3%
+15
Gained
JSON pass / text fail
−17
Lost
Text pass / JSON fail
161
Unchanged Pass
Both pass
11
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| blame_forensics | 58.3% | 100% | + 41.7% |
| commit_squash | 50% | 25% | -25% |
| git_clean | 100% | 75% | -25% |
| cherry_pick | 58.3% | 75% | + 16.7% |
| submodule_usage | 100% | 83.3% | -16.7% |
| branch_cleanup | 83.3% | 75% | -8.3% |
| git_grep | 91.7% | 100% | + 8.3% |
| git_show | 100% | 91.7% | -8.3% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| merge_conflicts | 75% | 75% | + 0% |
| rebase | 75% | 75% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
| worktree_usage | 91.7% | 91.7% | + 0% |
Changed Fixtures (32)
f001 +gain f002 +gain f004 +gain f006 +gain f010 +gain f001 +gain f002 +gain f003 -loss f009 -loss f011 -loss f001 +gain f003 +gain f004 -loss f006 +gain f002 -loss f007 -loss f008 -loss f011 -loss f012 +gain f001 -loss f004 -loss f011 -loss f004 +gain f002 -loss f001 +gain f006 -loss f005 -loss f006 +gain f003 -loss f008 -loss f005 -loss f008 +gain
Fixture Gallery (204)
blame_forensics f001
0%
Failed
Tokens
244
Input
265
Total output
256
Reasoning within output
blame_forensics f002
0%
Failed
Tokens
237
Input
264
Total output
251
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
265
Input
278
Total output
266
Reasoning within output
blame_forensics f004
0%
Failed
Tokens
190
Input
277
Total output
264
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
253
Input
259
Total output
249
Reasoning within output
blame_forensics f006
0%
Failed
Tokens
221
Input
257
Total output
247
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
201
Input
256
Total output
247
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
242
Input
259
Total output
249
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
198
Input
255
Total output
246
Reasoning within output
blame_forensics f010
0%
Failed
Tokens
430
Input
261
Total output
247
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
237
Input
249
Total output
239
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
136
Input
258
Total output
249
Reasoning within output
branch_cleanup f001
100%
Failed
Tokens
97
Input
261
Total output
250
Reasoning within output
branch_cleanup f002
100%
Failed
Tokens
111
Input
253
Total output
238
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
90
Input
255
Total output
246
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
123
Input
261
Total output
253
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
100
Input
249
Total output
240
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
125
Input
259
Total output
248
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
101
Input
262
Total output
250
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
117
Input
253
Total output
238
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
75
Input
256
Total output
251
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
113
Input
269
Total output
258
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
61
Input
252
Total output
248
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
149
Input
256
Total output
244
Reasoning within output
cherry_pick f001
0%
Failed
Tokens
84
Input
243
Total output
237
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
104
Input
263
Total output
254
Reasoning within output
cherry_pick f003
0%
Failed
Tokens
81
Input
274
Total output
263
Reasoning within output
cherry_pick f004
100%
Passed
Tokens
144
Input
274
Total output
249
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
136
Input
281
Total output
261
Reasoning within output
cherry_pick f006
0%
Failed
Tokens
132
Input
290
Total output
260
Reasoning within output
cherry_pick f007
0%
Failed
Tokens
118
Input
247
Total output
231
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
114
Input
272
Total output
260
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
96
Input
259
Total output
247
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
208
Input
274
Total output
246
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
153
Input
281
Total output
255
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
264
Input
295
Total output
250
Reasoning within output
commit_messages f001
92.5%
Passed
Tokens
103
Input
268
Total output
259
Reasoning within output
commit_messages f002
90%
Passed
Tokens
210
Input
260
Total output
252
Reasoning within output
commit_messages f003
96%
Passed
Tokens
73
Input
256
Total output
246
Reasoning within output
commit_messages f004
92%
Passed
Tokens
108
Input
249
Total output
244
Reasoning within output
commit_messages f005
92.5%
Passed
Tokens
92
Input
259
Total output
252
Reasoning within output
commit_messages f006
93.5%
Passed
Tokens
139
Input
251
Total output
242
Reasoning within output
commit_messages f007
80%
Passed
Tokens
184
Input
259
Total output
251
Reasoning within output
commit_messages f008
89.5%
Passed
Tokens
67
Input
271
Total output
261
Reasoning within output
commit_messages f009
87%
Passed
Tokens
117
Input
253
Total output
244
Reasoning within output
commit_messages f010
90%
Passed
Tokens
279
Input
261
Total output
252
Reasoning within output
commit_messages f011
89%
Passed
Tokens
135
Input
260
Total output
251
Reasoning within output
commit_messages f012
50%
Passed
Tokens
117
Input
254
Total output
245
Reasoning within output
commit_squash f001
0%
Failed
Tokens
128
Input
283
Total output
258
Reasoning within output
commit_squash f002
100%
Passed
Tokens
105
Input
250
Total output
236
Reasoning within output
commit_squash f003
0%
Failed
Tokens
117
Input
283
Total output
258
Reasoning within output
commit_squash f004
100%
Failed
Tokens
110
Input
279
Total output
262
Reasoning within output
commit_squash f005
100%
Passed
Tokens
109
Input
262
Total output
251
Reasoning within output
commit_squash f006
0%
Failed
Tokens
90
Input
273
Total output
245
Reasoning within output
commit_squash f007
100%
Passed
Tokens
96
Input
276
Total output
262
Reasoning within output
commit_squash f008
100%
Passed
Tokens
107
Input
256
Total output
244
Reasoning within output
commit_squash f009
0%
Failed
Tokens
100
Input
276
Total output
253
Reasoning within output
commit_squash f010
100%
Passed
Tokens
116
Input
271
Total output
254
Reasoning within output
commit_squash f011
100%
Passed
Tokens
119
Input
260
Total output
245
Reasoning within output
commit_squash f012
0%
Failed
Tokens
123
Input
291
Total output
251
Reasoning within output
git_bisect f001
100%
Passed
Tokens
177
Input
258
Total output
247
Reasoning within output
git_bisect f002
100%
Passed
Tokens
201
Input
255
Total output
244
Reasoning within output
git_bisect f003
100%
Passed
Tokens
201
Input
260
Total output
249
Reasoning within output
git_bisect f004
100%
Passed
Tokens
199
Input
260
Total output
251
Reasoning within output
git_bisect f005
100%
Passed
Tokens
201
Input
257
Total output
248
Reasoning within output
git_bisect f006
100%
Passed
Tokens
236
Input
263
Total output
252
Reasoning within output
git_bisect f007
100%
Passed
Tokens
202
Input
259
Total output
248
Reasoning within output
git_bisect f008
100%
Passed
Tokens
202
Input
255
Total output
244
Reasoning within output
git_bisect f009
100%
Passed
Tokens
195
Input
255
Total output
245
Reasoning within output
git_bisect f010
100%
Passed
Tokens
201
Input
253
Total output
244
Reasoning within output
git_bisect f011
100%
Passed
Tokens
202
Input
253
Total output
241
Reasoning within output
git_bisect f012
100%
Passed
Tokens
225
Input
252
Total output
242
Reasoning within output
git_clean f001
100%
Passed
Tokens
41
Input
252
Total output
242
Reasoning within output
git_clean f002
100%
Passed
Tokens
52
Input
266
Total output
256
Reasoning within output
git_clean f003
100%
Passed
Tokens
52
Input
266
Total output
256
Reasoning within output
git_clean f004
100%
Passed
Tokens
48
Input
273
Total output
264
Reasoning within output
git_clean f005
100%
Passed
Tokens
41
Input
267
Total output
257
Reasoning within output
git_clean f006
100%
Passed
Tokens
64
Input
256
Total output
246
Reasoning within output
git_clean f007
100%
Passed
Tokens
55
Input
250
Total output
235
Reasoning within output
git_clean f008
100%
Passed
Tokens
69
Input
263
Total output
255
Reasoning within output
git_clean f009
100%
Passed
Tokens
60
Input
267
Total output
258
Reasoning within output
git_clean f010
100%
Passed
Tokens
53
Input
259
Total output
251
Reasoning within output
git_clean f011
100%
Passed
Tokens
52
Input
249
Total output
242
Reasoning within output
git_clean f012
100%
Passed
Tokens
53
Input
248
Total output
239
Reasoning within output
git_grep f001
100%
Passed
Tokens
41
Input
258
Total output
250
Reasoning within output
git_grep f002
100%
Passed
Tokens
55
Input
268
Total output
263
Reasoning within output
git_grep f003
100%
Passed
Tokens
76
Input
265
Total output
260
Reasoning within output
git_grep f004
0%
Failed
Tokens
63
Input
250
Total output
241
Reasoning within output
git_grep f005
100%
Passed
Tokens
103
Input
252
Total output
247
Reasoning within output
git_grep f006
100%
Passed
Tokens
30
Input
259
Total output
253
Reasoning within output
git_grep f007
100%
Passed
Tokens
156
Input
259
Total output
249
Reasoning within output
git_grep f008
100%
Passed
Tokens
45
Input
247
Total output
243
Reasoning within output
git_grep f009
100%
Passed
Tokens
42
Input
247
Total output
239
Reasoning within output
git_grep f010
100%
Passed
Tokens
52
Input
266
Total output
261
Reasoning within output
git_grep f011
100%
Passed
Tokens
98
Input
252
Total output
242
Reasoning within output
git_grep f012
100%
Passed
Tokens
52
Input
252
Total output
237
Reasoning within output
git_log_format f001
100%
Passed
Tokens
869
Input
245
Total output
240
Reasoning within output
git_log_format f002
100%
Passed
Tokens
876
Input
270
Total output
261
Reasoning within output
git_log_format f003
100%
Passed
Tokens
692
Input
253
Total output
243
Reasoning within output
git_log_format f004
100%
Passed
Tokens
871
Input
254
Total output
244
Reasoning within output
git_log_format f005
100%
Passed
Tokens
693
Input
252
Total output
243
Reasoning within output
git_log_format f006
100%
Passed
Tokens
874
Input
253
Total output
248
Reasoning within output
git_log_format f007
100%
Passed
Tokens
878
Input
267
Total output
257
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,168
Input
259
Total output
255
Reasoning within output
git_log_format f009
100%
Passed
Tokens
681
Input
242
Total output
233
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,394
Input
263
Total output
259
Reasoning within output
git_log_format f011
100%
Passed
Tokens
411
Input
250
Total output
242
Reasoning within output
git_log_format f012
100%
Passed
Tokens
392
Input
258
Total output
253
Reasoning within output
git_show f001
100%
Passed
Tokens
184
Input
271
Total output
262
Reasoning within output
git_show f002
100%
Passed
Tokens
185
Input
263
Total output
256
Reasoning within output
git_show f003
100%
Passed
Tokens
657
Input
255
Total output
242
Reasoning within output
git_show f004
100%
Passed
Tokens
457
Input
258
Total output
247
Reasoning within output
git_show f005
100%
Passed
Tokens
192
Input
260
Total output
255
Reasoning within output
git_show f006
100%
Passed
Tokens
193
Input
261
Total output
257
Reasoning within output
git_show f007
100%
Passed
Tokens
185
Input
267
Total output
258
Reasoning within output
git_show f008
100%
Passed
Tokens
191
Input
294
Total output
257
Reasoning within output
git_show f009
100%
Passed
Tokens
309
Input
270
Total output
264
Reasoning within output
git_show f010
100%
Passed
Tokens
177
Input
261
Total output
257
Reasoning within output
git_show f011
100%
Passed
Tokens
211
Input
247
Total output
237
Reasoning within output
git_show f012
100%
Passed
Tokens
323
Input
249
Total output
239
Reasoning within output
merge_conflicts f001
0%
Failed
Tokens
72
Input
252
Total output
246
Reasoning within output
merge_conflicts f002
0%
Failed
Tokens
93
Input
259
Total output
250
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
66
Input
247
Total output
237
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
130
Input
268
Total output
244
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
125
Input
269
Total output
245
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
119
Input
279
Total output
249
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
119
Input
256
Total output
244
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
92
Input
262
Total output
252
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
89
Input
266
Total output
257
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
171
Input
282
Total output
250
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
130
Input
272
Total output
247
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
225
Input
301
Total output
256
Reasoning within output
rebase f001
0%
Failed
Tokens
87
Input
259
Total output
251
Reasoning within output
rebase f002
100%
Passed
Tokens
112
Input
258
Total output
249
Reasoning within output
rebase f003
100%
Passed
Tokens
94
Input
263
Total output
253
Reasoning within output
rebase f004
100%
Passed
Tokens
148
Input
290
Total output
263
Reasoning within output
rebase f005
100%
Passed
Tokens
132
Input
266
Total output
249
Reasoning within output
rebase f006
0%
Failed
Tokens
128
Input
281
Total output
256
Reasoning within output
rebase f007
100%
Passed
Tokens
122
Input
261
Total output
249
Reasoning within output
rebase f008
100%
Passed
Tokens
108
Input
259
Total output
247
Reasoning within output
rebase f009
100%
Passed
Tokens
89
Input
254
Total output
244
Reasoning within output
rebase f010
100%
Passed
Tokens
196
Input
273
Total output
245
Reasoning within output
rebase f011
100%
Passed
Tokens
141
Input
270
Total output
239
Reasoning within output
rebase f012
0%
Failed
Tokens
257
Input
307
Total output
262
Reasoning within output
reflog f001
100%
Passed
Tokens
228
Input
289
Total output
255
Reasoning within output
reflog f002
100%
Passed
Tokens
239
Input
357
Total output
238
Reasoning within output
reflog f003
100%
Passed
Tokens
199
Input
332
Total output
249
Reasoning within output
reflog f004
100%
Passed
Tokens
332
Input
293
Total output
242
Reasoning within output
reflog f005
100%
Passed
Tokens
388
Input
370
Total output
245
Reasoning within output
reflog f006
100%
Passed
Tokens
256
Input
385
Total output
246
Reasoning within output
reflog f007
100%
Passed
Tokens
284
Input
387
Total output
252
Reasoning within output
reflog f008
100%
Passed
Tokens
374
Input
357
Total output
240
Reasoning within output
reflog f009
100%
Passed
Tokens
340
Input
304
Total output
247
Reasoning within output
reflog f010
100%
Passed
Tokens
281
Input
363
Total output
247
Reasoning within output
reflog f011
100%
Passed
Tokens
327
Input
362
Total output
247
Reasoning within output
reflog f012
100%
Passed
Tokens
321
Input
427
Total output
255
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
127
Input
300
Total output
247
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
290
Input
311
Total output
253
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
112
Input
263
Total output
240
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
110
Input
266
Total output
244
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
118
Input
257
Total output
237
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
169
Input
255
Total output
237
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
201
Input
300
Total output
246
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
172
Input
269
Total output
253
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
197
Input
257
Total output
241
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
116
Input
266
Total output
253
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
108
Input
267
Total output
248
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
123
Input
264
Total output
246
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
33
Input
257
Total output
247
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
87
Input
251
Total output
241
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
97
Input
289
Total output
246
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
84
Input
258
Total output
250
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
40
Input
275
Total output
251
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
82
Input
254
Total output
249
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
39
Input
264
Total output
245
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
92
Input
262
Total output
250
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
86
Input
262
Total output
254
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
91
Input
259
Total output
249
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
95
Input
252
Total output
242
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
38
Input
262
Total output
244
Reasoning within output
tag_management f001
100%
Passed
Tokens
53
Input
253
Total output
243
Reasoning within output
tag_management f002
100%
Passed
Tokens
47
Input
265
Total output
243
Reasoning within output
tag_management f003
100%
Passed
Tokens
56
Input
268
Total output
258
Reasoning within output
tag_management f004
100%
Passed
Tokens
62
Input
269
Total output
262
Reasoning within output
tag_management f005
100%
Passed
Tokens
75
Input
259
Total output
250
Reasoning within output
tag_management f006
100%
Passed
Tokens
58
Input
270
Total output
254
Reasoning within output
tag_management f007
100%
Passed
Tokens
55
Input
273
Total output
260
Reasoning within output
tag_management f008
100%
Passed
Tokens
58
Input
267
Total output
244
Reasoning within output
tag_management f009
100%
Passed
Tokens
61
Input
280
Total output
262
Reasoning within output
tag_management f010
100%
Passed
Tokens
40
Input
269
Total output
260
Reasoning within output
tag_management f011
100%
Passed
Tokens
42
Input
251
Total output
242
Reasoning within output
tag_management f012
100%
Passed
Tokens
79
Input
253
Total output
243
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
135
Input
273
Total output
263
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
134
Input
275
Total output
251
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
214
Input
260
Total output
248
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
205
Input
260
Total output
252
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
126
Input
264
Total output
250
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
125
Input
260
Total output
246
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
129
Input
263
Total output
244
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
152
Input
288
Total output
246
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
242
Input
255
Total output
244
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
223
Input
260
Total output
243
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
217
Input
259
Total output
247
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
131
Input
267
Total output
247
Reasoning within output