Arcee-ai / trinity-mini
xhigh
71.6%
146 / 204 fixtures · 1 run(s)
34,517 input / 97,115 total output / 98,227 reasoning within output tokens $0.01612051
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
+0%
Text: 71.6% →
JSON: 71.6%
+25
Gained
JSON pass / text fail
−26
Lost
Text pass / JSON fail
119
Unchanged Pass
Both pass
33
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|---|---|---|
| f010 | 0% (0/1) | 100% (1/1) | -100% |
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| commit_squash | 50% | 8.3% | -41.7% |
| reflog | 100% | 58.3% | -41.7% |
| tag_management | 50% | 91.7% | + 41.7% |
| cherry_pick | 33.3% | 66.7% | + 33.3% |
| git_log_format | 75% | 100% | + 25% |
| branch_cleanup | 100% | 83.3% | -16.7% |
| git_clean | 58.3% | 75% | + 16.7% |
| rebase | 66.7% | 50% | -16.7% |
| worktree_usage | 58.3% | 41.7% | -16.7% |
| git_grep | 83.3% | 91.7% | + 8.3% |
| commit_messages | 91.7% | 100% | + 8.3% |
| git_show | 83.3% | 75% | -8.3% |
| blame_forensics | 41.7% | 50% | + 8.3% |
| git_bisect | 100% | 100% | + 0% |
| merge_conflicts | 66.7% | 66.7% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 58.3% | 58.3% | + 0% |
Changed Fixtures (51)
f001 -loss f002 +gain f003 +gain f004 -loss f009 +gain f011 -loss f001 -loss f002 -loss f003 +gain f005 +gain f009 +gain f010 +gain f010 +gain f001 +gain f003 -loss f006 -loss f009 -loss f010 -loss f011 -loss f012 -loss f006 +gain f012 +gain f002 +gain f003 +gain f006 +gain f005 -loss f001 +gain f002 -loss f010 +gain f006 -loss f009 -loss f004 -loss f006 -loss f009 -loss f010 -loss f012 -loss f001 +gain f002 -loss f006 -loss f007 +gain f001 +gain f002 +gain f005 +gain f008 +gain f009 -loss f010 +gain f011 +gain f001 -loss f002 -loss f004 -loss f010 +gain
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
220
Input
886
Total output
1,016
Reasoning within output
blame_forensics f002
0%
Failed
Tokens
208
Input
330
Total output
368
Reasoning within output
blame_forensics f003
0%
Failed
Tokens
227
Input
365
Total output
364
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
174
Input
788
Total output
800
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
233
Input
1,373
Total output
1,325
Reasoning within output
blame_forensics f006
0%
Failed
Tokens
209
Input
737
Total output
798
Reasoning within output
blame_forensics f007
0%
Failed
Tokens
181
Input
455
Total output
440
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
211
Input
772
Total output
902
Reasoning within output
blame_forensics f009
0%
Failed
Tokens
173
Input
653
Total output
705
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
360
Input
1,822
Total output
1,870
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
205
Input
559
Total output
590
Reasoning within output
blame_forensics f012
0%
Failed
Tokens
134
Input
824
Total output
771
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
100
Input
545
Total output
591
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
113
Input
312
Total output
330
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
89
Input
562
Total output
662
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
118
Input
299
Total output
342
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
100
Input
288
Total output
324
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
121
Input
413
Total output
455
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
109
Input
199
Total output
231
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
116
Input
262
Total output
266
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
77
Input
393
Total output
456
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
117
Input
279
Total output
274
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
71
Input
242
Total output
277
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
156
Input
294
Total output
298
Reasoning within output
cherry_pick f001
0%
Failed
Tokens
92
Input
827
Total output
957
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
116
Input
1,170
Total output
1,159
Reasoning within output
cherry_pick f003
0%
Failed
Tokens
86
Input
702
Total output
837
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
142
Input
642
Total output
665
Reasoning within output
cherry_pick f005
0%
Failed
Tokens
146
Input
432
Total output
501
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
130
Input
457
Total output
462
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
122
Input
368
Total output
399
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
122
Input
261
Total output
291
Reasoning within output
cherry_pick f009
0%
Failed
Tokens
106
Input
375
Total output
423
Reasoning within output
cherry_pick f010
0%
Failed
Tokens
205
Input
274
Total output
288
Reasoning within output
cherry_pick f011
0%
Failed
Tokens
160
Input
382
Total output
363
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
258
Input
634
Total output
626
Reasoning within output
commit_messages f001
93.3%
Passed
Tokens
100
Input
202
Total output
217
Reasoning within output
commit_messages f002
77.7%
Passed
Tokens
195
Input
210
Total output
228
Reasoning within output
commit_messages f003
86%
Passed
Tokens
82
Input
368
Total output
401
Reasoning within output
commit_messages f004
95.3%
Passed
Tokens
104
Input
268
Total output
298
Reasoning within output
commit_messages f005
83.3%
Passed
Tokens
98
Input
241
Total output
261
Reasoning within output
commit_messages f006
81%
Passed
Tokens
128
Input
366
Total output
404
Reasoning within output
commit_messages f007
91%
Passed
Tokens
174
Input
196
Total output
212
Reasoning within output
commit_messages f008
90%
Passed
Tokens
71
Input
348
Total output
375
Reasoning within output
commit_messages f009
74.3%
Passed
Tokens
122
Input
1,463
Total output
1,568
Reasoning within output
commit_messages f010
49.3%
Failed
Tokens
255
Input
1,152
Total output
1,164
Reasoning within output
commit_messages f011
73.3%
Passed
Tokens
140
Input
269
Total output
300
Reasoning within output
commit_messages f012
91.7%
Passed
Tokens
119
Input
276
Total output
325
Reasoning within output
commit_squash f001
0%
Failed
Tokens
128
Input
468
Total output
490
Reasoning within output
commit_squash f002
0%
Failed
Tokens
115
Input
340
Total output
362
Reasoning within output
commit_squash f003
100%
Passed
Tokens
120
Input
423
Total output
432
Reasoning within output
commit_squash f004
50%
Failed
Tokens
107
Input
314
Total output
325
Reasoning within output
commit_squash f005
0%
Failed
Tokens
113
Input
286
Total output
317
Reasoning within output
commit_squash f006
100%
Passed
Tokens
96
Input
316
Total output
345
Reasoning within output
commit_squash f007
0%
Failed
Tokens
98
Input
388
Total output
402
Reasoning within output
commit_squash f008
0%
Failed
Tokens
106
Input
306
Total output
328
Reasoning within output
commit_squash f009
100%
Passed
Tokens
100
Input
382
Total output
393
Reasoning within output
commit_squash f010
100%
Passed
Tokens
115
Input
404
Total output
395
Reasoning within output
commit_squash f011
100%
Passed
Tokens
127
Input
350
Total output
315
Reasoning within output
commit_squash f012
100%
Passed
Tokens
121
Input
343
Total output
335
Reasoning within output
git_bisect f001
100%
Passed
Tokens
169
Input
1,373
Total output
1,481
Reasoning within output
git_bisect f002
100%
Passed
Tokens
194
Input
500
Total output
438
Reasoning within output
git_bisect f003
100%
Passed
Tokens
196
Input
632
Total output
672
Reasoning within output
git_bisect f004
100%
Passed
Tokens
192
Input
714
Total output
630
Reasoning within output
git_bisect f005
100%
Passed
Tokens
196
Input
720
Total output
570
Reasoning within output
git_bisect f006
100%
Passed
Tokens
219
Input
411
Total output
370
Reasoning within output
git_bisect f007
100%
Passed
Tokens
190
Input
1,050
Total output
1,070
Reasoning within output
git_bisect f008
100%
Passed
Tokens
202
Input
619
Total output
417
Reasoning within output
git_bisect f009
100%
Passed
Tokens
192
Input
838
Total output
806
Reasoning within output
git_bisect f010
100%
Passed
Tokens
192
Input
836
Total output
779
Reasoning within output
git_bisect f011
100%
Passed
Tokens
188
Input
738
Total output
738
Reasoning within output
git_bisect f012
100%
Passed
Tokens
215
Input
252
Total output
231
Reasoning within output
git_clean f001
100%
Passed
Tokens
50
Input
302
Total output
322
Reasoning within output
git_clean f002
100%
Passed
Tokens
61
Input
605
Total output
682
Reasoning within output
git_clean f003
100%
Passed
Tokens
58
Input
397
Total output
428
Reasoning within output
git_clean f004
33.3%
Failed
Tokens
58
Input
936
Total output
1,139
Reasoning within output
git_clean f005
100%
Passed
Tokens
50
Input
683
Total output
703
Reasoning within output
git_clean f006
75%
Failed
Tokens
73
Input
386
Total output
431
Reasoning within output
git_clean f007
50%
Failed
Tokens
65
Input
389
Total output
435
Reasoning within output
git_clean f008
100%
Passed
Tokens
72
Input
390
Total output
428
Reasoning within output
git_clean f009
100%
Passed
Tokens
65
Input
400
Total output
469
Reasoning within output
git_clean f010
100%
Passed
Tokens
61
Input
258
Total output
302
Reasoning within output
git_clean f011
80%
Failed
Tokens
62
Input
379
Total output
415
Reasoning within output
git_clean f012
50%
Failed
Tokens
64
Input
1,134
Total output
1,270
Reasoning within output
git_grep f001
100%
Passed
Tokens
53
Input
375
Total output
427
Reasoning within output
git_grep f002
100%
Passed
Tokens
64
Input
214
Total output
228
Reasoning within output
git_grep f003
100%
Passed
Tokens
86
Input
238
Total output
278
Reasoning within output
git_grep f004
100%
Passed
Tokens
78
Input
270
Total output
268
Reasoning within output
git_grep f005
100%
Passed
Tokens
106
Input
262
Total output
287
Reasoning within output
git_grep f006
0%
Failed
Tokens
43
Input
227
Total output
246
Reasoning within output
git_grep f007
100%
Passed
Tokens
158
Input
420
Total output
412
Reasoning within output
git_grep f008
100%
Passed
Tokens
60
Input
251
Total output
281
Reasoning within output
git_grep f009
100%
Passed
Tokens
56
Input
206
Total output
202
Reasoning within output
git_grep f010
100%
Passed
Tokens
64
Input
242
Total output
261
Reasoning within output
git_grep f011
100%
Passed
Tokens
110
Input
389
Total output
360
Reasoning within output
git_grep f012
0%
Failed
Tokens
67
Input
337
Total output
373
Reasoning within output
git_log_format f001
100%
Passed
Tokens
720
Input
306
Total output
316
Reasoning within output
git_log_format f002
50%
Failed
Tokens
675
Input
398
Total output
466
Reasoning within output
git_log_format f003
50%
Failed
Tokens
560
Input
374
Total output
407
Reasoning within output
git_log_format f004
100%
Passed
Tokens
691
Input
309
Total output
298
Reasoning within output
git_log_format f005
100%
Passed
Tokens
564
Input
371
Total output
351
Reasoning within output
git_log_format f006
0%
Failed
Tokens
690
Input
582
Total output
462
Reasoning within output
git_log_format f007
100%
Passed
Tokens
720
Input
241
Total output
232
Reasoning within output
git_log_format f008
100%
Passed
Tokens
926
Input
230
Total output
231
Reasoning within output
git_log_format f009
100%
Passed
Tokens
560
Input
191
Total output
208
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,031
Input
232
Total output
274
Reasoning within output
git_log_format f011
100%
Passed
Tokens
338
Input
154
Total output
167
Reasoning within output
git_log_format f012
100%
Passed
Tokens
308
Input
203
Total output
207
Reasoning within output
git_show f001
100%
Passed
Tokens
165
Input
264
Total output
297
Reasoning within output
git_show f002
0%
Failed
Tokens
165
Input
378
Total output
418
Reasoning within output
git_show f003
0%
Failed
Tokens
571
Input
347
Total output
312
Reasoning within output
git_show f004
100%
Passed
Tokens
391
Input
279
Total output
277
Reasoning within output
git_show f005
100%
Passed
Tokens
171
Input
1,140
Total output
1,326
Reasoning within output
git_show f006
100%
Passed
Tokens
178
Input
285
Total output
304
Reasoning within output
git_show f007
100%
Passed
Tokens
166
Input
251
Total output
274
Reasoning within output
git_show f008
100%
Passed
Tokens
173
Input
295
Total output
285
Reasoning within output
git_show f009
100%
Passed
Tokens
256
Input
294
Total output
294
Reasoning within output
git_show f010
100%
Passed
Tokens
167
Input
288
Total output
312
Reasoning within output
git_show f011
100%
Passed
Tokens
190
Input
234
Total output
259
Reasoning within output
git_show f012
100%
Passed
Tokens
285
Input
280
Total output
290
Reasoning within output
merge_conflicts f001
0%
Failed
Tokens
85
Input
515
Total output
592
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
105
Input
770
Total output
766
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
78
Input
842
Total output
989
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
131
Input
405
Total output
425
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
135
Input
345
Total output
395
Reasoning within output
merge_conflicts f006
0%
Failed
Tokens
120
Input
494
Total output
460
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
125
Input
395
Total output
454
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
107
Input
290
Total output
311
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
104
Input
356
Total output
380
Reasoning within output
merge_conflicts f010
0%
Failed
Tokens
173
Input
224
Total output
240
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
142
Input
956
Total output
928
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
222
Input
350
Total output
329
Reasoning within output
rebase f001
0%
Failed
Tokens
95
Input
669
Total output
752
Reasoning within output
rebase f002
100%
Passed
Tokens
122
Input
273
Total output
262
Reasoning within output
rebase f003
100%
Passed
Tokens
100
Input
367
Total output
416
Reasoning within output
rebase f004
0%
Failed
Tokens
140
Input
1,216
Total output
1,319
Reasoning within output
rebase f005
100%
Passed
Tokens
139
Input
392
Total output
458
Reasoning within output
rebase f006
100%
Passed
Tokens
131
Input
545
Total output
542
Reasoning within output
rebase f007
100%
Passed
Tokens
125
Input
330
Total output
361
Reasoning within output
rebase f008
100%
Passed
Tokens
117
Input
301
Total output
323
Reasoning within output
rebase f009
100%
Passed
Tokens
100
Input
350
Total output
398
Reasoning within output
rebase f010
100%
Passed
Tokens
199
Input
323
Total output
345
Reasoning within output
rebase f011
0%
Failed
Tokens
149
Input
738
Total output
616
Reasoning within output
rebase f012
0%
Failed
Tokens
252
Input
1,140
Total output
1,109
Reasoning within output
reflog f001
100%
Passed
Tokens
209
Input
1,091
Total output
1,085
Reasoning within output
reflog f002
100%
Passed
Tokens
206
Input
809
Total output
615
Reasoning within output
reflog f003
100%
Passed
Tokens
175
Input
428
Total output
314
Reasoning within output
reflog f004
100%
Passed
Tokens
286
Input
619
Total output
481
Reasoning within output
reflog f005
100%
Passed
Tokens
332
Input
644
Total output
452
Reasoning within output
reflog f006
100%
Passed
Tokens
214
Input
557
Total output
302
Reasoning within output
reflog f007
100%
Passed
Tokens
226
Input
402
Total output
292
Reasoning within output
reflog f008
100%
Passed
Tokens
305
Input
795
Total output
580
Reasoning within output
reflog f009
100%
Passed
Tokens
274
Input
862
Total output
621
Reasoning within output
reflog f010
100%
Passed
Tokens
232
Input
358
Total output
335
Reasoning within output
reflog f011
100%
Passed
Tokens
270
Input
648
Total output
409
Reasoning within output
reflog f012
100%
Passed
Tokens
269
Input
878
Total output
680
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
121
Input
268
Total output
183
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
254
Input
405
Total output
233
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
108
Input
338
Total output
230
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
106
Input
350
Total output
251
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
118
Input
357
Total output
227
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
164
Input
202
Total output
178
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
189
Input
405
Total output
255
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
157
Input
338
Total output
244
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
187
Input
427
Total output
298
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
116
Input
217
Total output
151
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
105
Input
324
Total output
273
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
119
Input
328
Total output
218
Reasoning within output
submodule_usage f001
0%
Failed
Tokens
45
Input
297
Total output
317
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
89
Input
301
Total output
359
Reasoning within output
submodule_usage f003
0%
Failed
Tokens
97
Input
1,030
Total output
1,181
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
80
Input
280
Total output
347
Reasoning within output
submodule_usage f005
0%
Failed
Tokens
52
Input
362
Total output
389
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
84
Input
461
Total output
546
Reasoning within output
submodule_usage f007
0%
Failed
Tokens
52
Input
380
Total output
406
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
89
Input
297
Total output
311
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
83
Input
406
Total output
455
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
92
Input
318
Total output
356
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
97
Input
231
Total output
264
Reasoning within output
submodule_usage f012
66.7%
Failed
Tokens
50
Input
1,436
Total output
1,648
Reasoning within output
tag_management f001
50%
Failed
Tokens
59
Input
283
Total output
296
Reasoning within output
tag_management f002
0%
Failed
Tokens
56
Input
378
Total output
369
Reasoning within output
tag_management f003
100%
Passed
Tokens
60
Input
373
Total output
369
Reasoning within output
tag_management f004
100%
Passed
Tokens
66
Input
304
Total output
320
Reasoning within output
tag_management f005
80%
Failed
Tokens
79
Input
318
Total output
294
Reasoning within output
tag_management f006
100%
Passed
Tokens
62
Input
293
Total output
261
Reasoning within output
tag_management f007
100%
Passed
Tokens
64
Input
267
Total output
272
Reasoning within output
tag_management f008
33.3%
Failed
Tokens
66
Input
737
Total output
721
Reasoning within output
tag_management f009
100%
Passed
Tokens
70
Input
400
Total output
407
Reasoning within output
tag_management f010
0%
Failed
Tokens
50
Input
278
Total output
283
Reasoning within output
tag_management f011
0%
Failed
Tokens
49
Input
324
Total output
359
Reasoning within output
tag_management f012
100%
Passed
Tokens
86
Input
552
Total output
525
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
122
Input
342
Total output
359
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
124
Input
1,064
Total output
1,116
Reasoning within output
worktree_usage f003
0%
Failed
Tokens
175
Input
317
Total output
346
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
180
Input
284
Total output
339
Reasoning within output
worktree_usage f005
33.3%
Failed
Tokens
117
Input
377
Total output
421
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
119
Input
419
Total output
443
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
125
Input
421
Total output
403
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
139
Input
759
Total output
726
Reasoning within output
worktree_usage f009
0%
Failed
Tokens
206
Input
775
Total output
888
Reasoning within output
worktree_usage f010
0%
Failed
Tokens
173
Input
286
Total output
306
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
176
Input
478
Total output
520
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
115
Input
497
Total output
494
Reasoning within output