Arcee-ai / trinity-mini
medium
69.6%
142 / 204 fixtures · 1 run(s)
34,198 input / 103,288 total output / 105,171 reasoning within output tokens $0.01703211
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
+5.9%
Text: 69.6% →
JSON: 75.5%
+29
Gained
JSON pass / text fail
−16
Lost
Text pass / JSON fail
125
Unchanged Pass
Both pass
33
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| merge_conflicts | 16.7% | 58.3% | + 41.7% |
| commit_squash | 33.3% | 0% | -33.3% |
| rebase | 50% | 75% | + 25% |
| cherry_pick | 50% | 66.7% | + 16.7% |
| git_grep | 75% | 91.7% | + 16.7% |
| git_log_format | 83.3% | 100% | + 16.7% |
| reflog | 100% | 83.3% | -16.7% |
| submodule_usage | 58.3% | 66.7% | + 8.3% |
| git_bisect | 91.7% | 100% | + 8.3% |
| git_clean | 50% | 58.3% | + 8.3% |
| worktree_usage | 41.7% | 50% | + 8.3% |
| blame_forensics | 66.7% | 66.7% | + 0% |
| branch_cleanup | 91.7% | 91.7% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| git_show | 83.3% | 83.3% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| tag_management | 91.7% | 91.7% | + 0% |
Changed Fixtures (45)
f001 -loss f002 +gain f006 +gain f009 -loss f001 -loss f008 +gain f002 -loss f003 +gain f004 +gain f005 +gain f010 +gain f011 -loss f004 -loss f005 -loss f008 -loss f011 -loss f003 +gain f001 +gain f007 +gain f010 +gain f002 +gain f003 +gain f001 +gain f004 +gain f005 +gain f007 +gain f008 +gain f010 +gain f004 +gain f005 +gain f006 +gain f010 +gain f011 -loss f004 -loss f005 -loss f004 +gain f005 +gain f006 -loss f007 +gain f009 -loss f002 +gain f010 -loss f003 -loss f006 +gain f009 +gain
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
220
Input
831
Total output
923
Reasoning within output
blame_forensics f002
0%
Failed
Tokens
208
Input
8,086
Total output
8,679
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
222
Input
299
Total output
315
Reasoning within output
blame_forensics f004
0%
Failed
Tokens
172
Input
404
Total output
385
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
226
Input
963
Total output
1,142
Reasoning within output
blame_forensics f006
0%
Failed
Tokens
208
Input
1,258
Total output
1,290
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
181
Input
350
Total output
386
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
209
Input
1,018
Total output
1,177
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
180
Input
872
Total output
899
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
367
Input
589
Total output
596
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
215
Input
630
Total output
540
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
129
Input
727
Total output
778
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
101
Input
520
Total output
552
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
117
Input
433
Total output
469
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
89
Input
946
Total output
1,138
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
127
Input
276
Total output
314
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
104
Input
332
Total output
376
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
116
Input
233
Total output
255
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
106
Input
301
Total output
344
Reasoning within output
branch_cleanup f008
33.3%
Failed
Tokens
119
Input
350
Total output
367
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
78
Input
389
Total output
462
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
112
Input
376
Total output
393
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
70
Input
320
Total output
380
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
149
Input
684
Total output
744
Reasoning within output
cherry_pick f001
0%
Failed
Tokens
92
Input
471
Total output
555
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
113
Input
1,069
Total output
980
Reasoning within output
cherry_pick f003
0%
Failed
Tokens
87
Input
1,204
Total output
1,352
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
141
Input
446
Total output
503
Reasoning within output
cherry_pick f005
0%
Failed
Tokens
144
Input
343
Total output
390
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
130
Input
752
Total output
769
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
122
Input
374
Total output
414
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
122
Input
312
Total output
352
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
106
Input
344
Total output
373
Reasoning within output
cherry_pick f010
0%
Failed
Tokens
201
Input
296
Total output
329
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
159
Input
455
Total output
447
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
256
Input
333
Total output
312
Reasoning within output
commit_messages f001
93%
Passed
Tokens
100
Input
498
Total output
520
Reasoning within output
commit_messages f002
81.7%
Passed
Tokens
195
Input
319
Total output
333
Reasoning within output
commit_messages f003
94.3%
Passed
Tokens
82
Input
424
Total output
457
Reasoning within output
commit_messages f004
93.7%
Passed
Tokens
104
Input
262
Total output
287
Reasoning within output
commit_messages f005
68.3%
Passed
Tokens
98
Input
353
Total output
393
Reasoning within output
commit_messages f006
56.7%
Passed
Tokens
128
Input
617
Total output
704
Reasoning within output
commit_messages f007
92.5%
Passed
Tokens
174
Input
331
Total output
378
Reasoning within output
commit_messages f008
87.7%
Passed
Tokens
71
Input
381
Total output
420
Reasoning within output
commit_messages f009
81%
Passed
Tokens
122
Input
1,097
Total output
1,159
Reasoning within output
commit_messages f010
56.7%
Passed
Tokens
255
Input
843
Total output
929
Reasoning within output
commit_messages f011
75.7%
Passed
Tokens
140
Input
418
Total output
432
Reasoning within output
commit_messages f012
93.3%
Passed
Tokens
119
Input
238
Total output
284
Reasoning within output
commit_squash f001
0%
Failed
Tokens
129
Input
508
Total output
535
Reasoning within output
commit_squash f002
0%
Failed
Tokens
115
Input
359
Total output
362
Reasoning within output
commit_squash f003
50%
Failed
Tokens
119
Input
535
Total output
531
Reasoning within output
commit_squash f004
100%
Passed
Tokens
112
Input
290
Total output
275
Reasoning within output
commit_squash f005
100%
Passed
Tokens
113
Input
697
Total output
791
Reasoning within output
commit_squash f006
50%
Failed
Tokens
97
Input
409
Total output
416
Reasoning within output
commit_squash f007
50%
Failed
Tokens
96
Input
240
Total output
242
Reasoning within output
commit_squash f008
100%
Passed
Tokens
113
Input
263
Total output
271
Reasoning within output
commit_squash f009
50%
Failed
Tokens
99
Input
348
Total output
349
Reasoning within output
commit_squash f010
50%
Failed
Tokens
118
Input
333
Total output
345
Reasoning within output
commit_squash f011
100%
Passed
Tokens
122
Input
436
Total output
430
Reasoning within output
commit_squash f012
66.7%
Failed
Tokens
118
Input
506
Total output
526
Reasoning within output
git_bisect f001
100%
Passed
Tokens
167
Input
332
Total output
309
Reasoning within output
git_bisect f002
100%
Passed
Tokens
200
Input
663
Total output
709
Reasoning within output
git_bisect f003
0%
Failed
git_bisect f004
100%
Passed
Tokens
198
Input
472
Total output
468
Reasoning within output
git_bisect f005
100%
Passed
Tokens
194
Input
803
Total output
623
Reasoning within output
git_bisect f006
100%
Passed
Tokens
217
Input
523
Total output
343
Reasoning within output
git_bisect f007
100%
Passed
Tokens
194
Input
536
Total output
574
Reasoning within output
git_bisect f008
100%
Passed
Tokens
194
Input
870
Total output
756
Reasoning within output
git_bisect f009
100%
Passed
Tokens
190
Input
692
Total output
632
Reasoning within output
git_bisect f010
100%
Passed
Tokens
192
Input
464
Total output
519
Reasoning within output
git_bisect f011
100%
Passed
Tokens
196
Input
430
Total output
428
Reasoning within output
git_bisect f012
100%
Passed
Tokens
213
Input
797
Total output
817
Reasoning within output
git_clean f001
50%
Failed
Tokens
50
Input
337
Total output
374
Reasoning within output
git_clean f002
100%
Passed
Tokens
61
Input
377
Total output
428
Reasoning within output
git_clean f003
100%
Passed
Tokens
58
Input
362
Total output
405
Reasoning within output
git_clean f004
33.3%
Failed
Tokens
58
Input
760
Total output
905
Reasoning within output
git_clean f005
100%
Passed
Tokens
50
Input
505
Total output
542
Reasoning within output
git_clean f006
75%
Failed
Tokens
73
Input
365
Total output
408
Reasoning within output
git_clean f007
75%
Failed
Tokens
65
Input
438
Total output
457
Reasoning within output
git_clean f008
100%
Passed
Tokens
72
Input
311
Total output
356
Reasoning within output
git_clean f009
100%
Passed
Tokens
65
Input
1,141
Total output
1,254
Reasoning within output
git_clean f010
100%
Passed
Tokens
61
Input
536
Total output
596
Reasoning within output
git_clean f011
80%
Failed
Tokens
62
Input
310
Total output
335
Reasoning within output
git_clean f012
50%
Failed
Tokens
64
Input
1,538
Total output
1,693
Reasoning within output
git_grep f001
100%
Passed
Tokens
53
Input
571
Total output
674
Reasoning within output
git_grep f002
100%
Passed
Tokens
65
Input
242
Total output
255
Reasoning within output
git_grep f003
100%
Passed
Tokens
86
Input
251
Total output
291
Reasoning within output
git_grep f004
100%
Passed
Tokens
78
Input
325
Total output
341
Reasoning within output
git_grep f005
100%
Passed
Tokens
106
Input
240
Total output
257
Reasoning within output
git_grep f006
0%
Failed
Tokens
43
Input
189
Total output
204
Reasoning within output
git_grep f007
0%
Failed
Tokens
158
Input
990
Total output
984
Reasoning within output
git_grep f008
100%
Passed
Tokens
60
Input
237
Total output
272
Reasoning within output
git_grep f009
100%
Passed
Tokens
56
Input
251
Total output
263
Reasoning within output
git_grep f010
0%
Failed
Tokens
64
Input
222
Total output
235
Reasoning within output
git_grep f011
100%
Passed
Tokens
110
Input
390
Total output
361
Reasoning within output
git_grep f012
100%
Passed
Tokens
67
Input
359
Total output
394
Reasoning within output
git_log_format f001
100%
Passed
Tokens
703
Input
216
Total output
239
Reasoning within output
git_log_format f002
50%
Failed
Tokens
676
Input
388
Total output
456
Reasoning within output
git_log_format f003
50%
Failed
Tokens
556
Input
329
Total output
339
Reasoning within output
git_log_format f004
100%
Passed
Tokens
670
Input
300
Total output
313
Reasoning within output
git_log_format f005
100%
Passed
Tokens
564
Input
448
Total output
487
Reasoning within output
git_log_format f006
100%
Passed
Tokens
690
Input
520
Total output
424
Reasoning within output
git_log_format f007
100%
Passed
Tokens
708
Input
257
Total output
242
Reasoning within output
git_log_format f008
100%
Passed
Tokens
911
Input
240
Total output
269
Reasoning within output
git_log_format f009
100%
Passed
Tokens
559
Input
176
Total output
193
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,045
Input
225
Total output
255
Reasoning within output
git_log_format f011
100%
Passed
Tokens
345
Input
146
Total output
157
Reasoning within output
git_log_format f012
100%
Passed
Tokens
312
Input
224
Total output
236
Reasoning within output
git_show f001
100%
Passed
Tokens
165
Input
639
Total output
705
Reasoning within output
git_show f002
0%
Failed
Tokens
168
Input
534
Total output
613
Reasoning within output
git_show f003
100%
Passed
Tokens
545
Input
298
Total output
293
Reasoning within output
git_show f004
100%
Passed
Tokens
391
Input
265
Total output
265
Reasoning within output
git_show f005
0%
Failed
Tokens
175
Input
450
Total output
515
Reasoning within output
git_show f006
100%
Passed
Tokens
177
Input
224
Total output
262
Reasoning within output
git_show f007
100%
Passed
Tokens
166
Input
254
Total output
294
Reasoning within output
git_show f008
100%
Passed
Tokens
181
Input
260
Total output
211
Reasoning within output
git_show f009
100%
Passed
Tokens
260
Input
209
Total output
198
Reasoning within output
git_show f010
100%
Passed
Tokens
169
Input
322
Total output
347
Reasoning within output
git_show f011
100%
Passed
Tokens
197
Input
319
Total output
338
Reasoning within output
git_show f012
100%
Passed
Tokens
281
Input
263
Total output
273
Reasoning within output
merge_conflicts f001
0%
Failed
Tokens
85
Input
731
Total output
837
Reasoning within output
merge_conflicts f002
0%
Failed
Tokens
105
Input
789
Total output
792
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
78
Input
911
Total output
1,057
Reasoning within output
merge_conflicts f004
0%
Failed
Tokens
131
Input
303
Total output
298
Reasoning within output
merge_conflicts f005
0%
Failed
Tokens
135
Input
392
Total output
452
Reasoning within output
merge_conflicts f006
0%
Failed
Tokens
120
Input
435
Total output
440
Reasoning within output
merge_conflicts f007
0%
Failed
Tokens
125
Input
296
Total output
331
Reasoning within output
merge_conflicts f008
0%
Failed
Tokens
107
Input
376
Total output
410
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
104
Input
147
Total output
153
Reasoning within output
merge_conflicts f010
0%
Failed
Tokens
173
Input
283
Total output
318
Reasoning within output
merge_conflicts f011
0%
Failed
Tokens
142
Input
599
Total output
574
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
222
Input
324
Total output
310
Reasoning within output
rebase f001
0%
Failed
Tokens
94
Input
449
Total output
504
Reasoning within output
rebase f002
100%
Passed
Tokens
121
Input
620
Total output
607
Reasoning within output
rebase f003
100%
Passed
Tokens
99
Input
360
Total output
417
Reasoning within output
rebase f004
0%
Failed
Tokens
142
Input
516
Total output
531
Reasoning within output
rebase f005
0%
Failed
Tokens
137
Input
741
Total output
844
Reasoning within output
rebase f006
0%
Failed
Tokens
130
Input
463
Total output
449
Reasoning within output
rebase f007
100%
Passed
Tokens
124
Input
373
Total output
415
Reasoning within output
rebase f008
100%
Passed
Tokens
119
Input
348
Total output
382
Reasoning within output
rebase f009
100%
Passed
Tokens
102
Input
380
Total output
412
Reasoning within output
rebase f010
0%
Failed
Tokens
195
Input
484
Total output
508
Reasoning within output
rebase f011
100%
Passed
Tokens
150
Input
553
Total output
531
Reasoning within output
rebase f012
0%
Failed
Tokens
252
Input
278
Total output
268
Reasoning within output
reflog f001
100%
Passed
Tokens
198
Input
391
Total output
378
Reasoning within output
reflog f002
100%
Passed
Tokens
188
Input
643
Total output
455
Reasoning within output
reflog f003
100%
Passed
Tokens
175
Input
638
Total output
491
Reasoning within output
reflog f004
100%
Passed
Tokens
286
Input
721
Total output
461
Reasoning within output
reflog f005
100%
Passed
Tokens
307
Input
656
Total output
466
Reasoning within output
reflog f006
100%
Passed
Tokens
214
Input
884
Total output
697
Reasoning within output
reflog f007
100%
Passed
Tokens
246
Input
726
Total output
329
Reasoning within output
reflog f008
100%
Passed
Tokens
293
Input
345
Total output
251
Reasoning within output
reflog f009
100%
Passed
Tokens
262
Input
723
Total output
455
Reasoning within output
reflog f010
100%
Passed
Tokens
225
Input
751
Total output
530
Reasoning within output
reflog f011
100%
Passed
Tokens
282
Input
716
Total output
558
Reasoning within output
reflog f012
100%
Passed
Tokens
266
Input
1,178
Total output
878
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
121
Input
454
Total output
324
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
254
Input
469
Total output
263
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
108
Input
323
Total output
208
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
106
Input
409
Total output
303
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
117
Input
334
Total output
276
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
164
Input
282
Total output
245
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
187
Input
404
Total output
312
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
157
Input
344
Total output
197
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
187
Input
378
Total output
259
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
116
Input
308
Total output
258
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
104
Input
338
Total output
201
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
119
Input
307
Total output
207
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
45
Input
310
Total output
342
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
89
Input
411
Total output
510
Reasoning within output
submodule_usage f003
25%
Failed
Tokens
93
Input
881
Total output
977
Reasoning within output
submodule_usage f004
0%
Failed
Tokens
79
Input
273
Total output
312
Reasoning within output
submodule_usage f005
0%
Failed
Tokens
52
Input
502
Total output
561
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
79
Input
496
Total output
583
Reasoning within output
submodule_usage f007
0%
Failed
Tokens
52
Input
302
Total output
310
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
85
Input
894
Total output
1,056
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
86
Input
269
Total output
289
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
87
Input
269
Total output
314
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
94
Input
263
Total output
297
Reasoning within output
submodule_usage f012
0%
Failed
Tokens
50
Input
460
Total output
491
Reasoning within output
tag_management f001
100%
Passed
Tokens
57
Input
344
Total output
357
Reasoning within output
tag_management f002
0%
Failed
Tokens
57
Input
335
Total output
329
Reasoning within output
tag_management f003
100%
Passed
Tokens
61
Input
322
Total output
315
Reasoning within output
tag_management f004
100%
Passed
Tokens
66
Input
322
Total output
338
Reasoning within output
tag_management f005
100%
Passed
Tokens
78
Input
320
Total output
311
Reasoning within output
tag_management f006
100%
Passed
Tokens
62
Input
719
Total output
677
Reasoning within output
tag_management f007
100%
Passed
Tokens
63
Input
234
Total output
221
Reasoning within output
tag_management f008
100%
Passed
Tokens
66
Input
523
Total output
532
Reasoning within output
tag_management f009
100%
Passed
Tokens
69
Input
424
Total output
441
Reasoning within output
tag_management f010
100%
Passed
Tokens
50
Input
252
Total output
260
Reasoning within output
tag_management f011
100%
Passed
Tokens
50
Input
288
Total output
319
Reasoning within output
tag_management f012
100%
Passed
Tokens
83
Input
436
Total output
430
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
127
Input
392
Total output
427
Reasoning within output
worktree_usage f002
0%
Failed
Tokens
132
Input
906
Total output
981
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
180
Input
321
Total output
311
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
173
Input
214
Total output
249
Reasoning within output
worktree_usage f005
33.3%
Failed
Tokens
113
Input
411
Total output
445
Reasoning within output
worktree_usage f006
0%
Failed
Tokens
115
Input
420
Total output
454
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
121
Input
433
Total output
455
Reasoning within output
worktree_usage f008
50%
Failed
Tokens
146
Input
1,414
Total output
1,443
Reasoning within output
worktree_usage f009
0%
Failed
Tokens
200
Input
375
Total output
454
Reasoning within output
worktree_usage f010
50%
Failed
Tokens
182
Input
361
Total output
391
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
177
Input
282
Total output
310
Reasoning within output
worktree_usage f012
0%
Failed
Tokens
114
Input
411
Total output
402
Reasoning within output