Arcee-ai / trinity-mini
high
71.6%
146 / 204 fixtures · 1 run(s)
34,415 input / 97,176 total output / 98,085 reasoning within output tokens $0.01612508
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
+3.4%
Text: 71.6% →
JSON: 75%
+26
Gained
JSON pass / text fail
−19
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 |
|---|---|---|---|
| commit_squash | 41.7% | 0% | -41.7% |
| merge_conflicts | 33.3% | 66.7% | + 33.3% |
| submodule_usage | 33.3% | 66.7% | + 33.3% |
| worktree_usage | 33.3% | 58.3% | + 25% |
| branch_cleanup | 75% | 100% | + 25% |
| git_log_format | 83.3% | 100% | + 16.7% |
| reflog | 100% | 83.3% | -16.7% |
| cherry_pick | 66.7% | 58.3% | -8.3% |
| blame_forensics | 75% | 66.7% | -8.3% |
| git_grep | 100% | 91.7% | -8.3% |
| rebase | 66.7% | 75% | + 8.3% |
| commit_messages | 91.7% | 91.7% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_clean | 58.3% | 58.3% | + 0% |
| git_show | 83.3% | 83.3% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| tag_management | 75% | 75% | + 0% |
Changed Fixtures (45)
f002 -loss f004 +gain f005 -loss f006 -loss f007 +gain f008 -loss f011 +gain f001 +gain f002 +gain f008 +gain f003 +gain f006 -loss f011 -loss f004 -loss f005 -loss f007 -loss f009 -loss f010 -loss f003 -loss f003 +gain f006 +gain f006 -loss f002 +gain f005 +gain f002 +gain f008 +gain f011 +gain f004 +gain f006 +gain f011 -loss f001 -loss f008 -loss f005 +gain f007 +gain f010 +gain f011 +gain f003 +gain f009 +gain f010 -loss f011 -loss f001 +gain f002 +gain f003 +gain f006 +gain f009 -loss
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
221
Input
557
Total output
579
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
200
Input
705
Total output
696
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
232
Input
308
Total output
298
Reasoning within output
blame_forensics f004
0%
Failed
Tokens
168
Input
303
Total output
343
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
227
Input
2,097
Total output
2,165
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
207
Input
526
Total output
552
Reasoning within output
blame_forensics f007
0%
Failed
Tokens
184
Input
344
Total output
350
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
212
Input
476
Total output
538
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
174
Input
577
Total output
576
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
360
Input
998
Total output
1,046
Reasoning within output
blame_forensics f011
0%
Failed
Tokens
205
Input
428
Total output
424
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
135
Input
671
Total output
699
Reasoning within output
branch_cleanup f001
100%
Failed
Tokens
99
Input
676
Total output
726
Reasoning within output
branch_cleanup f002
0%
Failed
Tokens
109
Input
773
Total output
826
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
91
Input
590
Total output
711
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
124
Input
276
Total output
312
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
99
Input
316
Total output
355
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
119
Input
307
Total output
334
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
105
Input
259
Total output
296
Reasoning within output
branch_cleanup f008
33.3%
Failed
Tokens
117
Input
410
Total output
442
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
79
Input
293
Total output
339
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
115
Input
232
Total output
233
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
68
Input
810
Total output
942
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
147
Input
412
Total output
427
Reasoning within output
cherry_pick f001
0%
Failed
Tokens
92
Input
1,382
Total output
1,559
Reasoning within output
cherry_pick f002
0%
Failed
Tokens
113
Input
515
Total output
487
Reasoning within output
cherry_pick f003
0%
Failed
Tokens
85
Input
596
Total output
682
Reasoning within output
cherry_pick f004
100%
Passed
Tokens
141
Input
888
Total output
1,006
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
147
Input
505
Total output
602
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
132
Input
341
Total output
341
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
123
Input
293
Total output
323
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
122
Input
280
Total output
311
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
104
Input
327
Total output
361
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
203
Input
333
Total output
353
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
158
Input
473
Total output
460
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
250
Input
829
Total output
880
Reasoning within output
commit_messages f001
93.3%
Passed
Tokens
100
Input
239
Total output
252
Reasoning within output
commit_messages f002
83.3%
Passed
Tokens
195
Input
266
Total output
284
Reasoning within output
commit_messages f003
71.7%
Passed
Tokens
82
Input
476
Total output
517
Reasoning within output
commit_messages f004
93.3%
Passed
Tokens
104
Input
349
Total output
399
Reasoning within output
commit_messages f005
87.7%
Passed
Tokens
98
Input
341
Total output
384
Reasoning within output
commit_messages f006
77.3%
Passed
Tokens
128
Input
484
Total output
534
Reasoning within output
commit_messages f007
75%
Passed
Tokens
174
Input
437
Total output
483
Reasoning within output
commit_messages f008
92.7%
Passed
Tokens
71
Input
308
Total output
343
Reasoning within output
commit_messages f009
71.7%
Passed
Tokens
122
Input
463
Total output
510
Reasoning within output
commit_messages f010
81.7%
Passed
Tokens
255
Input
929
Total output
1,038
Reasoning within output
commit_messages f011
49%
Failed
Tokens
140
Input
327
Total output
338
Reasoning within output
commit_messages f012
81%
Passed
Tokens
119
Input
363
Total output
411
Reasoning within output
commit_squash f001
50%
Failed
Tokens
133
Input
329
Total output
339
Reasoning within output
commit_squash f002
0%
Failed
Tokens
118
Input
1,216
Total output
1,243
Reasoning within output
commit_squash f003
50%
Failed
Tokens
120
Input
460
Total output
461
Reasoning within output
commit_squash f004
100%
Passed
Tokens
109
Input
375
Total output
368
Reasoning within output
commit_squash f005
100%
Passed
Tokens
112
Input
455
Total output
518
Reasoning within output
commit_squash f006
50%
Failed
Tokens
95
Input
383
Total output
421
Reasoning within output
commit_squash f007
100%
Passed
Tokens
97
Input
396
Total output
414
Reasoning within output
commit_squash f008
0%
Failed
Tokens
109
Input
378
Total output
381
Reasoning within output
commit_squash f009
100%
Passed
Tokens
102
Input
395
Total output
416
Reasoning within output
commit_squash f010
100%
Passed
Tokens
117
Input
286
Total output
296
Reasoning within output
commit_squash f011
0%
Failed
Tokens
124
Input
309
Total output
313
Reasoning within output
commit_squash f012
33.3%
Failed
Tokens
121
Input
374
Total output
366
Reasoning within output
git_bisect f001
100%
Passed
Tokens
167
Input
291
Total output
286
Reasoning within output
git_bisect f002
100%
Passed
Tokens
190
Input
815
Total output
731
Reasoning within output
git_bisect f003
100%
Passed
Tokens
186
Input
1,063
Total output
1,047
Reasoning within output
git_bisect f004
100%
Passed
Tokens
198
Input
555
Total output
324
Reasoning within output
git_bisect f005
100%
Passed
Tokens
198
Input
697
Total output
685
Reasoning within output
git_bisect f006
100%
Passed
Tokens
215
Input
767
Total output
489
Reasoning within output
git_bisect f007
100%
Passed
Tokens
192
Input
1,379
Total output
1,333
Reasoning within output
git_bisect f008
100%
Passed
Tokens
192
Input
825
Total output
749
Reasoning within output
git_bisect f009
100%
Passed
Tokens
194
Input
513
Total output
474
Reasoning within output
git_bisect f010
100%
Passed
Tokens
196
Input
916
Total output
634
Reasoning within output
git_bisect f011
100%
Passed
Tokens
200
Input
539
Total output
471
Reasoning within output
git_bisect f012
100%
Passed
Tokens
221
Input
907
Total output
799
Reasoning within output
git_clean f001
100%
Passed
Tokens
50
Input
296
Total output
327
Reasoning within output
git_clean f002
100%
Passed
Tokens
61
Input
348
Total output
380
Reasoning within output
git_clean f003
33.3%
Failed
Tokens
58
Input
384
Total output
428
Reasoning within output
git_clean f004
33.3%
Failed
Tokens
58
Input
1,540
Total output
1,853
Reasoning within output
git_clean f005
100%
Passed
Tokens
50
Input
329
Total output
350
Reasoning within output
git_clean f006
75%
Failed
Tokens
73
Input
398
Total output
415
Reasoning within output
git_clean f007
100%
Passed
Tokens
65
Input
480
Total output
530
Reasoning within output
git_clean f008
100%
Passed
Tokens
72
Input
257
Total output
284
Reasoning within output
git_clean f009
100%
Passed
Tokens
65
Input
569
Total output
643
Reasoning within output
git_clean f010
100%
Passed
Tokens
61
Input
327
Total output
379
Reasoning within output
git_clean f011
20%
Failed
Tokens
62
Input
473
Total output
531
Reasoning within output
git_clean f012
50%
Failed
Tokens
64
Input
1,456
Total output
1,710
Reasoning within output
git_grep f001
100%
Passed
Tokens
53
Input
752
Total output
906
Reasoning within output
git_grep f002
100%
Passed
Tokens
68
Input
212
Total output
227
Reasoning within output
git_grep f003
100%
Passed
Tokens
86
Input
248
Total output
287
Reasoning within output
git_grep f004
100%
Passed
Tokens
78
Input
293
Total output
305
Reasoning within output
git_grep f005
100%
Passed
Tokens
106
Input
244
Total output
250
Reasoning within output
git_grep f006
100%
Passed
Tokens
43
Input
392
Total output
445
Reasoning within output
git_grep f007
100%
Passed
Tokens
158
Input
1,026
Total output
999
Reasoning within output
git_grep f008
100%
Passed
Tokens
60
Input
180
Total output
207
Reasoning within output
git_grep f009
100%
Passed
Tokens
56
Input
181
Total output
177
Reasoning within output
git_grep f010
100%
Passed
Tokens
64
Input
309
Total output
321
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
323
Total output
352
Reasoning within output
git_log_format f001
100%
Passed
Tokens
703
Input
251
Total output
270
Reasoning within output
git_log_format f002
50%
Failed
Tokens
686
Input
358
Total output
404
Reasoning within output
git_log_format f003
100%
Passed
Tokens
575
Input
336
Total output
356
Reasoning within output
git_log_format f004
100%
Passed
Tokens
697
Input
210
Total output
214
Reasoning within output
git_log_format f005
50%
Failed
Tokens
564
Input
356
Total output
349
Reasoning within output
git_log_format f006
100%
Passed
Tokens
690
Input
429
Total output
348
Reasoning within output
git_log_format f007
100%
Passed
Tokens
694
Input
254
Total output
248
Reasoning within output
git_log_format f008
100%
Passed
Tokens
925
Input
147
Total output
170
Reasoning within output
git_log_format f009
100%
Passed
Tokens
543
Input
209
Total output
208
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,015
Input
275
Total output
308
Reasoning within output
git_log_format f011
100%
Passed
Tokens
336
Input
163
Total output
167
Reasoning within output
git_log_format f012
100%
Passed
Tokens
329
Input
228
Total output
237
Reasoning within output
git_show f001
100%
Passed
Tokens
170
Input
223
Total output
236
Reasoning within output
git_show f002
0%
Failed
Tokens
169
Input
443
Total output
498
Reasoning within output
git_show f003
100%
Passed
Tokens
549
Input
344
Total output
332
Reasoning within output
git_show f004
100%
Passed
Tokens
389
Input
315
Total output
326
Reasoning within output
git_show f005
0%
Failed
Tokens
173
Input
574
Total output
640
Reasoning within output
git_show f006
100%
Passed
Tokens
175
Input
238
Total output
265
Reasoning within output
git_show f007
100%
Passed
Tokens
166
Input
258
Total output
277
Reasoning within output
git_show f008
100%
Passed
Tokens
178
Input
261
Total output
242
Reasoning within output
git_show f009
100%
Passed
Tokens
256
Input
272
Total output
252
Reasoning within output
git_show f010
100%
Passed
Tokens
167
Input
278
Total output
294
Reasoning within output
git_show f011
100%
Passed
Tokens
193
Input
246
Total output
278
Reasoning within output
git_show f012
100%
Passed
Tokens
286
Input
288
Total output
304
Reasoning within output
merge_conflicts f001
0%
Failed
Tokens
85
Input
553
Total output
641
Reasoning within output
merge_conflicts f002
0%
Failed
Tokens
105
Input
1,286
Total output
1,357
Reasoning within output
merge_conflicts f003
0%
Failed
Tokens
78
Input
865
Total output
1,040
Reasoning within output
merge_conflicts f004
0%
Failed
Tokens
131
Input
349
Total output
350
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
135
Input
371
Total output
423
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
120
Input
690
Total output
701
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
125
Input
263
Total output
296
Reasoning within output
merge_conflicts f008
0%
Failed
Tokens
107
Input
294
Total output
326
Reasoning within output
merge_conflicts f009
0%
Failed
Tokens
104
Input
593
Total output
640
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
173
Input
221
Total output
233
Reasoning within output
merge_conflicts f011
0%
Failed
Tokens
142
Input
471
Total output
434
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
222
Input
311
Total output
286
Reasoning within output
rebase f001
0%
Failed
Tokens
94
Input
696
Total output
788
Reasoning within output
rebase f002
100%
Passed
Tokens
120
Input
447
Total output
413
Reasoning within output
rebase f003
100%
Passed
Tokens
101
Input
435
Total output
496
Reasoning within output
rebase f004
0%
Failed
Tokens
141
Input
1,086
Total output
1,166
Reasoning within output
rebase f005
100%
Passed
Tokens
137
Input
556
Total output
625
Reasoning within output
rebase f006
0%
Failed
Tokens
130
Input
323
Total output
321
Reasoning within output
rebase f007
100%
Passed
Tokens
125
Input
378
Total output
411
Reasoning within output
rebase f008
100%
Passed
Tokens
119
Input
227
Total output
246
Reasoning within output
rebase f009
100%
Passed
Tokens
100
Input
341
Total output
377
Reasoning within output
rebase f010
100%
Passed
Tokens
199
Input
275
Total output
294
Reasoning within output
rebase f011
100%
Passed
Tokens
150
Input
719
Total output
651
Reasoning within output
rebase f012
0%
Failed
Tokens
250
Input
344
Total output
331
Reasoning within output
reflog f001
100%
Passed
Tokens
195
Input
660
Total output
632
Reasoning within output
reflog f002
100%
Passed
Tokens
199
Input
473
Total output
315
Reasoning within output
reflog f003
100%
Passed
Tokens
173
Input
418
Total output
298
Reasoning within output
reflog f004
100%
Passed
Tokens
269
Input
683
Total output
423
Reasoning within output
reflog f005
100%
Passed
Tokens
307
Input
587
Total output
475
Reasoning within output
reflog f006
100%
Passed
Tokens
205
Input
492
Total output
313
Reasoning within output
reflog f007
100%
Passed
Tokens
236
Input
1,039
Total output
743
Reasoning within output
reflog f008
100%
Passed
Tokens
307
Input
552
Total output
319
Reasoning within output
reflog f009
100%
Passed
Tokens
282
Input
639
Total output
366
Reasoning within output
reflog f010
100%
Passed
Tokens
232
Input
527
Total output
484
Reasoning within output
reflog f011
100%
Passed
Tokens
283
Input
595
Total output
460
Reasoning within output
reflog f012
100%
Passed
Tokens
256
Input
845
Total output
604
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
120
Input
232
Total output
148
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
257
Input
401
Total output
300
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
108
Input
303
Total output
197
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
106
Input
367
Total output
347
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
117
Input
362
Total output
254
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
164
Input
269
Total output
212
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
185
Input
395
Total output
253
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
157
Input
379
Total output
198
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
187
Input
432
Total output
279
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
116
Input
229
Total output
178
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
105
Input
354
Total output
259
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
119
Input
239
Total output
185
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
45
Input
292
Total output
318
Reasoning within output
submodule_usage f002
0%
Failed
Tokens
94
Input
523
Total output
606
Reasoning within output
submodule_usage f003
75%
Failed
Tokens
94
Input
1,078
Total output
1,190
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
82
Input
385
Total output
433
Reasoning within output
submodule_usage f005
0%
Failed
Tokens
52
Input
371
Total output
397
Reasoning within output
submodule_usage f006
0%
Failed
Tokens
79
Input
371
Total output
448
Reasoning within output
submodule_usage f007
0%
Failed
Tokens
52
Input
472
Total output
511
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
86
Input
297
Total output
330
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
87
Input
422
Total output
499
Reasoning within output
submodule_usage f010
0%
Failed
Tokens
89
Input
335
Total output
395
Reasoning within output
submodule_usage f011
0%
Failed
Tokens
93
Input
365
Total output
413
Reasoning within output
submodule_usage f012
0%
Failed
Tokens
50
Input
290
Total output
307
Reasoning within output
tag_management f001
100%
Passed
Tokens
57
Input
314
Total output
337
Reasoning within output
tag_management f002
100%
Passed
Tokens
57
Input
364
Total output
360
Reasoning within output
tag_management f003
50%
Failed
Tokens
63
Input
440
Total output
466
Reasoning within output
tag_management f004
100%
Passed
Tokens
69
Input
305
Total output
282
Reasoning within output
tag_management f005
100%
Passed
Tokens
80
Input
281
Total output
270
Reasoning within output
tag_management f006
100%
Passed
Tokens
67
Input
274
Total output
236
Reasoning within output
tag_management f007
100%
Passed
Tokens
64
Input
302
Total output
307
Reasoning within output
tag_management f008
33.3%
Failed
Tokens
68
Input
514
Total output
497
Reasoning within output
tag_management f009
0%
Failed
Tokens
69
Input
433
Total output
433
Reasoning within output
tag_management f010
100%
Passed
Tokens
49
Input
243
Total output
252
Reasoning within output
tag_management f011
100%
Passed
Tokens
48
Input
198
Total output
228
Reasoning within output
tag_management f012
100%
Passed
Tokens
82
Input
622
Total output
583
Reasoning within output
worktree_usage f001
25%
Failed
Tokens
122
Input
317
Total output
338
Reasoning within output
worktree_usage f002
0%
Failed
Tokens
127
Input
940
Total output
992
Reasoning within output
worktree_usage f003
0%
Failed
Tokens
179
Input
377
Total output
411
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
175
Input
348
Total output
394
Reasoning within output
worktree_usage f005
33.3%
Failed
Tokens
113
Input
349
Total output
387
Reasoning within output
worktree_usage f006
0%
Failed
Tokens
119
Input
1,100
Total output
1,109
Reasoning within output
worktree_usage f007
0%
Failed
Tokens
121
Input
480
Total output
486
Reasoning within output
worktree_usage f008
50%
Failed
Tokens
144
Input
624
Total output
606
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
212
Input
583
Total output
669
Reasoning within output
worktree_usage f010
50%
Failed
Tokens
184
Input
348
Total output
371
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
173
Input
301
Total output
344
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
115
Input
278
Total output
277
Reasoning within output