Arcee-ai / trinity-mini
low
76.5%
156 / 204 fixtures · 1 run(s)
34,424 input / 98,694 total output / 100,477 reasoning within output tokens $0.01635318
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-3.9%
Text: 76.5% →
JSON: 72.6%
+17
Gained
JSON pass / text fail
−26
Lost
Text pass / JSON fail
130
Unchanged Pass
Both pass
31
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|---|---|---|
| f011 | 0% (0/1) | 100% (1/1) | -100% |
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| commit_squash | 41.7% | 0% | -41.7% |
| cherry_pick | 50% | 66.7% | + 16.7% |
| git_clean | 50% | 66.7% | + 16.7% |
| rebase | 75% | 58.3% | -16.7% |
| reflog | 100% | 83.3% | -16.7% |
| submodule_usage | 50% | 66.7% | + 16.7% |
| tag_management | 91.7% | 75% | -16.7% |
| blame_forensics | 66.7% | 58.3% | -8.3% |
| git_show | 91.7% | 83.3% | -8.3% |
| branch_cleanup | 100% | 91.7% | -8.3% |
| commit_messages | 91.7% | 100% | + 8.3% |
| git_bisect | 100% | 91.7% | -8.3% |
| git_grep | 100% | 91.7% | -8.3% |
| worktree_usage | 41.7% | 50% | + 8.3% |
| git_log_format | 91.7% | 91.7% | + 0% |
| merge_conflicts | 58.3% | 58.3% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
Changed Fixtures (43)
f001 -loss f005 +gain f007 +gain f008 -loss f012 -loss f001 -loss f001 -loss f003 +gain f004 +gain f010 +gain f011 +gain f003 -loss f005 -loss f006 -loss f007 -loss f010 -loss f012 -loss f001 +gain f005 -loss f007 -loss f008 +gain f009 +gain f010 -loss f003 +gain f006 -loss f005 -loss f001 -loss f004 +gain f008 +gain f009 -loss f010 +gain f011 -loss f008 -loss f011 -loss f005 -loss f012 -loss f001 +gain f007 +gain f006 -loss f009 -loss f001 +gain f006 -loss f011 +gain
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
211
Input
356
Total output
404
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
203
Input
405
Total output
433
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
223
Input
309
Total output
320
Reasoning within output
blame_forensics f004
0%
Failed
Tokens
167
Input
544
Total output
568
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
235
Input
420
Total output
460
Reasoning within output
blame_forensics f006
0%
Failed
Tokens
209
Input
904
Total output
940
Reasoning within output
blame_forensics f007
0%
Failed
Tokens
178
Input
445
Total output
456
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
211
Input
531
Total output
597
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
176
Input
450
Total output
484
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
360
Input
1,060
Total output
1,210
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
207
Input
285
Total output
300
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
133
Input
619
Total output
631
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
99
Input
458
Total output
492
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
115
Input
349
Total output
375
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
91
Input
296
Total output
345
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
120
Input
406
Total output
472
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
98
Input
353
Total output
408
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
116
Input
431
Total output
483
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
106
Input
273
Total output
317
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
117
Input
261
Total output
262
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
79
Input
538
Total output
664
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
112
Input
228
Total output
232
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
70
Input
328
Total output
388
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
149
Input
282
Total output
287
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
92
Input
579
Total output
694
Reasoning within output
cherry_pick f002
0%
Failed
Tokens
114
Input
395
Total output
366
Reasoning within output
cherry_pick f003
0%
Failed
Tokens
86
Input
1,001
Total output
1,164
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
143
Input
436
Total output
496
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
147
Input
650
Total output
755
Reasoning within output
cherry_pick f006
0%
Failed
Tokens
132
Input
618
Total output
645
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
121
Input
512
Total output
567
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
121
Input
287
Total output
325
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
104
Input
264
Total output
296
Reasoning within output
cherry_pick f010
0%
Failed
Tokens
205
Input
234
Total output
234
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
158
Input
657
Total output
628
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
254
Input
325
Total output
303
Reasoning within output
commit_messages f001
95%
Passed
Tokens
100
Input
225
Total output
228
Reasoning within output
commit_messages f002
88.7%
Passed
Tokens
195
Input
361
Total output
373
Reasoning within output
commit_messages f003
71%
Passed
Tokens
82
Input
375
Total output
415
Reasoning within output
commit_messages f004
92.7%
Passed
Tokens
104
Input
253
Total output
285
Reasoning within output
commit_messages f005
84.7%
Passed
Tokens
98
Input
277
Total output
292
Reasoning within output
commit_messages f006
90%
Passed
Tokens
128
Input
480
Total output
555
Reasoning within output
commit_messages f007
73.3%
Passed
Tokens
174
Input
307
Total output
346
Reasoning within output
commit_messages f008
89.3%
Passed
Tokens
71
Input
308
Total output
338
Reasoning within output
commit_messages f009
72%
Passed
Tokens
122
Input
1,546
Total output
1,637
Reasoning within output
commit_messages f010
75.3%
Passed
Tokens
255
Input
903
Total output
985
Reasoning within output
commit_messages f011
48.3%
Failed
Tokens
140
Input
344
Total output
372
Reasoning within output
commit_messages f012
93.3%
Passed
Tokens
119
Input
199
Total output
230
Reasoning within output
commit_squash f001
50%
Failed
Tokens
129
Input
679
Total output
732
Reasoning within output
commit_squash f002
0%
Failed
Tokens
115
Input
432
Total output
465
Reasoning within output
commit_squash f003
100%
Passed
Tokens
122
Input
467
Total output
499
Reasoning within output
commit_squash f004
50%
Failed
Tokens
111
Input
338
Total output
359
Reasoning within output
commit_squash f005
100%
Passed
Tokens
110
Input
781
Total output
849
Reasoning within output
commit_squash f006
100%
Passed
Tokens
92
Input
420
Total output
468
Reasoning within output
commit_squash f007
100%
Passed
Tokens
96
Input
327
Total output
332
Reasoning within output
commit_squash f008
0%
Failed
Tokens
109
Input
341
Total output
344
Reasoning within output
commit_squash f009
0%
Failed
Tokens
102
Input
417
Total output
435
Reasoning within output
commit_squash f010
100%
Passed
Tokens
118
Input
305
Total output
323
Reasoning within output
commit_squash f011
50%
Failed
Tokens
123
Input
501
Total output
487
Reasoning within output
commit_squash f012
66.7%
Failed
Tokens
123
Input
317
Total output
276
Reasoning within output
git_bisect f001
100%
Passed
Tokens
169
Input
576
Total output
584
Reasoning within output
git_bisect f002
100%
Passed
Tokens
196
Input
1,386
Total output
1,363
Reasoning within output
git_bisect f003
100%
Passed
Tokens
186
Input
1,050
Total output
1,069
Reasoning within output
git_bisect f004
100%
Passed
Tokens
190
Input
346
Total output
352
Reasoning within output
git_bisect f005
100%
Passed
Tokens
192
Input
649
Total output
664
Reasoning within output
git_bisect f006
100%
Passed
Tokens
217
Input
663
Total output
636
Reasoning within output
git_bisect f007
100%
Passed
Tokens
196
Input
741
Total output
755
Reasoning within output
git_bisect f008
100%
Passed
Tokens
192
Input
841
Total output
783
Reasoning within output
git_bisect f009
100%
Passed
Tokens
188
Input
864
Total output
912
Reasoning within output
git_bisect f010
100%
Passed
Tokens
200
Input
439
Total output
416
Reasoning within output
git_bisect f011
100%
Passed
Tokens
188
Input
550
Total output
520
Reasoning within output
git_bisect f012
100%
Passed
Tokens
219
Input
570
Total output
518
Reasoning within output
git_clean f001
50%
Failed
Tokens
50
Input
385
Total output
422
Reasoning within output
git_clean f002
100%
Passed
Tokens
61
Input
320
Total output
376
Reasoning within output
git_clean f003
100%
Passed
Tokens
58
Input
538
Total output
604
Reasoning within output
git_clean f004
33.3%
Failed
Tokens
58
Input
847
Total output
1,011
Reasoning within output
git_clean f005
100%
Passed
Tokens
50
Input
373
Total output
409
Reasoning within output
git_clean f006
100%
Passed
Tokens
73
Input
292
Total output
306
Reasoning within output
git_clean f007
100%
Passed
Tokens
65
Input
341
Total output
373
Reasoning within output
git_clean f008
25%
Failed
Tokens
72
Input
335
Total output
375
Reasoning within output
git_clean f009
75%
Failed
Tokens
65
Input
957
Total output
1,083
Reasoning within output
git_clean f010
100%
Passed
Tokens
61
Input
351
Total output
406
Reasoning within output
git_clean f011
80%
Failed
Tokens
62
Input
381
Total output
415
Reasoning within output
git_clean f012
50%
Failed
Tokens
64
Input
980
Total output
1,081
Reasoning within output
git_grep f001
100%
Passed
Tokens
53
Input
378
Total output
431
Reasoning within output
git_grep f002
100%
Passed
Tokens
64
Input
192
Total output
200
Reasoning within output
git_grep f003
100%
Passed
Tokens
86
Input
273
Total output
317
Reasoning within output
git_grep f004
100%
Passed
Tokens
78
Input
280
Total output
277
Reasoning within output
git_grep f005
100%
Passed
Tokens
106
Input
257
Total output
283
Reasoning within output
git_grep f006
100%
Passed
Tokens
43
Input
263
Total output
276
Reasoning within output
git_grep f007
100%
Passed
Tokens
158
Input
832
Total output
781
Reasoning within output
git_grep f008
100%
Passed
Tokens
60
Input
310
Total output
358
Reasoning within output
git_grep f009
100%
Passed
Tokens
56
Input
174
Total output
175
Reasoning within output
git_grep f010
100%
Passed
Tokens
64
Input
232
Total output
247
Reasoning within output
git_grep f011
100%
Passed
Tokens
110
Input
390
Total output
364
Reasoning within output
git_grep f012
100%
Passed
Tokens
67
Input
348
Total output
379
Reasoning within output
git_log_format f001
100%
Passed
Tokens
722
Input
292
Total output
295
Reasoning within output
git_log_format f002
100%
Passed
Tokens
683
Input
492
Total output
569
Reasoning within output
git_log_format f003
50%
Failed
Tokens
566
Input
318
Total output
325
Reasoning within output
git_log_format f004
100%
Passed
Tokens
679
Input
258
Total output
260
Reasoning within output
git_log_format f005
100%
Passed
Tokens
564
Input
341
Total output
343
Reasoning within output
git_log_format f006
100%
Passed
Tokens
690
Input
643
Total output
539
Reasoning within output
git_log_format f007
100%
Passed
Tokens
703
Input
274
Total output
286
Reasoning within output
git_log_format f008
100%
Passed
Tokens
908
Input
226
Total output
249
Reasoning within output
git_log_format f009
100%
Passed
Tokens
575
Input
190
Total output
203
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,035
Input
281
Total output
313
Reasoning within output
git_log_format f011
100%
Passed
Tokens
345
Input
246
Total output
251
Reasoning within output
git_log_format f012
100%
Passed
Tokens
319
Input
224
Total output
226
Reasoning within output
git_show f001
100%
Passed
Tokens
166
Input
349
Total output
369
Reasoning within output
git_show f002
0%
Failed
Tokens
165
Input
334
Total output
345
Reasoning within output
git_show f003
100%
Passed
Tokens
557
Input
339
Total output
327
Reasoning within output
git_show f004
100%
Passed
Tokens
383
Input
331
Total output
337
Reasoning within output
git_show f005
100%
Passed
Tokens
177
Input
364
Total output
381
Reasoning within output
git_show f006
100%
Passed
Tokens
179
Input
222
Total output
246
Reasoning within output
git_show f007
100%
Passed
Tokens
166
Input
325
Total output
374
Reasoning within output
git_show f008
100%
Passed
Tokens
182
Input
296
Total output
276
Reasoning within output
git_show f009
100%
Passed
Tokens
262
Input
255
Total output
244
Reasoning within output
git_show f010
100%
Passed
Tokens
165
Input
256
Total output
279
Reasoning within output
git_show f011
100%
Passed
Tokens
193
Input
225
Total output
244
Reasoning within output
git_show f012
100%
Passed
Tokens
286
Input
312
Total output
325
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
85
Input
378
Total output
424
Reasoning within output
merge_conflicts f002
0%
Failed
Tokens
105
Input
1,207
Total output
1,237
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
78
Input
1,009
Total output
1,217
Reasoning within output
merge_conflicts f004
0%
Failed
Tokens
131
Input
256
Total output
279
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
135
Input
365
Total output
413
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
120
Input
330
Total output
326
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
125
Input
247
Total output
278
Reasoning within output
merge_conflicts f008
0%
Failed
Tokens
107
Input
344
Total output
398
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
104
Input
400
Total output
422
Reasoning within output
merge_conflicts f010
0%
Failed
Tokens
173
Input
994
Total output
1,107
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
142
Input
586
Total output
571
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
222
Input
343
Total output
321
Reasoning within output
rebase f001
0%
Failed
Tokens
94
Input
1,377
Total output
1,620
Reasoning within output
rebase f002
100%
Passed
Tokens
123
Input
961
Total output
988
Reasoning within output
rebase f003
100%
Passed
Tokens
100
Input
586
Total output
655
Reasoning within output
rebase f004
100%
Passed
Tokens
141
Input
1,297
Total output
1,376
Reasoning within output
rebase f005
100%
Passed
Tokens
138
Input
305
Total output
352
Reasoning within output
rebase f006
0%
Failed
Tokens
130
Input
368
Total output
368
Reasoning within output
rebase f007
100%
Passed
Tokens
125
Input
334
Total output
380
Reasoning within output
rebase f008
100%
Passed
Tokens
120
Input
302
Total output
343
Reasoning within output
rebase f009
100%
Passed
Tokens
100
Input
388
Total output
420
Reasoning within output
rebase f010
100%
Passed
Tokens
199
Input
406
Total output
429
Reasoning within output
rebase f011
100%
Passed
Tokens
149
Input
430
Total output
400
Reasoning within output
rebase f012
0%
Failed
Tokens
250
Input
562
Total output
537
Reasoning within output
reflog f001
100%
Passed
Tokens
205
Input
434
Total output
401
Reasoning within output
reflog f002
100%
Passed
Tokens
188
Input
570
Total output
405
Reasoning within output
reflog f003
100%
Passed
Tokens
172
Input
517
Total output
332
Reasoning within output
reflog f004
100%
Passed
Tokens
274
Input
740
Total output
511
Reasoning within output
reflog f005
100%
Passed
Tokens
311
Input
604
Total output
457
Reasoning within output
reflog f006
100%
Passed
Tokens
224
Input
589
Total output
383
Reasoning within output
reflog f007
100%
Passed
Tokens
245
Input
727
Total output
459
Reasoning within output
reflog f008
100%
Passed
Tokens
282
Input
883
Total output
664
Reasoning within output
reflog f009
100%
Passed
Tokens
260
Input
680
Total output
425
Reasoning within output
reflog f010
100%
Passed
Tokens
228
Input
905
Total output
617
Reasoning within output
reflog f011
100%
Passed
Tokens
267
Input
573
Total output
427
Reasoning within output
reflog f012
100%
Passed
Tokens
273
Input
932
Total output
726
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
122
Input
322
Total output
249
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
254
Input
433
Total output
261
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
108
Input
298
Total output
188
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
106
Input
339
Total output
303
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
119
Input
406
Total output
307
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
164
Input
265
Total output
222
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
187
Input
428
Total output
256
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
157
Input
394
Total output
280
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
187
Input
505
Total output
339
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
116
Input
314
Total output
268
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
106
Input
320
Total output
203
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
119
Input
345
Total output
229
Reasoning within output
submodule_usage f001
0%
Failed
Tokens
45
Input
309
Total output
337
Reasoning within output
submodule_usage f002
0%
Failed
Tokens
91
Input
914
Total output
1,069
Reasoning within output
submodule_usage f003
25%
Failed
Tokens
99
Input
2,496
Total output
2,713
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
87
Input
239
Total output
281
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
52
Input
365
Total output
391
Reasoning within output
submodule_usage f006
0%
Failed
Tokens
83
Input
324
Total output
370
Reasoning within output
submodule_usage f007
0%
Failed
Tokens
52
Input
266
Total output
271
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
87
Input
337
Total output
376
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
83
Input
724
Total output
776
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
90
Input
413
Total output
479
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
91
Input
266
Total output
309
Reasoning within output
submodule_usage f012
0%
Failed
Tokens
50
Input
307
Total output
334
Reasoning within output
tag_management f001
100%
Passed
Tokens
57
Input
233
Total output
244
Reasoning within output
tag_management f002
100%
Passed
Tokens
59
Input
381
Total output
369
Reasoning within output
tag_management f003
100%
Passed
Tokens
62
Input
284
Total output
279
Reasoning within output
tag_management f004
100%
Passed
Tokens
67
Input
335
Total output
359
Reasoning within output
tag_management f005
100%
Passed
Tokens
80
Input
294
Total output
288
Reasoning within output
tag_management f006
100%
Passed
Tokens
62
Input
1,653
Total output
1,589
Reasoning within output
tag_management f007
100%
Passed
Tokens
64
Input
293
Total output
304
Reasoning within output
tag_management f008
66.7%
Failed
Tokens
67
Input
659
Total output
637
Reasoning within output
tag_management f009
100%
Passed
Tokens
71
Input
354
Total output
341
Reasoning within output
tag_management f010
100%
Passed
Tokens
50
Input
252
Total output
256
Reasoning within output
tag_management f011
100%
Passed
Tokens
48
Input
388
Total output
434
Reasoning within output
tag_management f012
100%
Passed
Tokens
82
Input
397
Total output
367
Reasoning within output
worktree_usage f001
25%
Failed
Tokens
122
Input
330
Total output
349
Reasoning within output
worktree_usage f002
0%
Failed
Tokens
129
Input
732
Total output
782
Reasoning within output
worktree_usage f003
0%
Failed
Tokens
178
Input
293
Total output
325
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
174
Input
370
Total output
398
Reasoning within output
worktree_usage f005
33.3%
Failed
Tokens
115
Input
302
Total output
329
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
115
Input
1,402
Total output
1,443
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
119
Input
451
Total output
464
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
140
Input
1,012
Total output
1,025
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
203
Input
510
Total output
614
Reasoning within output
worktree_usage f010
0%
Failed
Tokens
194
Input
357
Total output
372
Reasoning within output
worktree_usage f011
0%
Failed
Tokens
179
Input
377
Total output
388
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
120
Input
288
Total output
289
Reasoning within output