Minimax / minimax-m2.5
high
88.7%
181 / 204 fixtures · 1 run(s)
41,249 input / 92,454 total output / 89,548 reasoning within output tokens $0.10024155
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
+3.4%
Text: 88.7% →
JSON: 92.2%
+16
Gained
JSON pass / text fail
−9
Lost
Text pass / JSON fail
172
Unchanged Pass
Both pass
7
Unchanged Fail
Both fail
Fixture Reliability Delta
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| branch_cleanup | 100% | 75% | -25% |
| commit_messages | 83.3% | 100% | + 16.7% |
| git_show | 83.3% | 100% | + 16.7% |
| rebase | 75% | 91.7% | + 16.7% |
| reflog | 100% | 83.3% | -16.7% |
| submodule_usage | 83.3% | 100% | + 16.7% |
| merge_conflicts | 83.3% | 91.7% | + 8.3% |
| blame_forensics | 91.7% | 100% | + 8.3% |
| cherry_pick | 75% | 66.7% | -8.3% |
| git_clean | 75% | 83.3% | + 8.3% |
| git_grep | 91.7% | 100% | + 8.3% |
| git_log_format | 91.7% | 100% | + 8.3% |
| commit_squash | 91.7% | 91.7% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| tag_management | 91.7% | 91.7% | + 0% |
| worktree_usage | 91.7% | 91.7% | + 0% |
Changed Fixtures (25)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
246
Input
507
Total output
583
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
239
Input
368
Total output
363
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
257
Input
235
Total output
228
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
203
Input
371
Total output
364
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
263
Input
2,445
Total output
2,699
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
237
Input
356
Total output
342
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
215
Input
332
Total output
325
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
245
Input
409
Total output
407
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
203
Input
321
Total output
363
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
442
Input
645
Total output
640
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
240
Input
243
Total output
236
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
157
Input
633
Total output
705
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
132
Input
832
Total output
826
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
142
Input
624
Total output
672
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
120
Input
328
Total output
382
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
168
Input
947
Total output
940
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
132
Input
388
Total output
435
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
153
Input
227
Total output
262
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
129
Input
344
Total output
396
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
149
Input
502
Total output
491
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
114
Input
247
Total output
245
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
153
Input
204
Total output
197
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
100
Input
171
Total output
200
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
183
Input
441
Total output
428
Reasoning within output
cherry_pick f001
0%
Failed
Tokens
122
Input
420
Total output
414
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
145
Input
212
Total output
203
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
125
Input
367
Total output
417
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
174
Input
2,161
Total output
2,428
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
178
Input
270
Total output
316
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
164
Input
415
Total output
391
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
154
Input
213
Total output
203
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
159
Input
127
Total output
122
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
138
Input
182
Total output
189
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
238
Input
215
Total output
189
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
192
Input
345
Total output
287
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
287
Input
1,150
Total output
1,110
Reasoning within output
commit_messages f001
93.3%
Passed
Tokens
133
Input
127
Total output
122
Reasoning within output
commit_messages f002
85%
Passed
Tokens
227
Input
208
Total output
206
Reasoning within output
commit_messages f003
38.3%
Failed
Tokens
113
Input
190
Total output
189
Reasoning within output
commit_messages f004
92.7%
Passed
Tokens
134
Input
101
Total output
96
Reasoning within output
commit_messages f005
93.3%
Passed
Tokens
129
Input
124
Total output
139
Reasoning within output
commit_messages f006
38.3%
Failed
Tokens
163
Input
364
Total output
404
Reasoning within output
commit_messages f007
91.7%
Passed
Tokens
212
Input
170
Total output
153
Reasoning within output
commit_messages f008
91.7%
Passed
Tokens
100
Input
131
Total output
125
Reasoning within output
commit_messages f009
78.3%
Passed
Tokens
152
Input
240
Total output
230
Reasoning within output
commit_messages f010
96%
Passed
Tokens
288
Input
185
Total output
174
Reasoning within output
commit_messages f011
82.7%
Passed
Tokens
170
Input
179
Total output
172
Reasoning within output
commit_messages f012
91.7%
Passed
Tokens
149
Input
128
Total output
147
Reasoning within output
commit_squash f001
100%
Passed
Tokens
168
Input
261
Total output
248
Reasoning within output
commit_squash f002
100%
Passed
Tokens
143
Input
205
Total output
208
Reasoning within output
commit_squash f003
100%
Passed
Tokens
154
Input
206
Total output
186
Reasoning within output
commit_squash f004
100%
Passed
Tokens
146
Input
801
Total output
788
Reasoning within output
commit_squash f005
0%
Failed
Tokens
140
Input
181
Total output
163
Reasoning within output
commit_squash f006
100%
Passed
Tokens
125
Input
182
Total output
183
Reasoning within output
commit_squash f007
100%
Passed
Tokens
136
Input
512
Total output
498
Reasoning within output
commit_squash f008
100%
Passed
Tokens
149
Input
609
Total output
595
Reasoning within output
commit_squash f009
100%
Passed
Tokens
133
Input
156
Total output
132
Reasoning within output
commit_squash f010
100%
Passed
Tokens
149
Input
190
Total output
176
Reasoning within output
commit_squash f011
100%
Passed
Tokens
156
Input
664
Total output
651
Reasoning within output
commit_squash f012
100%
Passed
Tokens
153
Input
619
Total output
597
Reasoning within output
git_bisect f001
100%
Passed
Tokens
202
Input
329
Total output
312
Reasoning within output
git_bisect f002
100%
Passed
Tokens
228
Input
233
Total output
228
Reasoning within output
git_bisect f003
100%
Passed
Tokens
225
Input
289
Total output
282
Reasoning within output
git_bisect f004
100%
Passed
Tokens
223
Input
351
Total output
345
Reasoning within output
git_bisect f005
100%
Passed
Tokens
217
Input
213
Total output
227
Reasoning within output
git_bisect f006
100%
Passed
Tokens
244
Input
418
Total output
418
Reasoning within output
git_bisect f007
100%
Passed
Tokens
223
Input
216
Total output
208
Reasoning within output
git_bisect f008
100%
Passed
Tokens
221
Input
282
Total output
297
Reasoning within output
git_bisect f009
100%
Passed
Tokens
215
Input
202
Total output
196
Reasoning within output
git_bisect f010
100%
Passed
Tokens
223
Input
280
Total output
273
Reasoning within output
git_bisect f011
100%
Passed
Tokens
223
Input
222
Total output
211
Reasoning within output
git_bisect f012
100%
Passed
Tokens
246
Input
416
Total output
416
Reasoning within output
git_clean f001
100%
Passed
Tokens
78
Input
253
Total output
287
Reasoning within output
git_clean f002
100%
Passed
Tokens
89
Input
155
Total output
150
Reasoning within output
git_clean f003
100%
Passed
Tokens
86
Input
258
Total output
294
Reasoning within output
git_clean f004
33.3%
Failed
Tokens
91
Input
886
Total output
1,031
Reasoning within output
git_clean f005
100%
Passed
Tokens
89
Input
267
Total output
261
Reasoning within output
git_clean f006
100%
Passed
Tokens
104
Input
177
Total output
191
Reasoning within output
git_clean f007
100%
Passed
Tokens
100
Input
201
Total output
192
Reasoning within output
git_clean f008
25%
Failed
Tokens
107
Input
137
Total output
147
Reasoning within output
git_clean f009
100%
Passed
Tokens
95
Input
103
Total output
92
Reasoning within output
git_clean f010
100%
Passed
Tokens
92
Input
304
Total output
298
Reasoning within output
git_clean f011
60%
Failed
Tokens
91
Input
169
Total output
162
Reasoning within output
git_clean f012
100%
Passed
Tokens
92
Input
679
Total output
669
Reasoning within output
git_grep f001
100%
Passed
Tokens
83
Input
370
Total output
365
Reasoning within output
git_grep f002
100%
Passed
Tokens
93
Input
118
Total output
126
Reasoning within output
git_grep f003
100%
Passed
Tokens
117
Input
126
Total output
135
Reasoning within output
git_grep f004
100%
Passed
Tokens
106
Input
165
Total output
158
Reasoning within output
git_grep f005
100%
Passed
Tokens
154
Input
188
Total output
185
Reasoning within output
git_grep f006
100%
Passed
Tokens
73
Input
386
Total output
457
Reasoning within output
git_grep f007
0%
Failed
Tokens
216
Input
5,627
Total output
5,624
Reasoning within output
git_grep f008
100%
Passed
Tokens
90
Input
155
Total output
182
Reasoning within output
git_grep f009
100%
Passed
Tokens
90
Input
89
Total output
84
Reasoning within output
git_grep f010
100%
Passed
Tokens
94
Input
291
Total output
316
Reasoning within output
git_grep f011
100%
Passed
Tokens
167
Input
272
Total output
269
Reasoning within output
git_grep f012
100%
Passed
Tokens
95
Input
106
Total output
106
Reasoning within output
git_log_format f001
100%
Passed
Tokens
734
Input
248
Total output
261
Reasoning within output
git_log_format f002
100%
Passed
Tokens
723
Input
258
Total output
249
Reasoning within output
git_log_format f003
100%
Passed
Tokens
582
Input
266
Total output
254
Reasoning within output
git_log_format f004
100%
Passed
Tokens
712
Input
189
Total output
173
Reasoning within output
git_log_format f005
100%
Passed
Tokens
599
Input
905
Total output
845
Reasoning within output
git_log_format f006
100%
Passed
Tokens
733
Input
503
Total output
392
Reasoning within output
git_log_format f007
100%
Passed
Tokens
757
Input
942
Total output
672
Reasoning within output
git_log_format f008
100%
Passed
Tokens
967
Input
118
Total output
115
Reasoning within output
git_log_format f009
100%
Passed
Tokens
606
Input
75
Total output
72
Reasoning within output
git_log_format f010
0%
Failed
Tokens
1,072
Input
148
Total output
149
Reasoning within output
git_log_format f011
100%
Passed
Tokens
379
Input
172
Total output
168
Reasoning within output
git_log_format f012
100%
Passed
Tokens
351
Input
121
Total output
120
Reasoning within output
git_show f001
100%
Passed
Tokens
195
Input
150
Total output
150
Reasoning within output
git_show f002
0%
Failed
Tokens
220
Input
518
Total output
514
Reasoning within output
git_show f003
100%
Passed
Tokens
661
Input
87
Total output
79
Reasoning within output
git_show f004
100%
Passed
Tokens
413
Input
246
Total output
238
Reasoning within output
git_show f005
0%
Failed
Tokens
209
Input
188
Total output
179
Reasoning within output
git_show f006
100%
Passed
Tokens
228
Input
210
Total output
207
Reasoning within output
git_show f007
100%
Passed
Tokens
195
Input
165
Total output
175
Reasoning within output
git_show f008
100%
Passed
Tokens
209
Input
130
Total output
106
Reasoning within output
git_show f009
100%
Passed
Tokens
298
Input
233
Total output
201
Reasoning within output
git_show f010
100%
Passed
Tokens
196
Input
125
Total output
122
Reasoning within output
git_show f011
100%
Passed
Tokens
246
Input
109
Total output
105
Reasoning within output
git_show f012
100%
Passed
Tokens
321
Input
135
Total output
132
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
115
Input
580
Total output
574
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
142
Input
382
Total output
373
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
112
Input
396
Total output
391
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
161
Input
561
Total output
538
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
166
Input
207
Total output
219
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
150
Input
525
Total output
504
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
155
Input
198
Total output
182
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
139
Input
228
Total output
221
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
135
Input
313
Total output
347
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
205
Input
471
Total output
506
Reasoning within output
merge_conflicts f011
0%
Failed
Tokens
178
Input
519
Total output
477
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
256
Input
830
Total output
846
Reasoning within output
rebase f001
0%
Failed
Tokens
134
Input
379
Total output
373
Reasoning within output
rebase f002
100%
Passed
Tokens
153
Input
109
Total output
104
Reasoning within output
rebase f003
100%
Passed
Tokens
134
Input
104
Total output
118
Reasoning within output
rebase f004
0%
Failed
Tokens
172
Input
1,813
Total output
1,975
Reasoning within output
rebase f005
100%
Passed
Tokens
170
Input
261
Total output
286
Reasoning within output
rebase f006
100%
Passed
Tokens
163
Input
236
Total output
195
Reasoning within output
rebase f007
100%
Passed
Tokens
156
Input
138
Total output
136
Reasoning within output
rebase f008
100%
Passed
Tokens
150
Input
331
Total output
384
Reasoning within output
rebase f009
100%
Passed
Tokens
133
Input
271
Total output
264
Reasoning within output
rebase f010
100%
Passed
Tokens
230
Input
897
Total output
1,021
Reasoning within output
rebase f011
100%
Passed
Tokens
183
Input
547
Total output
479
Reasoning within output
rebase f012
0%
Failed
Tokens
283
Input
755
Total output
715
Reasoning within output
reflog f001
100%
Passed
Tokens
229
Input
434
Total output
332
Reasoning within output
reflog f002
100%
Passed
Tokens
227
Input
652
Total output
416
Reasoning within output
reflog f003
100%
Passed
Tokens
210
Input
465
Total output
336
Reasoning within output
reflog f004
100%
Passed
Tokens
303
Input
2,559
Total output
2,059
Reasoning within output
reflog f005
100%
Passed
Tokens
350
Input
923
Total output
694
Reasoning within output
reflog f006
100%
Passed
Tokens
247
Input
1,010
Total output
592
Reasoning within output
reflog f007
100%
Passed
Tokens
269
Input
2,137
Total output
1,902
Reasoning within output
reflog f008
100%
Passed
Tokens
325
Input
1,798
Total output
1,649
Reasoning within output
reflog f009
100%
Passed
Tokens
298
Input
1,389
Total output
1,112
Reasoning within output
reflog f010
100%
Passed
Tokens
266
Input
982
Total output
772
Reasoning within output
reflog f011
100%
Passed
Tokens
298
Input
3,879
Total output
3,606
Reasoning within output
reflog f012
100%
Passed
Tokens
320
Input
2,037
Total output
1,736
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
150
Input
177
Total output
155
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
323
Input
555
Total output
458
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
139
Input
344
Total output
312
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
139
Input
159
Total output
163
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
148
Input
141
Total output
119
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
196
Input
233
Total output
191
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
215
Input
338
Total output
315
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
191
Input
312
Total output
331
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
221
Input
290
Total output
244
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
148
Input
218
Total output
214
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
137
Input
310
Total output
275
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
149
Input
171
Total output
174
Reasoning within output
submodule_usage f001
0%
Failed
Tokens
78
Input
401
Total output
438
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
119
Input
482
Total output
476
Reasoning within output
submodule_usage f003
50%
Failed
Tokens
127
Input
1,551
Total output
1,700
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
115
Input
83
Total output
99
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
80
Input
1,009
Total output
982
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
111
Input
131
Total output
167
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
80
Input
117
Total output
109
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
119
Input
1,603
Total output
1,596
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
112
Input
43
Total output
39
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
122
Input
230
Total output
222
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
125
Input
75
Total output
86
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
81
Input
76
Total output
63
Reasoning within output
tag_management f001
100%
Passed
Tokens
84
Input
62
Total output
55
Reasoning within output
tag_management f002
100%
Passed
Tokens
86
Input
117
Total output
98
Reasoning within output
tag_management f003
100%
Passed
Tokens
91
Input
594
Total output
551
Reasoning within output
tag_management f004
100%
Passed
Tokens
100
Input
66
Total output
62
Reasoning within output
tag_management f005
100%
Passed
Tokens
110
Input
191
Total output
185
Reasoning within output
tag_management f006
100%
Passed
Tokens
89
Input
228
Total output
203
Reasoning within output
tag_management f007
100%
Passed
Tokens
93
Input
559
Total output
458
Reasoning within output
tag_management f008
100%
Passed
Tokens
98
Input
622
Total output
601
Reasoning within output
tag_management f009
100%
Passed
Tokens
100
Input
116
Total output
98
Reasoning within output
tag_management f010
100%
Passed
Tokens
85
Input
41
Total output
32
Reasoning within output
tag_management f011
0%
Failed
Tokens
80
Input
216
Total output
236
Reasoning within output
tag_management f012
100%
Passed
Tokens
112
Input
498
Total output
485
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
154
Input
82
Total output
81
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
152
Input
1,044
Total output
1,103
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
206
Input
183
Total output
202
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
212
Input
202
Total output
201
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
145
Input
116
Total output
124
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
148
Input
240
Total output
214
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
151
Input
818
Total output
806
Reasoning within output
worktree_usage f008
50%
Failed
Tokens
171
Input
1,139
Total output
1,126
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
241
Input
342
Total output
337
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
219
Input
180
Total output
164
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
209
Input
110
Total output
108
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
163
Input
219
Total output
204
Reasoning within output