Minimax / minimax-m2.7
xhigh
96.6%
197 / 204 fixtures · 1 run(s)
40,742 input / 96,038 total output / 92,231 reasoning within output tokens $0.13925050
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-27.4%
Text: 96.6% →
JSON: 69.1%
+1
Gained
JSON pass / text fail
−57
Lost
Text pass / JSON fail
140
Unchanged Pass
Both pass
6
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| stash_recovery | 100% | 33.3% | -66.7% |
| tag_management | 100% | 50% | -50% |
| commit_messages | 100% | 58.3% | -41.7% |
| commit_squash | 91.7% | 58.3% | -33.3% |
| rebase | 91.7% | 58.3% | -33.3% |
| branch_cleanup | 100% | 66.7% | -33.3% |
| git_log_format | 100% | 66.7% | -33.3% |
| git_bisect | 100% | 75% | -25% |
| git_clean | 100% | 75% | -25% |
| git_grep | 100% | 75% | -25% |
| git_show | 100% | 75% | -25% |
| reflog | 100% | 75% | -25% |
| cherry_pick | 91.7% | 75% | -16.7% |
| merge_conflicts | 83.3% | 66.7% | -16.7% |
| submodule_usage | 91.7% | 83.3% | -8.3% |
| worktree_usage | 100% | 91.7% | -8.3% |
| blame_forensics | 91.7% | 91.7% | + 0% |
Changed Fixtures (58)
f003 -loss f007 -loss f009 -loss f011 -loss f005 -loss f009 -loss f001 -loss f002 -loss f003 -loss f005 -loss f006 -loss f006 -loss f008 -loss f010 -loss f012 -loss f006 -loss f009 -loss f012 -loss f001 -loss f010 -loss f011 -loss f004 -loss f006 -loss f008 -loss f001 -loss f005 -loss f006 -loss f012 -loss f002 -loss f003 -loss f010 -loss f002 -loss f004 -loss f009 +gain f011 -loss f003 -loss f005 -loss f007 -loss f011 -loss f006 -loss f010 -loss f011 -loss f001 -loss f002 -loss f004 -loss f005 -loss f007 -loss f008 -loss f009 -loss f010 -loss f009 -loss f002 -loss f005 -loss f007 -loss f009 -loss f011 -loss f012 -loss f002 -loss
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
251
Input
948
Total output
940
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
237
Input
527
Total output
522
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
259
Input
228
Total output
235
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
199
Input
481
Total output
473
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
266
Input
1,579
Total output
1,572
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
237
Input
489
Total output
470
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
211
Input
350
Total output
342
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
241
Input
801
Total output
846
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
206
Input
415
Total output
432
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
396
Input
354
Total output
348
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
235
Input
213
Total output
207
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
160
Input
518
Total output
546
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
134
Input
403
Total output
397
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
144
Input
173
Total output
167
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
124
Input
873
Total output
871
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
157
Input
418
Total output
410
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
131
Input
169
Total output
188
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
153
Input
120
Total output
111
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
137
Input
297
Total output
291
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
146
Input
263
Total output
252
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
115
Input
283
Total output
281
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
145
Input
230
Total output
222
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
98
Input
131
Total output
152
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
166
Input
107
Total output
105
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
125
Input
667
Total output
661
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
149
Input
502
Total output
494
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
119
Input
703
Total output
844
Reasoning within output
cherry_pick f004
100%
Passed
Tokens
175
Input
943
Total output
921
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
181
Input
217
Total output
200
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
165
Input
239
Total output
214
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
138
Input
190
Total output
183
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
152
Input
247
Total output
272
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
136
Input
316
Total output
340
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
243
Input
749
Total output
724
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
193
Input
512
Total output
445
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
292
Input
886
Total output
842
Reasoning within output
commit_messages f001
85%
Passed
Tokens
133
Input
236
Total output
252
Reasoning within output
commit_messages f002
82%
Passed
Tokens
227
Input
288
Total output
240
Reasoning within output
commit_messages f003
87.3%
Passed
Tokens
97
Input
218
Total output
224
Reasoning within output
commit_messages f004
94.3%
Passed
Tokens
134
Input
169
Total output
164
Reasoning within output
commit_messages f005
81.7%
Passed
Tokens
129
Input
138
Total output
147
Reasoning within output
commit_messages f006
92.7%
Passed
Tokens
163
Input
221
Total output
252
Reasoning within output
commit_messages f007
93.3%
Passed
Tokens
212
Input
196
Total output
206
Reasoning within output
commit_messages f008
91%
Passed
Tokens
100
Input
162
Total output
156
Reasoning within output
commit_messages f009
87.7%
Passed
Tokens
152
Input
195
Total output
186
Reasoning within output
commit_messages f010
90%
Passed
Tokens
288
Input
229
Total output
219
Reasoning within output
commit_messages f011
82.7%
Passed
Tokens
170
Input
407
Total output
429
Reasoning within output
commit_messages f012
91%
Passed
Tokens
149
Input
186
Total output
218
Reasoning within output
commit_squash f001
100%
Passed
Tokens
164
Input
655
Total output
640
Reasoning within output
commit_squash f002
100%
Passed
Tokens
144
Input
322
Total output
341
Reasoning within output
commit_squash f003
100%
Passed
Tokens
154
Input
310
Total output
297
Reasoning within output
commit_squash f004
100%
Failed
Tokens
143
Input
576
Total output
560
Reasoning within output
commit_squash f005
100%
Passed
Tokens
143
Input
364
Total output
356
Reasoning within output
commit_squash f006
100%
Passed
Tokens
125
Input
418
Total output
473
Reasoning within output
commit_squash f007
100%
Passed
Tokens
126
Input
280
Total output
292
Reasoning within output
commit_squash f008
100%
Passed
Tokens
146
Input
521
Total output
507
Reasoning within output
commit_squash f009
100%
Passed
Tokens
134
Input
371
Total output
358
Reasoning within output
commit_squash f010
100%
Passed
Tokens
148
Input
485
Total output
497
Reasoning within output
commit_squash f011
100%
Passed
Tokens
157
Input
308
Total output
297
Reasoning within output
commit_squash f012
100%
Passed
Tokens
149
Input
411
Total output
389
Reasoning within output
git_bisect f001
100%
Passed
Tokens
198
Input
267
Total output
262
Reasoning within output
git_bisect f002
100%
Passed
Tokens
227
Input
318
Total output
311
Reasoning within output
git_bisect f003
100%
Passed
Tokens
219
Input
318
Total output
311
Reasoning within output
git_bisect f004
100%
Passed
Tokens
219
Input
331
Total output
307
Reasoning within output
git_bisect f005
100%
Passed
Tokens
223
Input
593
Total output
586
Reasoning within output
git_bisect f006
100%
Passed
Tokens
247
Input
434
Total output
428
Reasoning within output
git_bisect f007
100%
Passed
Tokens
221
Input
903
Total output
895
Reasoning within output
git_bisect f008
100%
Passed
Tokens
225
Input
346
Total output
316
Reasoning within output
git_bisect f009
100%
Passed
Tokens
219
Input
305
Total output
255
Reasoning within output
git_bisect f010
100%
Passed
Tokens
207
Input
423
Total output
283
Reasoning within output
git_bisect f011
100%
Passed
Tokens
209
Input
255
Total output
205
Reasoning within output
git_bisect f012
100%
Passed
Tokens
248
Input
367
Total output
358
Reasoning within output
git_clean f001
100%
Passed
Tokens
78
Input
312
Total output
303
Reasoning within output
git_clean f002
100%
Passed
Tokens
89
Input
296
Total output
289
Reasoning within output
git_clean f003
100%
Passed
Tokens
86
Input
259
Total output
266
Reasoning within output
git_clean f004
100%
Passed
Tokens
86
Input
1,315
Total output
1,308
Reasoning within output
git_clean f005
100%
Passed
Tokens
80
Input
628
Total output
621
Reasoning within output
git_clean f006
100%
Passed
Tokens
104
Input
793
Total output
858
Reasoning within output
git_clean f007
100%
Passed
Tokens
100
Input
564
Total output
552
Reasoning within output
git_clean f008
100%
Passed
Tokens
102
Input
221
Total output
232
Reasoning within output
git_clean f009
100%
Passed
Tokens
95
Input
524
Total output
587
Reasoning within output
git_clean f010
100%
Passed
Tokens
92
Input
312
Total output
343
Reasoning within output
git_clean f011
100%
Passed
Tokens
75
Input
195
Total output
207
Reasoning within output
git_clean f012
100%
Passed
Tokens
92
Input
1,261
Total output
1,251
Reasoning within output
git_grep f001
100%
Passed
Tokens
86
Input
164
Total output
160
Reasoning within output
git_grep f002
100%
Passed
Tokens
94
Input
120
Total output
125
Reasoning within output
git_grep f003
100%
Passed
Tokens
120
Input
116
Total output
114
Reasoning within output
git_grep f004
100%
Passed
Tokens
111
Input
143
Total output
134
Reasoning within output
git_grep f005
100%
Passed
Tokens
139
Input
247
Total output
245
Reasoning within output
git_grep f006
100%
Passed
Tokens
71
Input
376
Total output
422
Reasoning within output
git_grep f007
100%
Passed
Tokens
187
Input
6,390
Total output
6,386
Reasoning within output
git_grep f008
100%
Passed
Tokens
90
Input
231
Total output
228
Reasoning within output
git_grep f009
100%
Passed
Tokens
84
Input
119
Total output
114
Reasoning within output
git_grep f010
100%
Passed
Tokens
97
Input
569
Total output
567
Reasoning within output
git_grep f011
100%
Passed
Tokens
138
Input
220
Total output
217
Reasoning within output
git_grep f012
100%
Passed
Tokens
97
Input
139
Total output
130
Reasoning within output
git_log_format f001
100%
Passed
Tokens
743
Input
172
Total output
168
Reasoning within output
git_log_format f002
100%
Passed
Tokens
718
Input
368
Total output
360
Reasoning within output
git_log_format f003
100%
Passed
Tokens
605
Input
701
Total output
758
Reasoning within output
git_log_format f004
100%
Passed
Tokens
718
Input
135
Total output
131
Reasoning within output
git_log_format f005
100%
Passed
Tokens
599
Input
219
Total output
211
Reasoning within output
git_log_format f006
100%
Passed
Tokens
733
Input
332
Total output
259
Reasoning within output
git_log_format f007
100%
Passed
Tokens
747
Input
168
Total output
160
Reasoning within output
git_log_format f008
100%
Passed
Tokens
954
Input
163
Total output
161
Reasoning within output
git_log_format f009
100%
Passed
Tokens
593
Input
85
Total output
82
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,104
Input
118
Total output
115
Reasoning within output
git_log_format f011
100%
Passed
Tokens
362
Input
135
Total output
145
Reasoning within output
git_log_format f012
100%
Passed
Tokens
357
Input
100
Total output
101
Reasoning within output
git_show f001
100%
Passed
Tokens
197
Input
107
Total output
103
Reasoning within output
git_show f002
100%
Passed
Tokens
201
Input
284
Total output
323
Reasoning within output
git_show f003
100%
Passed
Tokens
605
Input
203
Total output
196
Reasoning within output
git_show f004
100%
Passed
Tokens
413
Input
250
Total output
285
Reasoning within output
git_show f005
100%
Passed
Tokens
201
Input
334
Total output
330
Reasoning within output
git_show f006
100%
Passed
Tokens
209
Input
87
Total output
90
Reasoning within output
git_show f007
100%
Passed
Tokens
195
Input
156
Total output
168
Reasoning within output
git_show f008
100%
Passed
Tokens
215
Input
359
Total output
331
Reasoning within output
git_show f009
100%
Passed
Tokens
293
Input
345
Total output
341
Reasoning within output
git_show f010
100%
Passed
Tokens
201
Input
166
Total output
173
Reasoning within output
git_show f011
100%
Passed
Tokens
226
Input
300
Total output
311
Reasoning within output
git_show f012
100%
Passed
Tokens
318
Input
139
Total output
145
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
117
Input
816
Total output
811
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
135
Input
392
Total output
403
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
110
Input
854
Total output
962
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
161
Input
629
Total output
637
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
166
Input
391
Total output
456
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
150
Input
568
Total output
564
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
155
Input
252
Total output
241
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
137
Input
271
Total output
309
Reasoning within output
merge_conflicts f009
0%
Failed
Tokens
135
Input
1,167
Total output
1,155
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
205
Input
636
Total output
713
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
173
Input
309
Total output
303
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
255
Input
380
Total output
365
Reasoning within output
rebase f001
100%
Passed
Tokens
124
Input
527
Total output
611
Reasoning within output
rebase f002
100%
Passed
Tokens
154
Input
139
Total output
132
Reasoning within output
rebase f003
100%
Passed
Tokens
132
Input
230
Total output
224
Reasoning within output
rebase f004
100%
Passed
Tokens
176
Input
719
Total output
697
Reasoning within output
rebase f005
100%
Passed
Tokens
171
Input
249
Total output
233
Reasoning within output
rebase f006
100%
Passed
Tokens
165
Input
416
Total output
392
Reasoning within output
rebase f007
100%
Passed
Tokens
156
Input
245
Total output
234
Reasoning within output
rebase f008
100%
Passed
Tokens
151
Input
224
Total output
217
Reasoning within output
rebase f009
100%
Passed
Tokens
136
Input
213
Total output
207
Reasoning within output
rebase f010
100%
Passed
Tokens
229
Input
828
Total output
932
Reasoning within output
rebase f011
100%
Passed
Tokens
181
Input
1,137
Total output
1,109
Reasoning within output
rebase f012
0%
Failed
Tokens
281
Input
1,139
Total output
1,198
Reasoning within output
reflog f001
100%
Passed
Tokens
223
Input
767
Total output
744
Reasoning within output
reflog f002
100%
Passed
Tokens
212
Input
1,034
Total output
726
Reasoning within output
reflog f003
100%
Passed
Tokens
212
Input
578
Total output
435
Reasoning within output
reflog f004
100%
Passed
Tokens
318
Input
1,090
Total output
783
Reasoning within output
reflog f005
100%
Passed
Tokens
333
Input
391
Total output
154
Reasoning within output
reflog f006
100%
Passed
Tokens
251
Input
596
Total output
277
Reasoning within output
reflog f007
100%
Passed
Tokens
247
Input
607
Total output
272
Reasoning within output
reflog f008
100%
Passed
Tokens
337
Input
781
Total output
640
Reasoning within output
reflog f009
100%
Passed
Tokens
300
Input
1,776
Total output
1,248
Reasoning within output
reflog f010
100%
Passed
Tokens
263
Input
1,141
Total output
883
Reasoning within output
reflog f011
100%
Passed
Tokens
307
Input
3,561
Total output
3,407
Reasoning within output
reflog f012
100%
Passed
Tokens
304
Input
1,789
Total output
835
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
152
Input
200
Total output
213
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
289
Input
434
Total output
417
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
138
Input
109
Total output
117
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
123
Input
135
Total output
90
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
149
Input
240
Total output
209
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
198
Input
271
Total output
254
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
219
Input
242
Total output
214
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
191
Input
464
Total output
407
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
219
Input
222
Total output
188
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
148
Input
277
Total output
259
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
140
Input
202
Total output
189
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
149
Input
215
Total output
229
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
73
Input
160
Total output
150
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
119
Input
829
Total output
981
Reasoning within output
submodule_usage f003
75%
Failed
Tokens
126
Input
1,391
Total output
1,509
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
113
Input
542
Total output
536
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
80
Input
533
Total output
587
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
108
Input
534
Total output
529
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
83
Input
346
Total output
328
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
118
Input
1,154
Total output
1,146
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
115
Input
303
Total output
341
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
117
Input
542
Total output
534
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
124
Input
92
Total output
100
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
78
Input
184
Total output
171
Reasoning within output
tag_management f001
100%
Passed
Tokens
71
Input
63
Total output
60
Reasoning within output
tag_management f002
100%
Passed
Tokens
86
Input
291
Total output
273
Reasoning within output
tag_management f003
100%
Passed
Tokens
92
Input
546
Total output
536
Reasoning within output
tag_management f004
100%
Passed
Tokens
98
Input
213
Total output
210
Reasoning within output
tag_management f005
100%
Passed
Tokens
107
Input
204
Total output
182
Reasoning within output
tag_management f006
100%
Passed
Tokens
73
Input
707
Total output
689
Reasoning within output
tag_management f007
100%
Passed
Tokens
92
Input
478
Total output
393
Reasoning within output
tag_management f008
100%
Passed
Tokens
97
Input
725
Total output
636
Reasoning within output
tag_management f009
100%
Passed
Tokens
101
Input
238
Total output
221
Reasoning within output
tag_management f010
100%
Passed
Tokens
81
Input
74
Total output
66
Reasoning within output
tag_management f011
100%
Passed
Tokens
79
Input
203
Total output
216
Reasoning within output
tag_management f012
100%
Passed
Tokens
113
Input
704
Total output
694
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
158
Input
252
Total output
242
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
154
Input
384
Total output
363
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
217
Input
196
Total output
187
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
207
Input
211
Total output
236
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
144
Input
206
Total output
192
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
148
Input
334
Total output
318
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
144
Input
501
Total output
523
Reasoning within output
worktree_usage f008
100%
Passed
Tokens
174
Input
1,376
Total output
1,324
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
237
Input
225
Total output
219
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
217
Input
1,072
Total output
1,054
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
214
Input
136
Total output
134
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
142
Input
229
Total output
213
Reasoning within output