Minimax / minimax-m2.7
high
97.1%
198 / 204 fixtures · 1 run(s)
40,856 input / 91,260 total output / 87,656 reasoning within output tokens $0.12771553
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-28.9%
Text: 97.1% →
JSON: 68.1%
+1
Gained
JSON pass / text fail
−60
Lost
Text pass / JSON fail
138
Unchanged Pass
Both pass
5
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| reflog | 100% | 33.3% | -66.7% |
| branch_cleanup | 100% | 41.7% | -58.3% |
| blame_forensics | 100% | 50% | -50% |
| git_clean | 100% | 50% | -50% |
| merge_conflicts | 91.7% | 50% | -41.7% |
| submodule_usage | 100% | 58.3% | -41.7% |
| commit_squash | 100% | 66.7% | -33.3% |
| git_log_format | 100% | 75% | -25% |
| rebase | 91.7% | 66.7% | -25% |
| worktree_usage | 100% | 75% | -25% |
| cherry_pick | 91.7% | 75% | -16.7% |
| commit_messages | 100% | 83.3% | -16.7% |
| git_bisect | 100% | 83.3% | -16.7% |
| stash_recovery | 100% | 83.3% | -16.7% |
| git_show | 91.7% | 83.3% | -8.3% |
| git_grep | 100% | 100% | + 0% |
| tag_management | 83.3% | 83.3% | + 0% |
Changed Fixtures (61)
f001 -loss f003 -loss f005 -loss f008 -loss f010 -loss f011 -loss f002 -loss f003 -loss f005 -loss f007 -loss f009 -loss f011 -loss f012 -loss f004 -loss f011 -loss f003 -loss f010 -loss f002 -loss f004 -loss f008 -loss f010 -loss f009 -loss f012 -loss f003 -loss f006 -loss f007 -loss f009 -loss f010 -loss f011 -loss f002 -loss f005 -loss f007 -loss f012 -loss f001 -loss f002 -loss f003 -loss f004 -loss f011 -loss f004 -loss f005 -loss f011 -loss f003 -loss f004 -loss f005 -loss f006 -loss f008 -loss f009 -loss f010 -loss f012 -loss f011 -loss f012 -loss f006 -loss f007 -loss f008 -loss f009 -loss f011 -loss f007 +gain f010 -loss f004 -loss f008 -loss f011 -loss
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
243
Input
467
Total output
525
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
232
Input
134
Total output
119
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
258
Input
270
Total output
281
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
199
Input
306
Total output
299
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
262
Input
5,497
Total output
5,492
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
245
Input
428
Total output
424
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
216
Input
360
Total output
352
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
236
Input
590
Total output
657
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
209
Input
341
Total output
336
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
390
Input
238
Total output
247
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
241
Input
292
Total output
288
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
159
Input
438
Total output
482
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
132
Input
321
Total output
314
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
148
Input
228
Total output
222
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
125
Input
304
Total output
302
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
158
Input
234
Total output
228
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
131
Input
226
Total output
221
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
152
Input
283
Total output
273
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
129
Input
267
Total output
259
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
148
Input
179
Total output
159
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
111
Input
315
Total output
313
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
144
Input
244
Total output
237
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
101
Input
99
Total output
97
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
188
Input
338
Total output
329
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
126
Input
428
Total output
423
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
149
Input
656
Total output
648
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
119
Input
543
Total output
652
Reasoning within output
cherry_pick f004
100%
Passed
Tokens
174
Input
1,188
Total output
1,297
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
176
Input
191
Total output
167
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
164
Input
542
Total output
518
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
155
Input
235
Total output
224
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
156
Input
147
Total output
140
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
137
Input
106
Total output
98
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
236
Input
285
Total output
309
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
196
Input
290
Total output
268
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
290
Input
531
Total output
485
Reasoning within output
commit_messages f001
92.7%
Passed
Tokens
133
Input
184
Total output
177
Reasoning within output
commit_messages f002
91%
Passed
Tokens
229
Input
264
Total output
259
Reasoning within output
commit_messages f003
93.3%
Passed
Tokens
115
Input
137
Total output
128
Reasoning within output
commit_messages f004
92%
Passed
Tokens
134
Input
145
Total output
140
Reasoning within output
commit_messages f005
93.3%
Passed
Tokens
128
Input
213
Total output
227
Reasoning within output
commit_messages f006
91%
Passed
Tokens
147
Input
185
Total output
200
Reasoning within output
commit_messages f007
91.7%
Passed
Tokens
212
Input
145
Total output
136
Reasoning within output
commit_messages f008
93.3%
Passed
Tokens
99
Input
186
Total output
199
Reasoning within output
commit_messages f009
87.3%
Passed
Tokens
152
Input
297
Total output
285
Reasoning within output
commit_messages f010
85.7%
Passed
Tokens
290
Input
244
Total output
235
Reasoning within output
commit_messages f011
79.3%
Passed
Tokens
173
Input
245
Total output
230
Reasoning within output
commit_messages f012
90.3%
Passed
Tokens
149
Input
178
Total output
216
Reasoning within output
commit_squash f001
100%
Passed
Tokens
162
Input
1,087
Total output
1,072
Reasoning within output
commit_squash f002
100%
Passed
Tokens
143
Input
358
Total output
347
Reasoning within output
commit_squash f003
100%
Passed
Tokens
156
Input
224
Total output
211
Reasoning within output
commit_squash f004
100%
Passed
Tokens
142
Input
219
Total output
207
Reasoning within output
commit_squash f005
100%
Passed
Tokens
140
Input
241
Total output
232
Reasoning within output
commit_squash f006
100%
Passed
Tokens
125
Input
316
Total output
303
Reasoning within output
commit_squash f007
100%
Passed
Tokens
127
Input
384
Total output
414
Reasoning within output
commit_squash f008
100%
Passed
Tokens
143
Input
319
Total output
304
Reasoning within output
commit_squash f009
100%
Passed
Tokens
135
Input
250
Total output
238
Reasoning within output
commit_squash f010
100%
Passed
Tokens
153
Input
237
Total output
221
Reasoning within output
commit_squash f011
100%
Passed
Tokens
159
Input
354
Total output
336
Reasoning within output
commit_squash f012
100%
Passed
Tokens
151
Input
318
Total output
296
Reasoning within output
git_bisect f001
100%
Passed
Tokens
203
Input
174
Total output
168
Reasoning within output
git_bisect f002
100%
Passed
Tokens
226
Input
256
Total output
244
Reasoning within output
git_bisect f003
100%
Passed
Tokens
219
Input
407
Total output
400
Reasoning within output
git_bisect f004
100%
Passed
Tokens
221
Input
248
Total output
239
Reasoning within output
git_bisect f005
100%
Passed
Tokens
224
Input
467
Total output
462
Reasoning within output
git_bisect f006
100%
Passed
Tokens
242
Input
416
Total output
410
Reasoning within output
git_bisect f007
100%
Passed
Tokens
226
Input
216
Total output
211
Reasoning within output
git_bisect f008
100%
Passed
Tokens
219
Input
493
Total output
487
Reasoning within output
git_bisect f009
100%
Passed
Tokens
219
Input
229
Total output
217
Reasoning within output
git_bisect f010
100%
Passed
Tokens
229
Input
368
Total output
355
Reasoning within output
git_bisect f011
100%
Passed
Tokens
225
Input
239
Total output
227
Reasoning within output
git_bisect f012
100%
Passed
Tokens
253
Input
309
Total output
302
Reasoning within output
git_clean f001
100%
Passed
Tokens
81
Input
345
Total output
337
Reasoning within output
git_clean f002
100%
Passed
Tokens
89
Input
255
Total output
277
Reasoning within output
git_clean f003
100%
Passed
Tokens
86
Input
200
Total output
194
Reasoning within output
git_clean f004
100%
Passed
Tokens
88
Input
1,763
Total output
1,757
Reasoning within output
git_clean f005
100%
Passed
Tokens
78
Input
695
Total output
688
Reasoning within output
git_clean f006
100%
Passed
Tokens
107
Input
579
Total output
572
Reasoning within output
git_clean f007
100%
Passed
Tokens
103
Input
697
Total output
687
Reasoning within output
git_clean f008
100%
Passed
Tokens
102
Input
342
Total output
363
Reasoning within output
git_clean f009
100%
Passed
Tokens
95
Input
635
Total output
721
Reasoning within output
git_clean f010
100%
Passed
Tokens
95
Input
628
Total output
621
Reasoning within output
git_clean f011
100%
Passed
Tokens
93
Input
382
Total output
376
Reasoning within output
git_clean f012
100%
Passed
Tokens
92
Input
1,258
Total output
1,248
Reasoning within output
git_grep f001
100%
Passed
Tokens
67
Input
77
Total output
89
Reasoning within output
git_grep f002
100%
Passed
Tokens
93
Input
116
Total output
121
Reasoning within output
git_grep f003
100%
Passed
Tokens
117
Input
93
Total output
105
Reasoning within output
git_grep f004
100%
Passed
Tokens
106
Input
131
Total output
129
Reasoning within output
git_grep f005
100%
Passed
Tokens
139
Input
180
Total output
178
Reasoning within output
git_grep f006
100%
Passed
Tokens
71
Input
447
Total output
443
Reasoning within output
git_grep f007
100%
Passed
Tokens
171
Input
474
Total output
465
Reasoning within output
git_grep f008
100%
Passed
Tokens
92
Input
135
Total output
133
Reasoning within output
git_grep f009
100%
Passed
Tokens
86
Input
124
Total output
120
Reasoning within output
git_grep f010
100%
Passed
Tokens
94
Input
362
Total output
403
Reasoning within output
git_grep f011
100%
Passed
Tokens
141
Input
302
Total output
300
Reasoning within output
git_grep f012
100%
Passed
Tokens
95
Input
153
Total output
156
Reasoning within output
git_log_format f001
100%
Passed
Tokens
747
Input
166
Total output
163
Reasoning within output
git_log_format f002
100%
Passed
Tokens
739
Input
308
Total output
367
Reasoning within output
git_log_format f003
100%
Passed
Tokens
596
Input
269
Total output
257
Reasoning within output
git_log_format f004
100%
Passed
Tokens
713
Input
102
Total output
100
Reasoning within output
git_log_format f005
100%
Passed
Tokens
599
Input
325
Total output
317
Reasoning within output
git_log_format f006
100%
Passed
Tokens
733
Input
256
Total output
213
Reasoning within output
git_log_format f007
100%
Passed
Tokens
722
Input
176
Total output
169
Reasoning within output
git_log_format f008
100%
Passed
Tokens
963
Input
104
Total output
102
Reasoning within output
git_log_format f009
100%
Passed
Tokens
594
Input
145
Total output
142
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,056
Input
94
Total output
92
Reasoning within output
git_log_format f011
100%
Passed
Tokens
384
Input
175
Total output
172
Reasoning within output
git_log_format f012
100%
Passed
Tokens
351
Input
102
Total output
100
Reasoning within output
git_show f001
100%
Passed
Tokens
198
Input
184
Total output
190
Reasoning within output
git_show f002
0%
Failed
Tokens
200
Input
560
Total output
557
Reasoning within output
git_show f003
100%
Passed
Tokens
594
Input
287
Total output
297
Reasoning within output
git_show f004
100%
Passed
Tokens
423
Input
121
Total output
114
Reasoning within output
git_show f005
100%
Passed
Tokens
201
Input
298
Total output
324
Reasoning within output
git_show f006
100%
Passed
Tokens
209
Input
111
Total output
107
Reasoning within output
git_show f007
100%
Passed
Tokens
197
Input
137
Total output
132
Reasoning within output
git_show f008
100%
Passed
Tokens
210
Input
262
Total output
235
Reasoning within output
git_show f009
100%
Passed
Tokens
292
Input
128
Total output
126
Reasoning within output
git_show f010
100%
Passed
Tokens
199
Input
183
Total output
180
Reasoning within output
git_show f011
100%
Passed
Tokens
227
Input
102
Total output
99
Reasoning within output
git_show f012
100%
Passed
Tokens
323
Input
200
Total output
198
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
115
Input
371
Total output
364
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
135
Input
791
Total output
790
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
110
Input
1,233
Total output
1,404
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
161
Input
997
Total output
1,083
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
166
Input
351
Total output
413
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
152
Input
717
Total output
693
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
155
Input
501
Total output
555
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
139
Input
175
Total output
168
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
135
Input
368
Total output
360
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
207
Input
993
Total output
968
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
176
Input
380
Total output
358
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
256
Input
928
Total output
974
Reasoning within output
rebase f001
100%
Passed
Tokens
123
Input
1,307
Total output
1,568
Reasoning within output
rebase f002
100%
Passed
Tokens
153
Input
202
Total output
193
Reasoning within output
rebase f003
100%
Passed
Tokens
134
Input
220
Total output
215
Reasoning within output
rebase f004
100%
Passed
Tokens
174
Input
708
Total output
685
Reasoning within output
rebase f005
100%
Passed
Tokens
170
Input
520
Total output
620
Reasoning within output
rebase f006
100%
Passed
Tokens
160
Input
396
Total output
371
Reasoning within output
rebase f007
100%
Passed
Tokens
158
Input
392
Total output
383
Reasoning within output
rebase f008
100%
Passed
Tokens
148
Input
385
Total output
376
Reasoning within output
rebase f009
100%
Passed
Tokens
136
Input
297
Total output
291
Reasoning within output
rebase f010
100%
Passed
Tokens
228
Input
424
Total output
398
Reasoning within output
rebase f011
100%
Passed
Tokens
185
Input
380
Total output
358
Reasoning within output
rebase f012
0%
Failed
Tokens
285
Input
889
Total output
849
Reasoning within output
reflog f001
100%
Passed
Tokens
237
Input
387
Total output
362
Reasoning within output
reflog f002
100%
Passed
Tokens
226
Input
405
Total output
270
Reasoning within output
reflog f003
100%
Passed
Tokens
205
Input
469
Total output
341
Reasoning within output
reflog f004
100%
Passed
Tokens
289
Input
1,870
Total output
1,686
Reasoning within output
reflog f005
100%
Passed
Tokens
345
Input
1,266
Total output
1,021
Reasoning within output
reflog f006
100%
Passed
Tokens
258
Input
705
Total output
390
Reasoning within output
reflog f007
100%
Passed
Tokens
278
Input
792
Total output
439
Reasoning within output
reflog f008
100%
Passed
Tokens
340
Input
1,387
Total output
1,242
Reasoning within output
reflog f009
100%
Passed
Tokens
320
Input
994
Total output
577
Reasoning within output
reflog f010
100%
Passed
Tokens
262
Input
1,858
Total output
1,069
Reasoning within output
reflog f011
100%
Passed
Tokens
300
Input
1,871
Total output
1,710
Reasoning within output
reflog f012
100%
Passed
Tokens
304
Input
3,311
Total output
2,115
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
153
Input
149
Total output
136
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
286
Input
438
Total output
400
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
141
Input
173
Total output
154
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
141
Input
236
Total output
219
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
147
Input
276
Total output
256
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
198
Input
245
Total output
200
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
215
Input
372
Total output
350
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
193
Input
231
Total output
200
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
219
Input
490
Total output
448
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
148
Input
261
Total output
237
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
138
Input
310
Total output
295
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
149
Input
198
Total output
223
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
72
Input
186
Total output
208
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
122
Input
1,055
Total output
1,310
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
126
Input
2,637
Total output
2,860
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
114
Input
207
Total output
201
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
83
Input
532
Total output
506
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
114
Input
170
Total output
166
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
83
Input
330
Total output
312
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
102
Input
79
Total output
90
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
109
Input
146
Total output
167
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
123
Input
553
Total output
636
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
125
Input
142
Total output
137
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
78
Input
233
Total output
219
Reasoning within output
tag_management f001
100%
Passed
Tokens
87
Input
163
Total output
156
Reasoning within output
tag_management f002
100%
Passed
Tokens
84
Input
314
Total output
271
Reasoning within output
tag_management f003
100%
Passed
Tokens
94
Input
119
Total output
109
Reasoning within output
tag_management f004
100%
Passed
Tokens
95
Input
250
Total output
247
Reasoning within output
tag_management f005
100%
Passed
Tokens
109
Input
180
Total output
170
Reasoning within output
tag_management f006
100%
Passed
Tokens
76
Input
134
Total output
94
Reasoning within output
tag_management f007
66.7%
Failed
Tokens
97
Input
643
Total output
628
Reasoning within output
tag_management f008
100%
Passed
Tokens
100
Input
690
Total output
665
Reasoning within output
tag_management f009
100%
Passed
Tokens
99
Input
257
Total output
237
Reasoning within output
tag_management f010
100%
Passed
Tokens
77
Input
71
Total output
58
Reasoning within output
tag_management f011
0%
Failed
Tokens
80
Input
166
Total output
158
Reasoning within output
tag_management f012
100%
Passed
Tokens
113
Input
450
Total output
437
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
153
Input
986
Total output
972
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
158
Input
459
Total output
457
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
213
Input
284
Total output
295
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
209
Input
186
Total output
180
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
145
Input
309
Total output
297
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
149
Input
256
Total output
243
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
132
Input
350
Total output
272
Reasoning within output
worktree_usage f008
100%
Passed
Tokens
171
Input
1,451
Total output
1,483
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
242
Input
593
Total output
586
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
218
Input
286
Total output
270
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
215
Input
301
Total output
329
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
147
Input
212
Total output
197
Reasoning within output