Minimax / minimax-m2.5
low
89.2%
182 / 204 fixtures · 1 run(s)
41,301 input / 85,257 total output / 83,043 reasoning within output tokens $0.10429170
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-1.5%
Text: 89.2% →
JSON: 87.8%
+11
Gained
JSON pass / text fail
−14
Lost
Text pass / JSON fail
168
Unchanged Pass
Both pass
11
Unchanged Fail
Both fail
Fixture Reliability Delta
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| git_show | 58.3% | 91.7% | + 33.3% |
| branch_cleanup | 100% | 75% | -25% |
| commit_messages | 83.3% | 100% | + 16.7% |
| git_clean | 91.7% | 75% | -16.7% |
| commit_squash | 91.7% | 83.3% | -8.3% |
| rebase | 83.3% | 91.7% | + 8.3% |
| worktree_usage | 91.7% | 83.3% | -8.3% |
| blame_forensics | 100% | 91.7% | -8.3% |
| git_bisect | 100% | 91.7% | -8.3% |
| git_log_format | 91.7% | 100% | + 8.3% |
| reflog | 100% | 91.7% | -8.3% |
| submodule_usage | 100% | 91.7% | -8.3% |
| cherry_pick | 66.7% | 66.7% | + 0% |
| git_grep | 100% | 100% | + 0% |
| merge_conflicts | 66.7% | 66.7% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| tag_management | 91.7% | 91.7% | + 0% |
Changed Fixtures (25)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
243
Input
343
Total output
356
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
234
Input
418
Total output
413
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
258
Input
391
Total output
384
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
197
Input
473
Total output
552
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
271
Input
350
Total output
345
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
246
Input
738
Total output
734
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
214
Input
275
Total output
265
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
240
Input
1,136
Total output
1,130
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
204
Input
486
Total output
566
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
406
Input
534
Total output
581
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
240
Input
220
Total output
212
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
161
Input
334
Total output
327
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
131
Input
249
Total output
244
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
147
Input
418
Total output
411
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
125
Input
244
Total output
242
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
153
Input
789
Total output
883
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
144
Input
134
Total output
129
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
157
Input
169
Total output
159
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
136
Input
165
Total output
158
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
159
Input
369
Total output
358
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
109
Input
424
Total output
511
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
145
Input
388
Total output
381
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
98
Input
327
Total output
390
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
181
Input
258
Total output
240
Reasoning within output
cherry_pick f001
0%
Failed
Tokens
124
Input
398
Total output
469
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
147
Input
332
Total output
309
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
120
Input
548
Total output
542
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
173
Input
2,046
Total output
2,263
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
177
Input
293
Total output
339
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
163
Input
1,250
Total output
1,223
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
169
Input
167
Total output
157
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
154
Input
156
Total output
149
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
138
Input
236
Total output
229
Reasoning within output
cherry_pick f010
0%
Failed
Tokens
245
Input
716
Total output
828
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
192
Input
495
Total output
458
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
318
Input
656
Total output
616
Reasoning within output
commit_messages f001
93.3%
Passed
Tokens
133
Input
104
Total output
111
Reasoning within output
commit_messages f002
76.7%
Passed
Tokens
227
Input
284
Total output
324
Reasoning within output
commit_messages f003
0%
Failed
Tokens
113
Input
159
Total output
139
Reasoning within output
commit_messages f004
91%
Passed
Tokens
134
Input
110
Total output
105
Reasoning within output
commit_messages f005
91.7%
Passed
Tokens
129
Input
101
Total output
112
Reasoning within output
commit_messages f006
55%
Passed
Tokens
163
Input
506
Total output
574
Reasoning within output
commit_messages f007
90%
Passed
Tokens
212
Input
203
Total output
218
Reasoning within output
commit_messages f008
92%
Passed
Tokens
102
Input
117
Total output
112
Reasoning within output
commit_messages f009
84.3%
Passed
Tokens
152
Input
257
Total output
269
Reasoning within output
commit_messages f010
93.3%
Passed
Tokens
290
Input
234
Total output
226
Reasoning within output
commit_messages f011
46%
Failed
Tokens
170
Input
177
Total output
184
Reasoning within output
commit_messages f012
91.7%
Passed
Tokens
149
Input
120
Total output
148
Reasoning within output
commit_squash f001
100%
Passed
Tokens
165
Input
201
Total output
174
Reasoning within output
commit_squash f002
100%
Passed
Tokens
144
Input
193
Total output
187
Reasoning within output
commit_squash f003
0%
Failed
Tokens
158
Input
283
Total output
225
Reasoning within output
commit_squash f004
100%
Passed
Tokens
142
Input
715
Total output
793
Reasoning within output
commit_squash f005
100%
Passed
Tokens
144
Input
263
Total output
254
Reasoning within output
commit_squash f006
100%
Passed
Tokens
125
Input
178
Total output
184
Reasoning within output
commit_squash f007
100%
Passed
Tokens
127
Input
433
Total output
434
Reasoning within output
commit_squash f008
100%
Passed
Tokens
139
Input
577
Total output
563
Reasoning within output
commit_squash f009
100%
Passed
Tokens
132
Input
322
Total output
310
Reasoning within output
commit_squash f010
100%
Passed
Tokens
149
Input
212
Total output
197
Reasoning within output
commit_squash f011
100%
Passed
Tokens
157
Input
665
Total output
642
Reasoning within output
commit_squash f012
100%
Passed
Tokens
153
Input
634
Total output
610
Reasoning within output
git_bisect f001
100%
Passed
Tokens
201
Input
155
Total output
149
Reasoning within output
git_bisect f002
100%
Passed
Tokens
225
Input
263
Total output
248
Reasoning within output
git_bisect f003
100%
Passed
Tokens
221
Input
241
Total output
229
Reasoning within output
git_bisect f004
100%
Passed
Tokens
221
Input
314
Total output
309
Reasoning within output
git_bisect f005
100%
Passed
Tokens
243
Input
451
Total output
445
Reasoning within output
git_bisect f006
100%
Passed
Tokens
254
Input
212
Total output
205
Reasoning within output
git_bisect f007
100%
Passed
Tokens
226
Input
339
Total output
329
Reasoning within output
git_bisect f008
100%
Passed
Tokens
231
Input
237
Total output
239
Reasoning within output
git_bisect f009
100%
Passed
Tokens
223
Input
347
Total output
326
Reasoning within output
git_bisect f010
100%
Passed
Tokens
223
Input
294
Total output
291
Reasoning within output
git_bisect f011
100%
Passed
Tokens
239
Input
287
Total output
279
Reasoning within output
git_bisect f012
100%
Passed
Tokens
246
Input
516
Total output
502
Reasoning within output
git_clean f001
100%
Passed
Tokens
88
Input
147
Total output
138
Reasoning within output
git_clean f002
100%
Passed
Tokens
89
Input
116
Total output
141
Reasoning within output
git_clean f003
100%
Passed
Tokens
86
Input
129
Total output
141
Reasoning within output
git_clean f004
33.3%
Failed
Tokens
86
Input
195
Total output
234
Reasoning within output
git_clean f005
100%
Passed
Tokens
78
Input
636
Total output
683
Reasoning within output
git_clean f006
100%
Passed
Tokens
118
Input
132
Total output
124
Reasoning within output
git_clean f007
100%
Passed
Tokens
100
Input
297
Total output
275
Reasoning within output
git_clean f008
100%
Passed
Tokens
102
Input
598
Total output
652
Reasoning within output
git_clean f009
100%
Passed
Tokens
95
Input
173
Total output
204
Reasoning within output
git_clean f010
100%
Passed
Tokens
92
Input
171
Total output
163
Reasoning within output
git_clean f011
100%
Passed
Tokens
91
Input
308
Total output
321
Reasoning within output
git_clean f012
100%
Passed
Tokens
92
Input
362
Total output
353
Reasoning within output
git_grep f001
100%
Passed
Tokens
90
Input
89
Total output
84
Reasoning within output
git_grep f002
100%
Passed
Tokens
92
Input
145
Total output
143
Reasoning within output
git_grep f003
100%
Passed
Tokens
117
Input
183
Total output
176
Reasoning within output
git_grep f004
100%
Passed
Tokens
106
Input
193
Total output
188
Reasoning within output
git_grep f005
100%
Passed
Tokens
154
Input
222
Total output
219
Reasoning within output
git_grep f006
100%
Passed
Tokens
76
Input
283
Total output
336
Reasoning within output
git_grep f007
100%
Passed
Tokens
187
Input
3,080
Total output
3,274
Reasoning within output
git_grep f008
100%
Passed
Tokens
97
Input
141
Total output
138
Reasoning within output
git_grep f009
100%
Passed
Tokens
84
Input
143
Total output
143
Reasoning within output
git_grep f010
100%
Passed
Tokens
94
Input
451
Total output
497
Reasoning within output
git_grep f011
100%
Passed
Tokens
167
Input
352
Total output
349
Reasoning within output
git_grep f012
100%
Passed
Tokens
95
Input
124
Total output
122
Reasoning within output
git_log_format f001
100%
Passed
Tokens
761
Input
118
Total output
115
Reasoning within output
git_log_format f002
100%
Passed
Tokens
729
Input
243
Total output
291
Reasoning within output
git_log_format f003
50%
Failed
Tokens
593
Input
200
Total output
191
Reasoning within output
git_log_format f004
100%
Passed
Tokens
700
Input
199
Total output
190
Reasoning within output
git_log_format f005
100%
Passed
Tokens
599
Input
587
Total output
582
Reasoning within output
git_log_format f006
100%
Passed
Tokens
733
Input
328
Total output
230
Reasoning within output
git_log_format f007
100%
Passed
Tokens
753
Input
104
Total output
99
Reasoning within output
git_log_format f008
100%
Passed
Tokens
956
Input
119
Total output
108
Reasoning within output
git_log_format f009
100%
Passed
Tokens
576
Input
68
Total output
78
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,090
Input
285
Total output
261
Reasoning within output
git_log_format f011
100%
Passed
Tokens
374
Input
249
Total output
271
Reasoning within output
git_log_format f012
100%
Passed
Tokens
362
Input
107
Total output
104
Reasoning within output
git_show f001
0%
Failed
Tokens
204
Input
107
Total output
89
Reasoning within output
git_show f002
0%
Failed
Tokens
197
Input
448
Total output
452
Reasoning within output
git_show f003
100%
Passed
Tokens
591
Input
206
Total output
161
Reasoning within output
git_show f004
100%
Passed
Tokens
423
Input
118
Total output
108
Reasoning within output
git_show f005
100%
Passed
Tokens
202
Input
441
Total output
480
Reasoning within output
git_show f006
0%
Failed
Tokens
212
Input
186
Total output
170
Reasoning within output
git_show f007
100%
Passed
Tokens
195
Input
122
Total output
107
Reasoning within output
git_show f008
0%
Failed
Tokens
225
Input
168
Total output
141
Reasoning within output
git_show f009
0%
Failed
Tokens
289
Input
232
Total output
213
Reasoning within output
git_show f010
100%
Passed
Tokens
200
Input
213
Total output
210
Reasoning within output
git_show f011
100%
Passed
Tokens
223
Input
87
Total output
85
Reasoning within output
git_show f012
100%
Passed
Tokens
359
Input
100
Total output
97
Reasoning within output
merge_conflicts f001
0%
Failed
Tokens
115
Input
425
Total output
419
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
135
Input
508
Total output
498
Reasoning within output
merge_conflicts f003
0%
Failed
Tokens
115
Input
460
Total output
536
Reasoning within output
merge_conflicts f004
0%
Failed
Tokens
161
Input
2,438
Total output
2,643
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
166
Input
408
Total output
462
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
150
Input
630
Total output
576
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
155
Input
319
Total output
347
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
137
Input
499
Total output
573
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
135
Input
360
Total output
393
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
205
Input
687
Total output
666
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
173
Input
549
Total output
500
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
256
Input
573
Total output
544
Reasoning within output
rebase f001
100%
Passed
Tokens
125
Input
388
Total output
382
Reasoning within output
rebase f002
100%
Passed
Tokens
154
Input
190
Total output
171
Reasoning within output
rebase f003
100%
Passed
Tokens
134
Input
401
Total output
444
Reasoning within output
rebase f004
100%
Passed
Tokens
170
Input
744
Total output
721
Reasoning within output
rebase f005
100%
Passed
Tokens
170
Input
489
Total output
599
Reasoning within output
rebase f006
100%
Passed
Tokens
162
Input
686
Total output
652
Reasoning within output
rebase f007
100%
Passed
Tokens
154
Input
129
Total output
132
Reasoning within output
rebase f008
0%
Failed
Tokens
153
Input
462
Total output
509
Reasoning within output
rebase f009
100%
Passed
Tokens
133
Input
259
Total output
282
Reasoning within output
rebase f010
100%
Passed
Tokens
253
Input
1,204
Total output
1,178
Reasoning within output
rebase f011
100%
Passed
Tokens
184
Input
735
Total output
713
Reasoning within output
rebase f012
0%
Failed
Tokens
288
Input
1,536
Total output
1,497
Reasoning within output
reflog f001
100%
Passed
Tokens
235
Input
620
Total output
595
Reasoning within output
reflog f002
100%
Passed
Tokens
216
Input
576
Total output
423
Reasoning within output
reflog f003
100%
Passed
Tokens
212
Input
451
Total output
343
Reasoning within output
reflog f004
100%
Passed
Tokens
304
Input
2,288
Total output
1,837
Reasoning within output
reflog f005
100%
Passed
Tokens
348
Input
1,426
Total output
825
Reasoning within output
reflog f006
100%
Passed
Tokens
242
Input
1,445
Total output
1,065
Reasoning within output
reflog f007
100%
Passed
Tokens
282
Input
1,125
Total output
1,020
Reasoning within output
reflog f008
100%
Passed
Tokens
330
Input
1,121
Total output
973
Reasoning within output
reflog f009
100%
Passed
Tokens
319
Input
1,213
Total output
840
Reasoning within output
reflog f010
100%
Passed
Tokens
263
Input
885
Total output
675
Reasoning within output
reflog f011
100%
Passed
Tokens
311
Input
1,887
Total output
1,737
Reasoning within output
reflog f012
100%
Passed
Tokens
290
Input
1,225
Total output
822
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
152
Input
200
Total output
195
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
329
Input
471
Total output
453
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
139
Input
304
Total output
312
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
139
Input
197
Total output
199
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
154
Input
244
Total output
236
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
196
Input
198
Total output
186
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
247
Input
312
Total output
286
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
191
Input
220
Total output
205
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
219
Input
197
Total output
162
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
148
Input
212
Total output
177
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
153
Input
225
Total output
205
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
149
Input
287
Total output
232
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
73
Input
226
Total output
239
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
122
Input
429
Total output
532
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
124
Input
1,324
Total output
1,397
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
114
Input
729
Total output
819
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
80
Input
335
Total output
310
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
110
Input
171
Total output
167
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
80
Input
116
Total output
97
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
130
Input
458
Total output
451
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
114
Input
58
Total output
62
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
119
Input
429
Total output
527
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
123
Input
74
Total output
68
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
78
Input
78
Total output
65
Reasoning within output
tag_management f001
100%
Passed
Tokens
85
Input
68
Total output
65
Reasoning within output
tag_management f002
100%
Passed
Tokens
90
Input
117
Total output
98
Reasoning within output
tag_management f003
100%
Passed
Tokens
92
Input
235
Total output
225
Reasoning within output
tag_management f004
100%
Passed
Tokens
96
Input
85
Total output
80
Reasoning within output
tag_management f005
100%
Passed
Tokens
108
Input
241
Total output
231
Reasoning within output
tag_management f006
100%
Passed
Tokens
95
Input
85
Total output
64
Reasoning within output
tag_management f007
100%
Passed
Tokens
94
Input
316
Total output
278
Reasoning within output
tag_management f008
33.3%
Failed
Tokens
98
Input
669
Total output
581
Reasoning within output
tag_management f009
100%
Passed
Tokens
99
Input
93
Total output
80
Reasoning within output
tag_management f010
100%
Passed
Tokens
79
Input
66
Total output
60
Reasoning within output
tag_management f011
100%
Passed
Tokens
77
Input
86
Total output
97
Reasoning within output
tag_management f012
100%
Passed
Tokens
112
Input
507
Total output
486
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
149
Input
534
Total output
588
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
155
Input
321
Total output
304
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
207
Input
231
Total output
221
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
206
Input
87
Total output
98
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
144
Input
189
Total output
176
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
162
Input
140
Total output
126
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
147
Input
323
Total output
320
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
169
Input
2,020
Total output
1,954
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
244
Input
230
Total output
223
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
217
Input
135
Total output
118
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
212
Input
210
Total output
181
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
143
Input
100
Total output
85
Reasoning within output