Minimax / minimax-m2.5
medium
89.2%
182 / 204 fixtures · 1 run(s)
41,316 input / 78,304 total output / 75,625 reasoning within output tokens $0.09306196
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
+0%
Text: 89.2% →
JSON: 89.2%
+11
Gained
JSON pass / text fail
−11
Lost
Text pass / JSON fail
171
Unchanged Pass
Both pass
11
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| commit_squash | 41.7% | 75% | + 33.3% |
| branch_cleanup | 91.7% | 75% | -16.7% |
| reflog | 100% | 83.3% | -16.7% |
| merge_conflicts | 83.3% | 91.7% | + 8.3% |
| blame_forensics | 100% | 91.7% | -8.3% |
| git_clean | 83.3% | 75% | -8.3% |
| git_grep | 91.7% | 100% | + 8.3% |
| git_show | 91.7% | 100% | + 8.3% |
| stash_recovery | 100% | 91.7% | -8.3% |
| submodule_usage | 91.7% | 100% | + 8.3% |
| tag_management | 100% | 91.7% | -8.3% |
| cherry_pick | 75% | 75% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| rebase | 83.3% | 83.3% | + 0% |
| worktree_usage | 83.3% | 83.3% | + 0% |
Changed Fixtures (22)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
245
Input
741
Total output
858
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
235
Input
314
Total output
294
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
257
Input
214
Total output
211
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
197
Input
383
Total output
376
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
275
Input
303
Total output
298
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
233
Input
1,045
Total output
1,040
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
223
Input
246
Total output
239
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
250
Input
634
Total output
629
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
204
Input
372
Total output
366
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
391
Input
592
Total output
592
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
238
Input
314
Total output
309
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
163
Input
260
Total output
269
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
132
Input
319
Total output
346
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
143
Input
710
Total output
766
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
122
Input
724
Total output
788
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
166
Input
457
Total output
450
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
130
Input
313
Total output
309
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
148
Input
253
Total output
271
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
135
Input
147
Total output
140
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
151
Input
582
Total output
571
Reasoning within output
branch_cleanup f009
0%
Failed
Tokens
114
Input
236
Total output
232
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
144
Input
446
Total output
453
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
100
Input
182
Total output
209
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
181
Input
410
Total output
398
Reasoning within output
cherry_pick f001
0%
Failed
Tokens
127
Input
400
Total output
401
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
145
Input
895
Total output
887
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
120
Input
313
Total output
346
Reasoning within output
cherry_pick f004
100%
Passed
Tokens
175
Input
855
Total output
837
Reasoning within output
cherry_pick f005
0%
Failed
Tokens
182
Input
488
Total output
567
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
162
Input
893
Total output
877
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
152
Input
126
Total output
117
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
152
Input
230
Total output
251
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
138
Input
661
Total output
751
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
236
Input
485
Total output
455
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
191
Input
1,868
Total output
1,685
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
294
Input
447
Total output
423
Reasoning within output
commit_messages f001
83%
Passed
Tokens
133
Input
132
Total output
128
Reasoning within output
commit_messages f002
91%
Passed
Tokens
227
Input
168
Total output
162
Reasoning within output
commit_messages f003
94%
Passed
Tokens
123
Input
235
Total output
225
Reasoning within output
commit_messages f004
93%
Passed
Tokens
136
Input
118
Total output
114
Reasoning within output
commit_messages f005
82.7%
Passed
Tokens
129
Input
109
Total output
124
Reasoning within output
commit_messages f006
89.3%
Passed
Tokens
171
Input
156
Total output
149
Reasoning within output
commit_messages f007
93.3%
Passed
Tokens
230
Input
142
Total output
134
Reasoning within output
commit_messages f008
92.3%
Passed
Tokens
100
Input
114
Total output
126
Reasoning within output
commit_messages f009
90%
Passed
Tokens
152
Input
178
Total output
192
Reasoning within output
commit_messages f010
89.7%
Passed
Tokens
328
Input
137
Total output
129
Reasoning within output
commit_messages f011
50%
Passed
Tokens
175
Input
315
Total output
309
Reasoning within output
commit_messages f012
90%
Passed
Tokens
152
Input
97
Total output
91
Reasoning within output
commit_squash f001
50%
Failed
Tokens
167
Input
245
Total output
236
Reasoning within output
commit_squash f002
0%
Failed
Tokens
143
Input
173
Total output
159
Reasoning within output
commit_squash f003
0%
Failed
Tokens
160
Input
209
Total output
186
Reasoning within output
commit_squash f004
100%
Passed
Tokens
143
Input
215
Total output
202
Reasoning within output
commit_squash f005
0%
Failed
Tokens
147
Input
294
Total output
275
Reasoning within output
commit_squash f006
100%
Passed
Tokens
126
Input
249
Total output
269
Reasoning within output
commit_squash f007
0%
Failed
Tokens
127
Input
192
Total output
159
Reasoning within output
commit_squash f008
100%
Passed
Tokens
140
Input
368
Total output
354
Reasoning within output
commit_squash f009
100%
Passed
Tokens
134
Input
249
Total output
237
Reasoning within output
commit_squash f010
0%
Failed
Tokens
147
Input
212
Total output
189
Reasoning within output
commit_squash f011
50%
Failed
Tokens
161
Input
261
Total output
245
Reasoning within output
commit_squash f012
100%
Passed
Tokens
151
Input
388
Total output
374
Reasoning within output
git_bisect f001
100%
Passed
Tokens
200
Input
266
Total output
262
Reasoning within output
git_bisect f002
100%
Passed
Tokens
221
Input
174
Total output
166
Reasoning within output
git_bisect f003
100%
Passed
Tokens
219
Input
384
Total output
378
Reasoning within output
git_bisect f004
100%
Passed
Tokens
247
Input
342
Total output
335
Reasoning within output
git_bisect f005
100%
Passed
Tokens
229
Input
268
Total output
262
Reasoning within output
git_bisect f006
100%
Passed
Tokens
248
Input
278
Total output
266
Reasoning within output
git_bisect f007
100%
Passed
Tokens
239
Input
508
Total output
502
Reasoning within output
git_bisect f008
100%
Passed
Tokens
219
Input
538
Total output
552
Reasoning within output
git_bisect f009
100%
Passed
Tokens
225
Input
934
Total output
1,001
Reasoning within output
git_bisect f010
100%
Passed
Tokens
223
Input
282
Total output
259
Reasoning within output
git_bisect f011
100%
Passed
Tokens
223
Input
348
Total output
340
Reasoning within output
git_bisect f012
100%
Passed
Tokens
238
Input
337
Total output
327
Reasoning within output
git_clean f001
100%
Passed
Tokens
78
Input
158
Total output
185
Reasoning within output
git_clean f002
100%
Passed
Tokens
89
Input
85
Total output
90
Reasoning within output
git_clean f003
100%
Passed
Tokens
89
Input
183
Total output
178
Reasoning within output
git_clean f004
33.3%
Failed
Tokens
86
Input
306
Total output
341
Reasoning within output
git_clean f005
100%
Passed
Tokens
78
Input
746
Total output
820
Reasoning within output
git_clean f006
100%
Passed
Tokens
104
Input
190
Total output
200
Reasoning within output
git_clean f007
100%
Passed
Tokens
100
Input
203
Total output
212
Reasoning within output
git_clean f008
100%
Passed
Tokens
105
Input
196
Total output
191
Reasoning within output
git_clean f009
100%
Passed
Tokens
95
Input
484
Total output
564
Reasoning within output
git_clean f010
100%
Passed
Tokens
105
Input
113
Total output
105
Reasoning within output
git_clean f011
60%
Failed
Tokens
91
Input
177
Total output
186
Reasoning within output
git_clean f012
100%
Passed
Tokens
94
Input
449
Total output
440
Reasoning within output
git_grep f001
100%
Passed
Tokens
83
Input
97
Total output
109
Reasoning within output
git_grep f002
100%
Passed
Tokens
93
Input
218
Total output
239
Reasoning within output
git_grep f003
100%
Passed
Tokens
117
Input
238
Total output
255
Reasoning within output
git_grep f004
100%
Passed
Tokens
106
Input
92
Total output
84
Reasoning within output
git_grep f005
100%
Passed
Tokens
136
Input
229
Total output
227
Reasoning within output
git_grep f006
100%
Passed
Tokens
71
Input
322
Total output
358
Reasoning within output
git_grep f007
100%
Passed
Tokens
187
Input
1,249
Total output
1,247
Reasoning within output
git_grep f008
100%
Passed
Tokens
95
Input
111
Total output
121
Reasoning within output
git_grep f009
100%
Passed
Tokens
84
Input
64
Total output
58
Reasoning within output
git_grep f010
0%
Failed
Tokens
99
Input
173
Total output
174
Reasoning within output
git_grep f011
100%
Passed
Tokens
143
Input
249
Total output
257
Reasoning within output
git_grep f012
100%
Passed
Tokens
95
Input
150
Total output
150
Reasoning within output
git_log_format f001
100%
Passed
Tokens
733
Input
158
Total output
155
Reasoning within output
git_log_format f002
100%
Passed
Tokens
789
Input
223
Total output
214
Reasoning within output
git_log_format f003
100%
Passed
Tokens
605
Input
197
Total output
187
Reasoning within output
git_log_format f004
100%
Passed
Tokens
738
Input
250
Total output
248
Reasoning within output
git_log_format f005
100%
Passed
Tokens
599
Input
608
Total output
688
Reasoning within output
git_log_format f006
100%
Passed
Tokens
733
Input
284
Total output
235
Reasoning within output
git_log_format f007
100%
Passed
Tokens
741
Input
160
Total output
154
Reasoning within output
git_log_format f008
100%
Passed
Tokens
962
Input
123
Total output
104
Reasoning within output
git_log_format f009
100%
Passed
Tokens
643
Input
95
Total output
92
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,076
Input
198
Total output
184
Reasoning within output
git_log_format f011
100%
Passed
Tokens
383
Input
154
Total output
152
Reasoning within output
git_log_format f012
100%
Passed
Tokens
352
Input
192
Total output
195
Reasoning within output
git_show f001
100%
Passed
Tokens
195
Input
112
Total output
107
Reasoning within output
git_show f002
100%
Passed
Tokens
198
Input
500
Total output
549
Reasoning within output
git_show f003
100%
Passed
Tokens
585
Input
220
Total output
212
Reasoning within output
git_show f004
100%
Passed
Tokens
421
Input
191
Total output
183
Reasoning within output
git_show f005
0%
Failed
Tokens
207
Input
131
Total output
122
Reasoning within output
git_show f006
100%
Passed
Tokens
211
Input
92
Total output
90
Reasoning within output
git_show f007
100%
Passed
Tokens
195
Input
160
Total output
155
Reasoning within output
git_show f008
100%
Passed
Tokens
205
Input
162
Total output
132
Reasoning within output
git_show f009
100%
Passed
Tokens
286
Input
131
Total output
128
Reasoning within output
git_show f010
100%
Passed
Tokens
194
Input
190
Total output
187
Reasoning within output
git_show f011
100%
Passed
Tokens
226
Input
143
Total output
140
Reasoning within output
git_show f012
100%
Passed
Tokens
316
Input
93
Total output
92
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
115
Input
719
Total output
727
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
135
Input
578
Total output
548
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
110
Input
758
Total output
755
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
161
Input
1,291
Total output
1,292
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
166
Input
299
Total output
354
Reasoning within output
merge_conflicts f006
0%
Failed
Tokens
155
Input
593
Total output
533
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
155
Input
189
Total output
205
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
137
Input
555
Total output
547
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
135
Input
1,544
Total output
1,717
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
205
Input
911
Total output
1,024
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
173
Input
395
Total output
347
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
256
Input
1,278
Total output
1,307
Reasoning within output
rebase f001
0%
Failed
Tokens
124
Input
430
Total output
424
Reasoning within output
rebase f002
100%
Passed
Tokens
155
Input
268
Total output
256
Reasoning within output
rebase f003
100%
Passed
Tokens
134
Input
91
Total output
98
Reasoning within output
rebase f004
100%
Passed
Tokens
172
Input
879
Total output
856
Reasoning within output
rebase f005
100%
Passed
Tokens
170
Input
310
Total output
356
Reasoning within output
rebase f006
100%
Passed
Tokens
169
Input
365
Total output
339
Reasoning within output
rebase f007
100%
Passed
Tokens
155
Input
406
Total output
437
Reasoning within output
rebase f008
100%
Passed
Tokens
149
Input
223
Total output
253
Reasoning within output
rebase f009
100%
Passed
Tokens
132
Input
203
Total output
196
Reasoning within output
rebase f010
100%
Passed
Tokens
230
Input
491
Total output
561
Reasoning within output
rebase f011
100%
Passed
Tokens
182
Input
333
Total output
295
Reasoning within output
rebase f012
0%
Failed
Tokens
283
Input
610
Total output
570
Reasoning within output
reflog f001
100%
Passed
Tokens
223
Input
655
Total output
632
Reasoning within output
reflog f002
100%
Passed
Tokens
222
Input
713
Total output
579
Reasoning within output
reflog f003
100%
Passed
Tokens
207
Input
656
Total output
426
Reasoning within output
reflog f004
100%
Passed
Tokens
298
Input
2,116
Total output
1,778
Reasoning within output
reflog f005
100%
Passed
Tokens
359
Input
1,016
Total output
827
Reasoning within output
reflog f006
100%
Passed
Tokens
243
Input
570
Total output
340
Reasoning within output
reflog f007
100%
Passed
Tokens
272
Input
574
Total output
347
Reasoning within output
reflog f008
100%
Passed
Tokens
331
Input
1,085
Total output
934
Reasoning within output
reflog f009
100%
Passed
Tokens
296
Input
1,126
Total output
673
Reasoning within output
reflog f010
100%
Passed
Tokens
265
Input
436
Total output
294
Reasoning within output
reflog f011
100%
Passed
Tokens
295
Input
1,521
Total output
1,262
Reasoning within output
reflog f012
100%
Passed
Tokens
307
Input
1,283
Total output
824
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
150
Input
155
Total output
142
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
287
Input
277
Total output
295
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
141
Input
231
Total output
195
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
139
Input
174
Total output
175
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
165
Input
396
Total output
369
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
224
Input
233
Total output
213
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
221
Input
143
Total output
135
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
216
Input
198
Total output
146
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
249
Input
381
Total output
335
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
148
Input
118
Total output
122
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
137
Input
483
Total output
477
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
149
Input
389
Total output
342
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
73
Input
94
Total output
85
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
119
Input
967
Total output
1,164
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
123
Input
1,214
Total output
1,170
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
127
Input
92
Total output
87
Reasoning within output
submodule_usage f005
0%
Failed
Tokens
85
Input
522
Total output
551
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
115
Input
91
Total output
125
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
80
Input
471
Total output
538
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
126
Input
721
Total output
714
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
116
Input
96
Total output
108
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
116
Input
185
Total output
214
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
124
Input
78
Total output
83
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
78
Input
79
Total output
75
Reasoning within output
tag_management f001
100%
Passed
Tokens
87
Input
58
Total output
49
Reasoning within output
tag_management f002
100%
Passed
Tokens
84
Input
79
Total output
60
Reasoning within output
tag_management f003
100%
Passed
Tokens
98
Input
128
Total output
116
Reasoning within output
tag_management f004
100%
Passed
Tokens
96
Input
73
Total output
67
Reasoning within output
tag_management f005
100%
Passed
Tokens
107
Input
215
Total output
184
Reasoning within output
tag_management f006
100%
Passed
Tokens
92
Input
322
Total output
311
Reasoning within output
tag_management f007
100%
Passed
Tokens
101
Input
201
Total output
188
Reasoning within output
tag_management f008
100%
Passed
Tokens
96
Input
786
Total output
738
Reasoning within output
tag_management f009
100%
Passed
Tokens
99
Input
124
Total output
108
Reasoning within output
tag_management f010
100%
Passed
Tokens
78
Input
69
Total output
61
Reasoning within output
tag_management f011
100%
Passed
Tokens
78
Input
54
Total output
47
Reasoning within output
tag_management f012
100%
Passed
Tokens
117
Input
604
Total output
593
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
152
Input
304
Total output
294
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
173
Input
391
Total output
367
Reasoning within output
worktree_usage f003
0%
Failed
Tokens
220
Input
295
Total output
302
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
207
Input
68
Total output
62
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
144
Input
106
Total output
108
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
146
Input
212
Total output
180
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
150
Input
233
Total output
212
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
173
Input
1,456
Total output
1,392
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
264
Input
120
Total output
114
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
218
Input
218
Total output
181
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
206
Input
114
Total output
118
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
146
Input
94
Total output
75
Reasoning within output