Minimax / minimax-m3
xhigh
94.6%
193 / 204 fixtures · 1 run(s)
69,084 input / 46,678 total output / 39,094 reasoning within output tokens $0.07801650
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-10.3%
Text: 94.6% →
JSON: 84.3%
+5
Gained
JSON pass / text fail
−26
Lost
Text pass / JSON fail
167
Unchanged Pass
Both pass
6
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| commit_squash | 100% | 33.3% | -66.7% |
| git_clean | 91.7% | 66.7% | -25% |
| rebase | 91.7% | 66.7% | -25% |
| branch_cleanup | 100% | 83.3% | -16.7% |
| git_grep | 91.7% | 75% | -16.7% |
| reflog | 100% | 83.3% | -16.7% |
| cherry_pick | 91.7% | 83.3% | -8.3% |
| blame_forensics | 100% | 91.7% | -8.3% |
| git_log_format | 91.7% | 100% | + 8.3% |
| git_show | 100% | 91.7% | -8.3% |
| merge_conflicts | 75% | 83.3% | + 8.3% |
| submodule_usage | 91.7% | 100% | + 8.3% |
| worktree_usage | 83.3% | 75% | -8.3% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
Changed Fixtures (31)
f006 -loss f003 -loss f009 -loss f001 -loss f001 -loss f002 -loss f004 -loss f006 -loss f007 -loss f008 -loss f009 -loss f011 -loss f004 -loss f005 -loss f007 -loss f006 -loss f007 -loss f004 +gain f010 -loss f001 -loss f004 +gain f006 +gain f001 -loss f006 -loss f011 -loss f002 -loss f012 -loss f012 +gain f001 -loss f002 -loss f007 +gain
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
391
Input
392
Total output
407
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
614
Input
544
Total output
547
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
402
Input
69
Total output
60
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
335
Input
185
Total output
198
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
398
Input
534
Total output
519
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
375
Input
681
Total output
643
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
348
Input
319
Total output
289
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
384
Input
558
Total output
530
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
341
Input
303
Total output
327
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
537
Input
181
Total output
183
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
378
Input
313
Total output
297
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
297
Input
182
Total output
179
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
271
Input
244
Total output
238
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
278
Input
150
Total output
126
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
261
Input
292
Total output
323
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
296
Input
126
Total output
144
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
273
Input
184
Total output
195
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
290
Input
98
Total output
101
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
270
Input
129
Total output
143
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
291
Input
154
Total output
128
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
248
Input
124
Total output
135
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
284
Input
137
Total output
117
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
237
Input
88
Total output
107
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
321
Input
130
Total output
120
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
263
Input
280
Total output
344
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
284
Input
235
Total output
229
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
257
Input
91
Total output
101
Reasoning within output
cherry_pick f004
100%
Passed
Tokens
312
Input
249
Total output
235
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
317
Input
196
Total output
189
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
300
Input
524
Total output
497
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
292
Input
179
Total output
173
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
291
Input
99
Total output
91
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
276
Input
95
Total output
98
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
374
Input
185
Total output
190
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
331
Input
242
Total output
182
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
423
Input
933
Total output
978
Reasoning within output
commit_messages f001
88.3%
Passed
Tokens
271
Input
65
Total output
62
Reasoning within output
commit_messages f002
90%
Passed
Tokens
365
Input
47
Total output
50
Reasoning within output
commit_messages f003
93.7%
Passed
Tokens
251
Input
48
Total output
36
Reasoning within output
commit_messages f004
94.3%
Passed
Tokens
272
Input
60
Total output
64
Reasoning within output
commit_messages f005
91%
Passed
Tokens
267
Input
66
Total output
70
Reasoning within output
commit_messages f006
91.7%
Passed
Tokens
249
Input
219
Total output
211
Reasoning within output
commit_messages f007
90%
Passed
Tokens
298
Input
133
Total output
124
Reasoning within output
commit_messages f008
90.7%
Passed
Tokens
238
Input
63
Total output
63
Reasoning within output
commit_messages f009
86.7%
Passed
Tokens
287
Input
45
Total output
45
Reasoning within output
commit_messages f010
92.7%
Passed
Tokens
426
Input
161
Total output
159
Reasoning within output
commit_messages f011
64.7%
Passed
Tokens
308
Input
178
Total output
174
Reasoning within output
commit_messages f012
91.7%
Passed
Tokens
287
Input
54
Total output
63
Reasoning within output
commit_squash f001
100%
Passed
Tokens
301
Input
288
Total output
283
Reasoning within output
commit_squash f002
100%
Passed
Tokens
284
Input
151
Total output
133
Reasoning within output
commit_squash f003
100%
Passed
Tokens
292
Input
169
Total output
145
Reasoning within output
commit_squash f004
100%
Passed
Tokens
279
Input
296
Total output
296
Reasoning within output
commit_squash f005
100%
Passed
Tokens
279
Input
658
Total output
737
Reasoning within output
commit_squash f006
100%
Passed
Tokens
265
Input
172
Total output
168
Reasoning within output
commit_squash f007
100%
Passed
Tokens
266
Input
169
Total output
146
Reasoning within output
commit_squash f008
100%
Passed
Tokens
278
Input
139
Total output
127
Reasoning within output
commit_squash f009
100%
Passed
Tokens
274
Input
149
Total output
122
Reasoning within output
commit_squash f010
100%
Passed
Tokens
288
Input
163
Total output
149
Reasoning within output
commit_squash f011
100%
Passed
Tokens
296
Input
156
Total output
126
Reasoning within output
commit_squash f012
100%
Passed
Tokens
288
Input
157
Total output
122
Reasoning within output
git_bisect f001
100%
Passed
Tokens
340
Input
88
Total output
81
Reasoning within output
git_bisect f002
100%
Passed
Tokens
363
Input
158
Total output
89
Reasoning within output
git_bisect f003
100%
Passed
Tokens
365
Input
139
Total output
125
Reasoning within output
git_bisect f004
100%
Passed
Tokens
364
Input
165
Total output
87
Reasoning within output
git_bisect f005
100%
Passed
Tokens
351
Input
118
Total output
109
Reasoning within output
git_bisect f006
100%
Passed
Tokens
384
Input
128
Total output
109
Reasoning within output
git_bisect f007
100%
Passed
Tokens
360
Input
127
Total output
104
Reasoning within output
git_bisect f008
100%
Passed
Tokens
354
Input
220
Total output
146
Reasoning within output
git_bisect f009
100%
Passed
Tokens
363
Input
116
Total output
97
Reasoning within output
git_bisect f010
100%
Passed
Tokens
357
Input
100
Total output
89
Reasoning within output
git_bisect f011
100%
Passed
Tokens
365
Input
114
Total output
96
Reasoning within output
git_bisect f012
100%
Passed
Tokens
382
Input
125
Total output
116
Reasoning within output
git_clean f001
100%
Passed
Tokens
216
Input
39
Total output
33
Reasoning within output
git_clean f002
100%
Passed
Tokens
227
Input
50
Total output
45
Reasoning within output
git_clean f003
100%
Passed
Tokens
224
Input
55
Total output
62
Reasoning within output
git_clean f004
100%
Passed
Tokens
224
Input
85
Total output
83
Reasoning within output
git_clean f005
100%
Passed
Tokens
216
Input
198
Total output
215
Reasoning within output
git_clean f006
100%
Passed
Tokens
242
Input
277
Total output
282
Reasoning within output
git_clean f007
100%
Passed
Tokens
238
Input
103
Total output
106
Reasoning within output
git_clean f008
100%
Passed
Tokens
240
Input
36
Total output
35
Reasoning within output
git_clean f009
100%
Passed
Tokens
233
Input
806
Total output
963
Reasoning within output
git_clean f010
100%
Passed
Tokens
230
Input
68
Total output
68
Reasoning within output
git_clean f011
60%
Failed
Tokens
229
Input
93
Total output
101
Reasoning within output
git_clean f012
100%
Passed
Tokens
230
Input
149
Total output
154
Reasoning within output
git_grep f001
100%
Passed
Tokens
221
Input
38
Total output
38
Reasoning within output
git_grep f002
100%
Passed
Tokens
231
Input
66
Total output
63
Reasoning within output
git_grep f003
100%
Passed
Tokens
252
Input
85
Total output
81
Reasoning within output
git_grep f004
0%
Failed
Tokens
244
Input
88
Total output
73
Reasoning within output
git_grep f005
100%
Passed
Tokens
274
Input
138
Total output
134
Reasoning within output
git_grep f006
100%
Passed
Tokens
209
Input
145
Total output
170
Reasoning within output
git_grep f007
100%
Passed
Tokens
322
Input
170
Total output
132
Reasoning within output
git_grep f008
100%
Passed
Tokens
228
Input
84
Total output
90
Reasoning within output
git_grep f009
100%
Passed
Tokens
222
Input
65
Total output
65
Reasoning within output
git_grep f010
100%
Passed
Tokens
232
Input
109
Total output
111
Reasoning within output
git_grep f011
100%
Passed
Tokens
273
Input
121
Total output
116
Reasoning within output
git_grep f012
100%
Passed
Tokens
233
Input
75
Total output
70
Reasoning within output
git_log_format f001
100%
Passed
Tokens
875
Input
110
Total output
87
Reasoning within output
git_log_format f002
100%
Passed
Tokens
866
Input
106
Total output
104
Reasoning within output
git_log_format f003
100%
Passed
Tokens
725
Input
102
Total output
88
Reasoning within output
git_log_format f004
0%
Failed
Tokens
881
Input
4
Total output
5
Reasoning within output
git_log_format f005
100%
Passed
Tokens
737
Input
93
Total output
71
Reasoning within output
git_log_format f006
100%
Passed
Tokens
871
Input
150
Total output
100
Reasoning within output
git_log_format f007
100%
Passed
Tokens
865
Input
55
Total output
52
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,116
Input
4
Total output
1
Reasoning within output
git_log_format f009
100%
Passed
Tokens
724
Input
45
Total output
48
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,217
Input
109
Total output
111
Reasoning within output
git_log_format f011
100%
Passed
Tokens
535
Input
71
Total output
70
Reasoning within output
git_log_format f012
100%
Passed
Tokens
487
Input
75
Total output
70
Reasoning within output
git_show f001
100%
Passed
Tokens
334
Input
33
Total output
36
Reasoning within output
git_show f002
100%
Passed
Tokens
339
Input
484
Total output
572
Reasoning within output
git_show f003
100%
Passed
Tokens
727
Input
89
Total output
69
Reasoning within output
git_show f004
100%
Passed
Tokens
555
Input
93
Total output
69
Reasoning within output
git_show f005
100%
Passed
Tokens
336
Input
70
Total output
72
Reasoning within output
git_show f006
100%
Passed
Tokens
344
Input
51
Total output
56
Reasoning within output
git_show f007
100%
Passed
Tokens
333
Input
54
Total output
54
Reasoning within output
git_show f008
100%
Passed
Tokens
349
Input
95
Total output
68
Reasoning within output
git_show f009
100%
Passed
Tokens
426
Input
110
Total output
102
Reasoning within output
git_show f010
100%
Passed
Tokens
334
Input
40
Total output
42
Reasoning within output
git_show f011
100%
Passed
Tokens
362
Input
33
Total output
35
Reasoning within output
git_show f012
100%
Passed
Tokens
457
Input
4
Total output
3
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
253
Input
329
Total output
391
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
273
Input
256
Total output
276
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
248
Input
278
Total output
320
Reasoning within output
merge_conflicts f004
0%
Failed
Tokens
299
Input
367
Total output
360
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
301
Input
272
Total output
276
Reasoning within output
merge_conflicts f006
0%
Failed
Tokens
288
Input
532
Total output
449
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
293
Input
239
Total output
230
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
275
Input
105
Total output
108
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
273
Input
76
Total output
77
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
343
Input
218
Total output
208
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
308
Input
234
Total output
182
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
394
Input
2,409
Total output
2,572
Reasoning within output
rebase f001
100%
Passed
Tokens
263
Input
419
Total output
476
Reasoning within output
rebase f002
100%
Passed
Tokens
291
Input
253
Total output
240
Reasoning within output
rebase f003
100%
Passed
Tokens
271
Input
118
Total output
127
Reasoning within output
rebase f004
100%
Passed
Tokens
306
Input
403
Total output
413
Reasoning within output
rebase f005
100%
Passed
Tokens
307
Input
183
Total output
184
Reasoning within output
rebase f006
100%
Passed
Tokens
302
Input
218
Total output
181
Reasoning within output
rebase f007
100%
Passed
Tokens
293
Input
108
Total output
114
Reasoning within output
rebase f008
100%
Passed
Tokens
286
Input
74
Total output
66
Reasoning within output
rebase f009
100%
Passed
Tokens
271
Input
102
Total output
105
Reasoning within output
rebase f010
100%
Passed
Tokens
368
Input
174
Total output
159
Reasoning within output
rebase f011
100%
Passed
Tokens
320
Input
169
Total output
123
Reasoning within output
rebase f012
0%
Failed
Tokens
425
Input
203
Total output
137
Reasoning within output
reflog f001
100%
Passed
Tokens
378
Input
385
Total output
276
Reasoning within output
reflog f002
100%
Passed
Tokens
364
Input
608
Total output
173
Reasoning within output
reflog f003
100%
Passed
Tokens
344
Input
695
Total output
186
Reasoning within output
reflog f004
100%
Passed
Tokens
448
Input
1,193
Total output
838
Reasoning within output
reflog f005
100%
Passed
Tokens
492
Input
909
Total output
425
Reasoning within output
reflog f006
100%
Passed
Tokens
385
Input
577
Total output
160
Reasoning within output
reflog f007
100%
Passed
Tokens
408
Input
842
Total output
478
Reasoning within output
reflog f008
100%
Passed
Tokens
459
Input
801
Total output
420
Reasoning within output
reflog f009
100%
Passed
Tokens
444
Input
790
Total output
210
Reasoning within output
reflog f010
100%
Passed
Tokens
395
Input
705
Total output
261
Reasoning within output
reflog f011
100%
Passed
Tokens
443
Input
1,969
Total output
1,460
Reasoning within output
reflog f012
100%
Passed
Tokens
447
Input
2,451
Total output
1,711
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
289
Input
129
Total output
84
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
428
Input
299
Total output
137
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
277
Input
159
Total output
93
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
277
Input
219
Total output
95
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
286
Input
171
Total output
53
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
334
Input
134
Total output
63
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
359
Input
147
Total output
77
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
329
Input
258
Total output
96
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
357
Input
346
Total output
120
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
286
Input
166
Total output
106
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
276
Input
298
Total output
116
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
287
Input
150
Total output
74
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
211
Input
47
Total output
45
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
259
Input
142
Total output
156
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
260
Input
173
Total output
147
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
246
Input
32
Total output
34
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
218
Input
53
Total output
24
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
248
Input
168
Total output
192
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
218
Input
40
Total output
27
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
252
Input
43
Total output
47
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
253
Input
35
Total output
36
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
255
Input
35
Total output
32
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
263
Input
34
Total output
33
Reasoning within output
submodule_usage f012
0%
Failed
Tokens
216
Input
66
Total output
56
Reasoning within output
tag_management f001
100%
Passed
Tokens
224
Input
33
Total output
27
Reasoning within output
tag_management f002
100%
Passed
Tokens
222
Input
77
Total output
55
Reasoning within output
tag_management f003
100%
Passed
Tokens
227
Input
33
Total output
22
Reasoning within output
tag_management f004
100%
Passed
Tokens
234
Input
66
Total output
60
Reasoning within output
tag_management f005
100%
Passed
Tokens
245
Input
79
Total output
71
Reasoning within output
tag_management f006
100%
Passed
Tokens
228
Input
82
Total output
67
Reasoning within output
tag_management f007
100%
Passed
Tokens
233
Input
253
Total output
237
Reasoning within output
tag_management f008
100%
Passed
Tokens
234
Input
101
Total output
61
Reasoning within output
tag_management f009
100%
Passed
Tokens
233
Input
131
Total output
120
Reasoning within output
tag_management f010
100%
Passed
Tokens
217
Input
43
Total output
32
Reasoning within output
tag_management f011
100%
Passed
Tokens
213
Input
29
Total output
27
Reasoning within output
tag_management f012
100%
Passed
Tokens
247
Input
306
Total output
244
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
293
Input
129
Total output
119
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
296
Input
989
Total output
1,001
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
352
Input
36
Total output
29
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
344
Input
41
Total output
41
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
281
Input
112
Total output
95
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
282
Input
54
Total output
40
Reasoning within output
worktree_usage f007
0%
Failed
Tokens
285
Input
63
Total output
33
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
309
Input
735
Total output
647
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
379
Input
63
Total output
68
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
349
Input
56
Total output
40
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
348
Input
35
Total output
27
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
285
Input
72
Total output
55
Reasoning within output