Minimax / minimax-m3
high
93.1%
190 / 204 fixtures · 1 run(s)
68,711 input / 44,414 total output / 36,550 reasoning within output tokens $0.07249830
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-11.8%
Text: 93.1% →
JSON: 81.4%
+7
Gained
JSON pass / text fail
−31
Lost
Text pass / JSON fail
159
Unchanged Pass
Both pass
7
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| commit_squash | 100% | 33.3% | -66.7% |
| reflog | 100% | 58.3% | -41.7% |
| git_grep | 91.7% | 58.3% | -33.3% |
| branch_cleanup | 100% | 66.7% | -33.3% |
| git_clean | 91.7% | 66.7% | -25% |
| submodule_usage | 75% | 100% | + 25% |
| blame_forensics | 100% | 91.7% | -8.3% |
| merge_conflicts | 83.3% | 75% | -8.3% |
| tag_management | 100% | 91.7% | -8.3% |
| cherry_pick | 83.3% | 83.3% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 100% | 100% | + 0% |
| rebase | 75% | 75% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| worktree_usage | 83.3% | 83.3% | + 0% |
Changed Fixtures (38)
f006 -loss f003 -loss f007 -loss f009 -loss f011 -loss f001 -loss f011 +gain f002 -loss f003 -loss f006 -loss f007 -loss f008 -loss f009 -loss f011 -loss f012 -loss f005 -loss f007 -loss f011 -loss f001 -loss f006 -loss f007 -loss f011 -loss f001 -loss f006 +gain f007 -loss f005 +gain f011 -loss f001 -loss f006 -loss f007 -loss f008 -loss f012 -loss f003 +gain f006 +gain f012 +gain f009 -loss f001 -loss f007 +gain
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
386
Input
187
Total output
193
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
370
Input
319
Total output
309
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
394
Input
192
Total output
172
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
343
Input
134
Total output
144
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
399
Input
339
Total output
323
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
373
Input
405
Total output
381
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
355
Input
176
Total output
159
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
379
Input
238
Total output
241
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
343
Input
187
Total output
205
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
525
Input
419
Total output
444
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
376
Input
123
Total output
111
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
480
Input
234
Total output
220
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
272
Input
126
Total output
111
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
282
Input
166
Total output
181
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
261
Input
308
Total output
361
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
298
Input
335
Total output
338
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
272
Input
152
Total output
162
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
287
Input
110
Total output
124
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
267
Input
164
Total output
196
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
290
Input
95
Total output
93
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
248
Input
172
Total output
198
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
282
Input
197
Total output
184
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
238
Input
95
Total output
115
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
319
Input
231
Total output
212
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
262
Input
189
Total output
211
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
284
Input
136
Total output
126
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
257
Input
182
Total output
208
Reasoning within output
cherry_pick f004
100%
Passed
Tokens
259
Input
384
Total output
358
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
314
Input
157
Total output
154
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
300
Input
270
Total output
264
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
292
Input
147
Total output
143
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
291
Input
97
Total output
93
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
275
Input
75
Total output
74
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
378
Input
419
Total output
447
Reasoning within output
cherry_pick f011
0%
Failed
Tokens
278
Input
207
Total output
191
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
427
Input
246
Total output
190
Reasoning within output
commit_messages f001
87.7%
Passed
Tokens
271
Input
104
Total output
103
Reasoning within output
commit_messages f002
84.7%
Passed
Tokens
365
Input
68
Total output
70
Reasoning within output
commit_messages f003
94.3%
Passed
Tokens
251
Input
45
Total output
40
Reasoning within output
commit_messages f004
95%
Passed
Tokens
272
Input
56
Total output
62
Reasoning within output
commit_messages f005
91.7%
Passed
Tokens
267
Input
51
Total output
52
Reasoning within output
commit_messages f006
93%
Passed
Tokens
301
Input
165
Total output
186
Reasoning within output
commit_messages f007
87.3%
Passed
Tokens
350
Input
26
Total output
25
Reasoning within output
commit_messages f008
88.3%
Passed
Tokens
186
Input
42
Total output
37
Reasoning within output
commit_messages f009
88.3%
Passed
Tokens
290
Input
117
Total output
122
Reasoning within output
commit_messages f010
93.3%
Passed
Tokens
426
Input
74
Total output
78
Reasoning within output
commit_messages f011
73.7%
Passed
Tokens
308
Input
84
Total output
83
Reasoning within output
commit_messages f012
89.3%
Passed
Tokens
287
Input
120
Total output
143
Reasoning within output
commit_squash f001
100%
Passed
Tokens
309
Input
258
Total output
234
Reasoning within output
commit_squash f002
100%
Passed
Tokens
283
Input
121
Total output
114
Reasoning within output
commit_squash f003
100%
Passed
Tokens
293
Input
170
Total output
143
Reasoning within output
commit_squash f004
100%
Passed
Tokens
281
Input
135
Total output
119
Reasoning within output
commit_squash f005
100%
Passed
Tokens
281
Input
285
Total output
316
Reasoning within output
commit_squash f006
100%
Passed
Tokens
265
Input
154
Total output
153
Reasoning within output
commit_squash f007
100%
Passed
Tokens
212
Input
144
Total output
130
Reasoning within output
commit_squash f008
100%
Passed
Tokens
279
Input
148
Total output
128
Reasoning within output
commit_squash f009
100%
Passed
Tokens
269
Input
140
Total output
113
Reasoning within output
commit_squash f010
100%
Passed
Tokens
288
Input
137
Total output
116
Reasoning within output
commit_squash f011
100%
Passed
Tokens
289
Input
165
Total output
133
Reasoning within output
commit_squash f012
100%
Passed
Tokens
294
Input
137
Total output
106
Reasoning within output
git_bisect f001
100%
Passed
Tokens
338
Input
84
Total output
82
Reasoning within output
git_bisect f002
100%
Passed
Tokens
363
Input
93
Total output
80
Reasoning within output
git_bisect f003
100%
Passed
Tokens
359
Input
245
Total output
166
Reasoning within output
git_bisect f004
100%
Passed
Tokens
359
Input
106
Total output
108
Reasoning within output
git_bisect f005
100%
Passed
Tokens
355
Input
93
Total output
89
Reasoning within output
git_bisect f006
100%
Passed
Tokens
378
Input
116
Total output
96
Reasoning within output
git_bisect f007
100%
Passed
Tokens
361
Input
381
Total output
245
Reasoning within output
git_bisect f008
100%
Passed
Tokens
361
Input
202
Total output
145
Reasoning within output
git_bisect f009
100%
Passed
Tokens
365
Input
120
Total output
106
Reasoning within output
git_bisect f010
100%
Passed
Tokens
357
Input
118
Total output
108
Reasoning within output
git_bisect f011
100%
Passed
Tokens
363
Input
137
Total output
86
Reasoning within output
git_bisect f012
100%
Passed
Tokens
392
Input
356
Total output
150
Reasoning within output
git_clean f001
100%
Passed
Tokens
216
Input
223
Total output
227
Reasoning within output
git_clean f002
100%
Passed
Tokens
227
Input
42
Total output
39
Reasoning within output
git_clean f003
100%
Passed
Tokens
224
Input
109
Total output
116
Reasoning within output
git_clean f004
66.7%
Failed
Tokens
224
Input
118
Total output
126
Reasoning within output
git_clean f005
100%
Passed
Tokens
216
Input
268
Total output
295
Reasoning within output
git_clean f006
100%
Passed
Tokens
239
Input
91
Total output
87
Reasoning within output
git_clean f007
100%
Passed
Tokens
238
Input
159
Total output
151
Reasoning within output
git_clean f008
100%
Passed
Tokens
240
Input
169
Total output
189
Reasoning within output
git_clean f009
100%
Passed
Tokens
233
Input
118
Total output
128
Reasoning within output
git_clean f010
100%
Passed
Tokens
230
Input
88
Total output
90
Reasoning within output
git_clean f011
100%
Passed
Tokens
229
Input
178
Total output
180
Reasoning within output
git_clean f012
100%
Passed
Tokens
230
Input
139
Total output
139
Reasoning within output
git_grep f001
100%
Passed
Tokens
169
Input
35
Total output
30
Reasoning within output
git_grep f002
100%
Passed
Tokens
233
Input
54
Total output
53
Reasoning within output
git_grep f003
100%
Passed
Tokens
252
Input
83
Total output
83
Reasoning within output
git_grep f004
0%
Failed
Tokens
244
Input
72
Total output
53
Reasoning within output
git_grep f005
100%
Passed
Tokens
274
Input
134
Total output
130
Reasoning within output
git_grep f006
100%
Passed
Tokens
209
Input
63
Total output
82
Reasoning within output
git_grep f007
100%
Passed
Tokens
325
Input
146
Total output
124
Reasoning within output
git_grep f008
100%
Passed
Tokens
228
Input
78
Total output
84
Reasoning within output
git_grep f009
100%
Passed
Tokens
222
Input
49
Total output
41
Reasoning within output
git_grep f010
100%
Passed
Tokens
232
Input
37
Total output
37
Reasoning within output
git_grep f011
100%
Passed
Tokens
224
Input
110
Total output
107
Reasoning within output
git_grep f012
100%
Passed
Tokens
233
Input
92
Total output
87
Reasoning within output
git_log_format f001
100%
Passed
Tokens
866
Input
101
Total output
90
Reasoning within output
git_log_format f002
100%
Passed
Tokens
860
Input
125
Total output
106
Reasoning within output
git_log_format f003
100%
Passed
Tokens
725
Input
63
Total output
56
Reasoning within output
git_log_format f004
100%
Passed
Tokens
865
Input
102
Total output
81
Reasoning within output
git_log_format f005
100%
Passed
Tokens
737
Input
168
Total output
131
Reasoning within output
git_log_format f006
100%
Passed
Tokens
868
Input
160
Total output
109
Reasoning within output
git_log_format f007
100%
Passed
Tokens
861
Input
61
Total output
53
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,089
Input
104
Total output
86
Reasoning within output
git_log_format f009
100%
Passed
Tokens
718
Input
52
Total output
53
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,219
Input
59
Total output
59
Reasoning within output
git_log_format f011
100%
Passed
Tokens
530
Input
64
Total output
62
Reasoning within output
git_log_format f012
100%
Passed
Tokens
493
Input
42
Total output
45
Reasoning within output
git_show f001
100%
Passed
Tokens
334
Input
43
Total output
46
Reasoning within output
git_show f002
100%
Passed
Tokens
336
Input
165
Total output
185
Reasoning within output
git_show f003
100%
Passed
Tokens
729
Input
91
Total output
67
Reasoning within output
git_show f004
100%
Passed
Tokens
559
Input
61
Total output
52
Reasoning within output
git_show f005
100%
Passed
Tokens
334
Input
84
Total output
85
Reasoning within output
git_show f006
100%
Passed
Tokens
350
Input
4
Total output
3
Reasoning within output
git_show f007
100%
Passed
Tokens
333
Input
35
Total output
35
Reasoning within output
git_show f008
100%
Passed
Tokens
350
Input
81
Total output
44
Reasoning within output
git_show f009
100%
Passed
Tokens
424
Input
157
Total output
149
Reasoning within output
git_show f010
100%
Passed
Tokens
337
Input
106
Total output
115
Reasoning within output
git_show f011
100%
Passed
Tokens
367
Input
37
Total output
37
Reasoning within output
git_show f012
100%
Passed
Tokens
456
Input
64
Total output
69
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
253
Input
248
Total output
296
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
273
Input
388
Total output
417
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
248
Input
255
Total output
308
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
299
Input
664
Total output
723
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
304
Input
335
Total output
352
Reasoning within output
merge_conflicts f006
0%
Failed
Tokens
288
Input
426
Total output
338
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
293
Input
331
Total output
347
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
275
Input
105
Total output
114
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
273
Input
143
Total output
157
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
340
Input
263
Total output
265
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
311
Input
234
Total output
189
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
394
Input
882
Total output
889
Reasoning within output
rebase f001
0%
Failed
Tokens
262
Input
894
Total output
1,035
Reasoning within output
rebase f002
100%
Passed
Tokens
293
Input
187
Total output
162
Reasoning within output
rebase f003
100%
Passed
Tokens
219
Input
88
Total output
83
Reasoning within output
rebase f004
100%
Passed
Tokens
310
Input
246
Total output
223
Reasoning within output
rebase f005
0%
Failed
Tokens
307
Input
208
Total output
210
Reasoning within output
rebase f006
100%
Passed
Tokens
300
Input
302
Total output
264
Reasoning within output
rebase f007
100%
Passed
Tokens
243
Input
177
Total output
164
Reasoning within output
rebase f008
100%
Passed
Tokens
286
Input
83
Total output
82
Reasoning within output
rebase f009
100%
Passed
Tokens
271
Input
181
Total output
187
Reasoning within output
rebase f010
100%
Passed
Tokens
314
Input
157
Total output
129
Reasoning within output
rebase f011
100%
Passed
Tokens
321
Input
312
Total output
232
Reasoning within output
rebase f012
0%
Failed
Tokens
423
Input
277
Total output
216
Reasoning within output
reflog f001
100%
Passed
Tokens
370
Input
190
Total output
126
Reasoning within output
reflog f002
100%
Passed
Tokens
358
Input
549
Total output
174
Reasoning within output
reflog f003
100%
Passed
Tokens
343
Input
630
Total output
234
Reasoning within output
reflog f004
100%
Passed
Tokens
431
Input
1,964
Total output
1,386
Reasoning within output
reflog f005
100%
Passed
Tokens
485
Input
733
Total output
191
Reasoning within output
reflog f006
100%
Passed
Tokens
377
Input
729
Total output
275
Reasoning within output
reflog f007
100%
Passed
Tokens
402
Input
916
Total output
466
Reasoning within output
reflog f008
100%
Passed
Tokens
479
Input
667
Total output
236
Reasoning within output
reflog f009
100%
Passed
Tokens
458
Input
665
Total output
104
Reasoning within output
reflog f010
100%
Passed
Tokens
396
Input
833
Total output
333
Reasoning within output
reflog f011
100%
Passed
Tokens
444
Input
1,964
Total output
1,607
Reasoning within output
reflog f012
100%
Passed
Tokens
434
Input
1,436
Total output
678
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
290
Input
115
Total output
73
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
425
Input
427
Total output
170
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
277
Input
224
Total output
70
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
274
Input
156
Total output
111
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
286
Input
107
Total output
66
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
334
Input
137
Total output
75
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
355
Input
72
Total output
63
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
326
Input
174
Total output
71
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
357
Input
251
Total output
131
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
286
Input
190
Total output
120
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
275
Input
381
Total output
151
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
287
Input
202
Total output
116
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
211
Input
44
Total output
37
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
258
Input
150
Total output
145
Reasoning within output
submodule_usage f003
50%
Failed
Tokens
264
Input
1,236
Total output
1,274
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
380
Input
36
Total output
36
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
218
Input
202
Total output
196
Reasoning within output
submodule_usage f006
0%
Failed
Tokens
246
Input
230
Total output
269
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
215
Input
130
Total output
126
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
250
Input
79
Total output
83
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
254
Input
35
Total output
35
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
257
Input
36
Total output
33
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
260
Input
26
Total output
22
Reasoning within output
submodule_usage f012
0%
Failed
Tokens
216
Input
98
Total output
93
Reasoning within output
tag_management f001
100%
Passed
Tokens
223
Input
33
Total output
29
Reasoning within output
tag_management f002
100%
Passed
Tokens
224
Input
58
Total output
38
Reasoning within output
tag_management f003
100%
Passed
Tokens
230
Input
28
Total output
16
Reasoning within output
tag_management f004
100%
Passed
Tokens
233
Input
27
Total output
26
Reasoning within output
tag_management f005
100%
Passed
Tokens
243
Input
80
Total output
70
Reasoning within output
tag_management f006
100%
Passed
Tokens
234
Input
67
Total output
50
Reasoning within output
tag_management f007
100%
Passed
Tokens
232
Input
399
Total output
337
Reasoning within output
tag_management f008
100%
Passed
Tokens
235
Input
159
Total output
110
Reasoning within output
tag_management f009
100%
Passed
Tokens
237
Input
123
Total output
116
Reasoning within output
tag_management f010
100%
Passed
Tokens
215
Input
43
Total output
31
Reasoning within output
tag_management f011
100%
Passed
Tokens
219
Input
168
Total output
185
Reasoning within output
tag_management f012
100%
Passed
Tokens
253
Input
153
Total output
135
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
287
Input
63
Total output
57
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
291
Input
146
Total output
128
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
350
Input
179
Total output
165
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
346
Input
28
Total output
27
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
282
Input
125
Total output
126
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
287
Input
76
Total output
60
Reasoning within output
worktree_usage f007
0%
Failed
Tokens
287
Input
430
Total output
433
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
307
Input
1,130
Total output
1,085
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
374
Input
64
Total output
68
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
357
Input
50
Total output
35
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
350
Input
39
Total output
30
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
282
Input
52
Total output
36
Reasoning within output