Minimax / minimax-m3
low
96.1%
196 / 204 fixtures · 1 run(s)
68,945 input / 43,538 total output / 36,039 reasoning within output tokens $0.07175850
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-22.1%
Text: 96.1% →
JSON: 74%
+3
Gained
JSON pass / text fail
−48
Lost
Text pass / JSON fail
148
Unchanged Pass
Both pass
5
Unchanged Fail
Both fail
Fixture Reliability Delta
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| rebase | 91.7% | 0% | -91.7% |
| commit_squash | 100% | 25% | -75% |
| tag_management | 100% | 33.3% | -66.7% |
| branch_cleanup | 100% | 66.7% | -33.3% |
| git_clean | 100% | 66.7% | -33.3% |
| blame_forensics | 100% | 75% | -25% |
| commit_messages | 100% | 83.3% | -16.7% |
| reflog | 100% | 83.3% | -16.7% |
| submodule_usage | 83.3% | 100% | + 16.7% |
| worktree_usage | 91.7% | 75% | -16.7% |
| merge_conflicts | 91.7% | 83.3% | -8.3% |
| cherry_pick | 83.3% | 75% | -8.3% |
| git_bisect | 100% | 100% | + 0% |
| git_grep | 91.7% | 91.7% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
Changed Fixtures (51)
f002 -loss f005 -loss f010 -loss f003 -loss f004 -loss f009 -loss f011 -loss f004 -loss f006 -loss f011 -loss f002 -loss f003 -loss f004 -loss f005 -loss f006 -loss f007 -loss f008 -loss f009 -loss f012 -loss f004 -loss f005 -loss f011 -loss f012 -loss f004 +gain f007 -loss f001 -loss f001 -loss f002 -loss f003 -loss f004 -loss f005 -loss f006 -loss f007 -loss f008 -loss f009 -loss f010 -loss f011 -loss f001 -loss f012 -loss f005 +gain f012 +gain f001 -loss f002 -loss f003 -loss f004 -loss f005 -loss f006 -loss f007 -loss f008 -loss f001 -loss f002 -loss
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
386
Input
304
Total output
358
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
371
Input
585
Total output
589
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
395
Input
103
Total output
90
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
335
Input
164
Total output
173
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
406
Input
209
Total output
189
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
373
Input
298
Total output
267
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
350
Input
232
Total output
213
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
374
Input
430
Total output
451
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
345
Input
181
Total output
186
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
525
Input
305
Total output
326
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
375
Input
178
Total output
180
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
295
Input
162
Total output
171
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
272
Input
178
Total output
186
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
282
Input
194
Total output
184
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
260
Input
165
Total output
196
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
291
Input
138
Total output
141
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
272
Input
184
Total output
186
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
462
Input
148
Total output
144
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
267
Input
159
Total output
179
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
283
Input
152
Total output
144
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
250
Input
216
Total output
247
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
284
Input
155
Total output
140
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
237
Input
88
Total output
102
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
319
Input
180
Total output
152
Reasoning within output
cherry_pick f001
0%
Failed
Tokens
262
Input
151
Total output
166
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
283
Input
212
Total output
211
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
257
Input
150
Total output
158
Reasoning within output
cherry_pick f004
100%
Passed
Tokens
310
Input
376
Total output
379
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
316
Input
164
Total output
155
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
300
Input
218
Total output
176
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
294
Input
145
Total output
150
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
292
Input
119
Total output
118
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
276
Input
55
Total output
53
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
374
Input
168
Total output
154
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
329
Input
303
Total output
251
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
427
Input
261
Total output
246
Reasoning within output
commit_messages f001
82.7%
Passed
Tokens
271
Input
127
Total output
129
Reasoning within output
commit_messages f002
86.7%
Passed
Tokens
365
Input
50
Total output
51
Reasoning within output
commit_messages f003
95%
Passed
Tokens
251
Input
50
Total output
40
Reasoning within output
commit_messages f004
91.7%
Passed
Tokens
272
Input
64
Total output
70
Reasoning within output
commit_messages f005
92%
Passed
Tokens
267
Input
37
Total output
39
Reasoning within output
commit_messages f006
90.3%
Passed
Tokens
249
Input
149
Total output
143
Reasoning within output
commit_messages f007
86.7%
Passed
Tokens
350
Input
67
Total output
69
Reasoning within output
commit_messages f008
91%
Passed
Tokens
238
Input
46
Total output
43
Reasoning within output
commit_messages f009
91%
Passed
Tokens
290
Input
45
Total output
47
Reasoning within output
commit_messages f010
89.3%
Passed
Tokens
426
Input
76
Total output
69
Reasoning within output
commit_messages f011
81.7%
Passed
Tokens
308
Input
92
Total output
84
Reasoning within output
commit_messages f012
92.3%
Passed
Tokens
287
Input
135
Total output
164
Reasoning within output
commit_squash f001
100%
Passed
Tokens
299
Input
321
Total output
317
Reasoning within output
commit_squash f002
100%
Passed
Tokens
282
Input
199
Total output
188
Reasoning within output
commit_squash f003
100%
Passed
Tokens
289
Input
125
Total output
104
Reasoning within output
commit_squash f004
100%
Passed
Tokens
283
Input
301
Total output
288
Reasoning within output
commit_squash f005
100%
Passed
Tokens
279
Input
186
Total output
199
Reasoning within output
commit_squash f006
100%
Passed
Tokens
266
Input
146
Total output
145
Reasoning within output
commit_squash f007
100%
Passed
Tokens
269
Input
164
Total output
143
Reasoning within output
commit_squash f008
100%
Passed
Tokens
283
Input
140
Total output
120
Reasoning within output
commit_squash f009
100%
Passed
Tokens
271
Input
166
Total output
127
Reasoning within output
commit_squash f010
100%
Passed
Tokens
287
Input
159
Total output
134
Reasoning within output
commit_squash f011
100%
Passed
Tokens
295
Input
174
Total output
135
Reasoning within output
commit_squash f012
100%
Passed
Tokens
292
Input
153
Total output
114
Reasoning within output
git_bisect f001
100%
Passed
Tokens
338
Input
46
Total output
48
Reasoning within output
git_bisect f002
100%
Passed
Tokens
369
Input
139
Total output
123
Reasoning within output
git_bisect f003
100%
Passed
Tokens
353
Input
228
Total output
167
Reasoning within output
git_bisect f004
100%
Passed
Tokens
365
Input
256
Total output
182
Reasoning within output
git_bisect f005
100%
Passed
Tokens
359
Input
160
Total output
105
Reasoning within output
git_bisect f006
100%
Passed
Tokens
384
Input
88
Total output
66
Reasoning within output
git_bisect f007
100%
Passed
Tokens
361
Input
125
Total output
116
Reasoning within output
git_bisect f008
100%
Passed
Tokens
360
Input
178
Total output
168
Reasoning within output
git_bisect f009
100%
Passed
Tokens
361
Input
193
Total output
166
Reasoning within output
git_bisect f010
100%
Passed
Tokens
361
Input
191
Total output
164
Reasoning within output
git_bisect f011
100%
Passed
Tokens
361
Input
127
Total output
117
Reasoning within output
git_bisect f012
100%
Passed
Tokens
379
Input
136
Total output
121
Reasoning within output
git_clean f001
100%
Passed
Tokens
216
Input
303
Total output
329
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
55
Total output
65
Reasoning within output
git_clean f004
100%
Passed
Tokens
224
Input
385
Total output
419
Reasoning within output
git_clean f005
100%
Passed
Tokens
216
Input
240
Total output
230
Reasoning within output
git_clean f006
100%
Passed
Tokens
242
Input
173
Total output
177
Reasoning within output
git_clean f007
100%
Passed
Tokens
238
Input
236
Total output
239
Reasoning within output
git_clean f008
100%
Passed
Tokens
240
Input
35
Total output
36
Reasoning within output
git_clean f009
100%
Passed
Tokens
233
Input
209
Total output
244
Reasoning within output
git_clean f010
100%
Passed
Tokens
230
Input
229
Total output
258
Reasoning within output
git_clean f011
100%
Passed
Tokens
229
Input
99
Total output
111
Reasoning within output
git_clean f012
100%
Passed
Tokens
230
Input
203
Total output
202
Reasoning within output
git_grep f001
100%
Passed
Tokens
328
Input
91
Total output
106
Reasoning within output
git_grep f002
100%
Passed
Tokens
179
Input
79
Total output
75
Reasoning within output
git_grep f003
100%
Passed
Tokens
255
Input
84
Total output
83
Reasoning within output
git_grep f004
0%
Failed
Tokens
244
Input
57
Total output
47
Reasoning within output
git_grep f005
100%
Passed
Tokens
274
Input
137
Total output
135
Reasoning within output
git_grep f006
100%
Passed
Tokens
209
Input
55
Total output
66
Reasoning within output
git_grep f007
100%
Passed
Tokens
273
Input
147
Total output
143
Reasoning within output
git_grep f008
100%
Passed
Tokens
228
Input
86
Total output
95
Reasoning within output
git_grep f009
100%
Passed
Tokens
222
Input
39
Total output
34
Reasoning within output
git_grep f010
100%
Passed
Tokens
232
Input
57
Total output
61
Reasoning within output
git_grep f011
100%
Passed
Tokens
276
Input
107
Total output
103
Reasoning within output
git_grep f012
100%
Passed
Tokens
233
Input
63
Total output
63
Reasoning within output
git_log_format f001
100%
Passed
Tokens
862
Input
4
Total output
3
Reasoning within output
git_log_format f002
100%
Passed
Tokens
875
Input
125
Total output
125
Reasoning within output
git_log_format f003
100%
Passed
Tokens
716
Input
56
Total output
46
Reasoning within output
git_log_format f004
100%
Passed
Tokens
844
Input
109
Total output
79
Reasoning within output
git_log_format f005
100%
Passed
Tokens
737
Input
152
Total output
112
Reasoning within output
git_log_format f006
100%
Passed
Tokens
871
Input
106
Total output
75
Reasoning within output
git_log_format f007
100%
Passed
Tokens
875
Input
61
Total output
55
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,108
Input
101
Total output
80
Reasoning within output
git_log_format f009
100%
Passed
Tokens
719
Input
51
Total output
58
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,218
Input
113
Total output
115
Reasoning within output
git_log_format f011
100%
Passed
Tokens
531
Input
81
Total output
80
Reasoning within output
git_log_format f012
100%
Passed
Tokens
487
Input
92
Total output
72
Reasoning within output
git_show f001
100%
Passed
Tokens
337
Input
41
Total output
47
Reasoning within output
git_show f002
100%
Passed
Tokens
335
Input
135
Total output
150
Reasoning within output
git_show f003
100%
Passed
Tokens
711
Input
85
Total output
68
Reasoning within output
git_show f004
100%
Passed
Tokens
557
Input
102
Total output
85
Reasoning within output
git_show f005
100%
Passed
Tokens
337
Input
87
Total output
87
Reasoning within output
git_show f006
100%
Passed
Tokens
344
Input
50
Total output
48
Reasoning within output
git_show f007
100%
Passed
Tokens
333
Input
59
Total output
55
Reasoning within output
git_show f008
100%
Passed
Tokens
345
Input
76
Total output
52
Reasoning within output
git_show f009
100%
Passed
Tokens
421
Input
112
Total output
113
Reasoning within output
git_show f010
100%
Passed
Tokens
340
Input
176
Total output
178
Reasoning within output
git_show f011
100%
Passed
Tokens
360
Input
56
Total output
58
Reasoning within output
git_show f012
100%
Passed
Tokens
450
Input
117
Total output
116
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
253
Input
408
Total output
463
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
273
Input
343
Total output
371
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
248
Input
424
Total output
486
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
299
Input
439
Total output
423
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
304
Input
171
Total output
181
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
288
Input
222
Total output
180
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
290
Input
440
Total output
482
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
275
Input
32
Total output
26
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
273
Input
103
Total output
102
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
343
Input
167
Total output
142
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
311
Input
206
Total output
145
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
674
Input
215
Total output
169
Reasoning within output
rebase f001
100%
Passed
Tokens
262
Input
876
Total output
1,005
Reasoning within output
rebase f002
100%
Passed
Tokens
293
Input
161
Total output
137
Reasoning within output
rebase f003
100%
Passed
Tokens
272
Input
211
Total output
227
Reasoning within output
rebase f004
100%
Passed
Tokens
310
Input
451
Total output
478
Reasoning within output
rebase f005
100%
Passed
Tokens
309
Input
350
Total output
369
Reasoning within output
rebase f006
100%
Passed
Tokens
249
Input
266
Total output
240
Reasoning within output
rebase f007
100%
Passed
Tokens
293
Input
216
Total output
223
Reasoning within output
rebase f008
100%
Passed
Tokens
289
Input
84
Total output
86
Reasoning within output
rebase f009
100%
Passed
Tokens
271
Input
1,243
Total output
1,348
Reasoning within output
rebase f010
100%
Passed
Tokens
318
Input
321
Total output
295
Reasoning within output
rebase f011
100%
Passed
Tokens
320
Input
284
Total output
233
Reasoning within output
rebase f012
0%
Failed
Tokens
419
Input
508
Total output
463
Reasoning within output
reflog f001
100%
Passed
Tokens
381
Input
116
Total output
87
Reasoning within output
reflog f002
100%
Passed
Tokens
363
Input
426
Total output
171
Reasoning within output
reflog f003
100%
Passed
Tokens
350
Input
766
Total output
209
Reasoning within output
reflog f004
100%
Passed
Tokens
437
Input
1,301
Total output
829
Reasoning within output
reflog f005
100%
Passed
Tokens
493
Input
867
Total output
241
Reasoning within output
reflog f006
100%
Passed
Tokens
382
Input
579
Total output
138
Reasoning within output
reflog f007
100%
Passed
Tokens
406
Input
1,302
Total output
756
Reasoning within output
reflog f008
100%
Passed
Tokens
480
Input
1,138
Total output
471
Reasoning within output
reflog f009
100%
Passed
Tokens
438
Input
649
Total output
204
Reasoning within output
reflog f010
100%
Passed
Tokens
401
Input
853
Total output
380
Reasoning within output
reflog f011
100%
Passed
Tokens
439
Input
1,136
Total output
800
Reasoning within output
reflog f012
100%
Passed
Tokens
441
Input
1,292
Total output
670
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
289
Input
128
Total output
70
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
425
Input
372
Total output
135
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
277
Input
206
Total output
91
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
277
Input
127
Total output
66
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
287
Input
123
Total output
58
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
334
Input
251
Total output
111
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
352
Input
109
Total output
62
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
329
Input
187
Total output
95
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
357
Input
187
Total output
118
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
286
Input
132
Total output
85
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
276
Input
375
Total output
189
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
287
Input
129
Total output
99
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
211
Input
66
Total output
62
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
258
Input
140
Total output
157
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
264
Input
321
Total output
307
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
247
Input
20
Total output
19
Reasoning within output
submodule_usage f005
66.7%
Failed
Tokens
218
Input
67
Total output
45
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
248
Input
217
Total output
266
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
218
Input
220
Total output
235
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
256
Input
30
Total output
28
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
251
Input
34
Total output
34
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
256
Input
40
Total output
38
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
263
Input
32
Total output
33
Reasoning within output
submodule_usage f012
0%
Failed
Tokens
216
Input
101
Total output
103
Reasoning within output
tag_management f001
100%
Passed
Tokens
174
Input
59
Total output
51
Reasoning within output
tag_management f002
100%
Passed
Tokens
220
Input
72
Total output
46
Reasoning within output
tag_management f003
100%
Passed
Tokens
226
Input
33
Total output
20
Reasoning within output
tag_management f004
100%
Passed
Tokens
234
Input
27
Total output
28
Reasoning within output
tag_management f005
100%
Passed
Tokens
247
Input
34
Total output
27
Reasoning within output
tag_management f006
100%
Passed
Tokens
229
Input
64
Total output
38
Reasoning within output
tag_management f007
100%
Passed
Tokens
230
Input
140
Total output
124
Reasoning within output
tag_management f008
100%
Passed
Tokens
235
Input
135
Total output
98
Reasoning within output
tag_management f009
100%
Passed
Tokens
238
Input
127
Total output
115
Reasoning within output
tag_management f010
100%
Passed
Tokens
216
Input
34
Total output
25
Reasoning within output
tag_management f011
100%
Passed
Tokens
216
Input
30
Total output
27
Reasoning within output
tag_management f012
100%
Passed
Tokens
248
Input
300
Total output
221
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
288
Input
87
Total output
83
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
298
Input
269
Total output
223
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
295
Input
61
Total output
51
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
343
Input
33
Total output
32
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
281
Input
49
Total output
40
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
232
Input
97
Total output
81
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
285
Input
138
Total output
119
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
310
Input
1,409
Total output
1,336
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
375
Input
40
Total output
39
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
301
Input
172
Total output
155
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
351
Input
25
Total output
14
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
280
Input
96
Total output
77
Reasoning within output