Moonshotai / kimi-k3
xhigh
87.3%
178 / 204 fixtures · 1 run(s)
47,997 input / 56,903 total output / 44,887 reasoning within output tokens $0.97897890
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
+3.4%
Text: 87.3% →
JSON: 90.7%
+22
Gained
JSON pass / text fail
−18
Lost
Text pass / JSON fail
4
Unchanged Pass
Both pass
10
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| cherry_pick | 50% | 83.3% | + 33.3% |
| commit_squash | 83.3% | 91.7% | + 8.3% |
| rebase | 91.7% | 83.3% | -8.3% |
| blame_forensics | 91.7% | 100% | + 8.3% |
| git_grep | 91.7% | 100% | + 8.3% |
| worktree_usage | 91.7% | 100% | + 8.3% |
| branch_cleanup | 91.7% | 91.7% | + 0% |
| commit_messages | 0% | 0% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_clean | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 100% | 100% | + 0% |
| merge_conflicts | 91.7% | 91.7% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
Changed Fixtures (40)
f006 +gain f010 -loss f007 -loss f008 -loss f007 -loss f008 -loss f004 -loss f001 -loss f012 -loss f007 -loss f003 -loss f004 -loss f001 -loss f002 -loss f004 -loss f011 -loss f007 -loss f001 -loss f002 -loss f004 +gain f005 +gain f007 +gain f001 +gain f008 +gain f005 +gain f004 +gain f001 +gain f011 +gain f012 +gain f007 +gain f005 +gain f006 +gain f004 +gain f005 +gain f006 +gain f012 +gain f004 +gain f005 +gain f006 +gain f007 +gain
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
296
Input
279
Total output
259
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
285
Input
268
Total output
249
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
301
Input
81
Total output
60
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
246
Input
270
Total output
250
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
309
Input
787
Total output
769
Reasoning within output
blame_forensics f006
0%
Failed
blame_forensics f007
100%
Passed
Tokens
259
Input
88
Total output
69
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
284
Input
424
Total output
406
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
249
Input
201
Total output
182
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
435
Input
271
Total output
253
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
281
Input
93
Total output
75
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
205
Input
266
Total output
246
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
176
Input
146
Total output
127
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
192
Input
167
Total output
147
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
171
Input
71
Total output
55
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
200
Input
157
Total output
137
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
180
Input
196
Total output
178
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
190
Input
136
Total output
114
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
177
Input
141
Total output
121
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
198
Input
186
Total output
162
Reasoning within output
branch_cleanup f009
0%
Failed
branch_cleanup f010
100%
Passed
Tokens
191
Input
152
Total output
132
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
145
Input
74
Total output
58
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
222
Input
118
Total output
92
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
171
Input
219
Total output
200
Reasoning within output
cherry_pick f002
0%
Failed
cherry_pick f003
0%
Failed
cherry_pick f004
0%
Failed
cherry_pick f005
100%
Passed
Tokens
223
Input
186
Total output
150
Reasoning within output
cherry_pick f006
0%
Failed
cherry_pick f007
100%
Passed
Tokens
198
Input
216
Total output
193
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
201
Input
105
Total output
84
Reasoning within output
cherry_pick f009
0%
Failed
cherry_pick f010
100%
Passed
Tokens
282
Input
507
Total output
468
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
237
Input
200
Total output
160
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
334
Input
380
Total output
318
Reasoning within output
commit_messages f001
0%
Failed
Tokens
177
Input
113
Total output
74
Reasoning within output
commit_messages f002
0%
Failed
Tokens
274
Input
132
Total output
113
Reasoning within output
commit_messages f003
0%
Failed
Tokens
158
Input
139
Total output
83
Reasoning within output
commit_messages f004
38.3%
Failed
Tokens
181
Input
97
Total output
50
Reasoning within output
commit_messages f005
0%
Failed
Tokens
175
Input
107
Total output
87
Reasoning within output
commit_messages f006
0%
Failed
Tokens
210
Input
236
Total output
164
Reasoning within output
commit_messages f007
0%
Failed
Tokens
252
Input
167
Total output
113
Reasoning within output
commit_messages f008
0%
Failed
Tokens
147
Input
141
Total output
96
Reasoning within output
commit_messages f009
0%
Failed
Tokens
203
Input
395
Total output
328
Reasoning within output
commit_messages f010
0%
Failed
Tokens
335
Input
308
Total output
235
Reasoning within output
commit_messages f011
0%
Failed
Tokens
217
Input
300
Total output
230
Reasoning within output
commit_messages f012
0%
Failed
Tokens
196
Input
282
Total output
238
Reasoning within output
commit_squash f001
100%
Passed
Tokens
207
Input
250
Total output
223
Reasoning within output
commit_squash f002
100%
Passed
Tokens
191
Input
146
Total output
123
Reasoning within output
commit_squash f003
100%
Passed
Tokens
201
Input
1,076
Total output
1,049
Reasoning within output
commit_squash f004
100%
Passed
Tokens
191
Input
418
Total output
392
Reasoning within output
commit_squash f005
100%
Passed
Tokens
187
Input
577
Total output
555
Reasoning within output
commit_squash f006
100%
Passed
Tokens
169
Input
290
Total output
264
Reasoning within output
commit_squash f007
100%
Passed
Tokens
175
Input
307
Total output
280
Reasoning within output
commit_squash f008
100%
Passed
Tokens
187
Input
171
Total output
144
Reasoning within output
commit_squash f009
100%
Failed
Tokens
177
Input
841
Total output
812
Reasoning within output
commit_squash f010
100%
Passed
Tokens
197
Input
155
Total output
125
Reasoning within output
commit_squash f011
0%
Failed
commit_squash f012
100%
Passed
Tokens
200
Input
207
Total output
172
Reasoning within output
git_bisect f001
100%
Passed
Tokens
247
Input
140
Total output
30
Reasoning within output
git_bisect f002
100%
Passed
Tokens
276
Input
358
Total output
131
Reasoning within output
git_bisect f003
100%
Passed
Tokens
260
Input
182
Total output
98
Reasoning within output
git_bisect f004
100%
Passed
Tokens
270
Input
196
Total output
34
Reasoning within output
git_bisect f005
100%
Passed
Tokens
266
Input
132
Total output
34
Reasoning within output
git_bisect f006
100%
Passed
Tokens
297
Input
115
Total output
91
Reasoning within output
git_bisect f007
100%
Passed
Tokens
266
Input
317
Total output
159
Reasoning within output
git_bisect f008
100%
Passed
Tokens
266
Input
170
Total output
80
Reasoning within output
git_bisect f009
100%
Passed
Tokens
264
Input
252
Total output
64
Reasoning within output
git_bisect f010
100%
Passed
Tokens
266
Input
340
Total output
176
Reasoning within output
git_bisect f011
100%
Passed
Tokens
264
Input
270
Total output
114
Reasoning within output
git_bisect f012
100%
Passed
Tokens
289
Input
356
Total output
141
Reasoning within output
git_clean f001
100%
Passed
Tokens
128
Input
155
Total output
132
Reasoning within output
git_clean f002
100%
Passed
Tokens
138
Input
251
Total output
232
Reasoning within output
git_clean f003
100%
Passed
Tokens
135
Input
96
Total output
74
Reasoning within output
git_clean f004
100%
Passed
Tokens
136
Input
145
Total output
125
Reasoning within output
git_clean f005
100%
Passed
Tokens
127
Input
268
Total output
249
Reasoning within output
git_clean f006
100%
Passed
Tokens
154
Input
181
Total output
160
Reasoning within output
git_clean f007
100%
Passed
Tokens
142
Input
251
Total output
228
Reasoning within output
git_clean f008
100%
Passed
Tokens
149
Input
109
Total output
90
Reasoning within output
git_clean f009
100%
Passed
Tokens
143
Input
158
Total output
136
Reasoning within output
git_clean f010
100%
Passed
Tokens
138
Input
166
Total output
147
Reasoning within output
git_clean f011
100%
Passed
Tokens
140
Input
205
Total output
182
Reasoning within output
git_clean f012
100%
Passed
Tokens
141
Input
134
Total output
112
Reasoning within output
git_grep f001
100%
Passed
Tokens
129
Input
64
Total output
46
Reasoning within output
git_grep f002
100%
Passed
Tokens
139
Input
87
Total output
71
Reasoning within output
git_grep f003
100%
Passed
Tokens
164
Input
112
Total output
96
Reasoning within output
git_grep f004
100%
Passed
Tokens
153
Input
98
Total output
78
Reasoning within output
git_grep f005
0%
Failed
git_grep f006
100%
Passed
Tokens
118
Input
143
Total output
127
Reasoning within output
git_grep f007
100%
Passed
Tokens
233
Input
1,557
Total output
1,541
Reasoning within output
git_grep f008
100%
Passed
Tokens
137
Input
86
Total output
70
Reasoning within output
git_grep f009
100%
Passed
Tokens
131
Input
67
Total output
49
Reasoning within output
git_grep f010
100%
Passed
Tokens
140
Input
193
Total output
177
Reasoning within output
git_grep f011
100%
Passed
Tokens
185
Input
179
Total output
163
Reasoning within output
git_grep f012
100%
Passed
Tokens
142
Input
96
Total output
73
Reasoning within output
git_log_format f001
100%
Passed
Tokens
775
Input
154
Total output
138
Reasoning within output
git_log_format f002
100%
Passed
Tokens
776
Input
96
Total output
74
Reasoning within output
git_log_format f003
100%
Passed
Tokens
633
Input
76
Total output
52
Reasoning within output
git_log_format f004
100%
Passed
Tokens
769
Input
92
Total output
76
Reasoning within output
git_log_format f005
100%
Passed
Tokens
641
Input
154
Total output
134
Reasoning within output
git_log_format f006
100%
Passed
Tokens
775
Input
167
Total output
151
Reasoning within output
git_log_format f007
100%
Passed
Tokens
793
Input
65
Total output
47
Reasoning within output
git_log_format f008
100%
Passed
Tokens
999
Input
110
Total output
94
Reasoning within output
git_log_format f009
100%
Passed
Tokens
635
Input
66
Total output
50
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,118
Input
81
Total output
65
Reasoning within output
git_log_format f011
100%
Passed
Tokens
423
Input
72
Total output
55
Reasoning within output
git_log_format f012
100%
Passed
Tokens
394
Input
71
Total output
55
Reasoning within output
git_show f001
100%
Passed
Tokens
238
Input
97
Total output
78
Reasoning within output
git_show f002
100%
Passed
Tokens
239
Input
420
Total output
403
Reasoning within output
git_show f003
100%
Passed
Tokens
632
Input
112
Total output
91
Reasoning within output
git_show f004
100%
Passed
Tokens
464
Input
77
Total output
56
Reasoning within output
git_show f005
100%
Passed
Tokens
249
Input
167
Total output
150
Reasoning within output
git_show f006
100%
Passed
Tokens
254
Input
65
Total output
49
Reasoning within output
git_show f007
100%
Passed
Tokens
242
Input
122
Total output
103
Reasoning within output
git_show f008
100%
Passed
Tokens
255
Input
106
Total output
70
Reasoning within output
git_show f009
100%
Passed
Tokens
330
Input
177
Total output
161
Reasoning within output
git_show f010
100%
Passed
Tokens
249
Input
75
Total output
59
Reasoning within output
git_show f011
100%
Passed
Tokens
272
Input
79
Total output
62
Reasoning within output
git_show f012
100%
Passed
Tokens
363
Input
122
Total output
106
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
161
Input
179
Total output
160
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
181
Input
256
Total output
234
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
154
Input
487
Total output
469
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
211
Input
497
Total output
460
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
212
Input
289
Total output
258
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
196
Input
212
Total output
173
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
201
Input
122
Total output
99
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
183
Input
215
Total output
194
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
180
Input
148
Total output
128
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
251
Input
273
Total output
234
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
219
Input
161
Total output
121
Reasoning within output
merge_conflicts f012
0%
Failed
rebase f001
100%
Passed
Tokens
169
Input
341
Total output
322
Reasoning within output
rebase f002
100%
Passed
Tokens
201
Input
95
Total output
73
Reasoning within output
rebase f003
100%
Passed
Tokens
177
Input
168
Total output
150
Reasoning within output
rebase f004
100%
Passed
Tokens
221
Input
980
Total output
943
Reasoning within output
rebase f005
100%
Passed
Tokens
217
Input
550
Total output
517
Reasoning within output
rebase f006
100%
Passed
Tokens
208
Input
158
Total output
124
Reasoning within output
rebase f007
100%
Passed
Tokens
201
Input
561
Total output
538
Reasoning within output
rebase f008
100%
Passed
Tokens
196
Input
417
Total output
393
Reasoning within output
rebase f009
100%
Passed
Tokens
178
Input
186
Total output
166
Reasoning within output
rebase f010
100%
Passed
Tokens
278
Input
520
Total output
481
Reasoning within output
rebase f011
100%
Passed
Tokens
226
Input
407
Total output
367
Reasoning within output
rebase f012
0%
Failed
Tokens
332
Input
1,231
Total output
1,176
Reasoning within output
reflog f001
100%
Passed
Tokens
264
Input
161
Total output
126
Reasoning within output
reflog f002
100%
Passed
Tokens
267
Input
845
Total output
577
Reasoning within output
reflog f003
100%
Passed
Tokens
251
Input
745
Total output
404
Reasoning within output
reflog f004
100%
Passed
Tokens
348
Input
2,034
Total output
1,501
Reasoning within output
reflog f005
100%
Passed
Tokens
394
Input
1,068
Total output
589
Reasoning within output
reflog f006
100%
Passed
Tokens
293
Input
800
Total output
421
Reasoning within output
reflog f007
100%
Passed
Tokens
310
Input
1,537
Total output
1,205
Reasoning within output
reflog f008
100%
Passed
Tokens
377
Input
1,273
Total output
895
Reasoning within output
reflog f009
100%
Passed
Tokens
337
Input
1,377
Total output
926
Reasoning within output
reflog f010
100%
Passed
Tokens
306
Input
1,121
Total output
704
Reasoning within output
reflog f011
100%
Passed
Tokens
347
Input
1,364
Total output
1,033
Reasoning within output
reflog f012
100%
Passed
Tokens
349
Input
1,455
Total output
990
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
200
Input
199
Total output
143
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
339
Input
409
Total output
169
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
187
Input
183
Total output
45
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
187
Input
299
Total output
160
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
196
Input
398
Total output
134
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
243
Input
276
Total output
155
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
266
Input
120
Total output
95
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
239
Input
355
Total output
174
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
268
Input
383
Total output
228
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
194
Input
196
Total output
109
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
188
Input
696
Total output
404
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
197
Input
369
Total output
236
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
120
Input
86
Total output
63
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
168
Input
241
Total output
217
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
171
Input
626
Total output
590
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
161
Input
49
Total output
31
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
127
Input
242
Total output
200
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
155
Input
222
Total output
204
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
127
Input
107
Total output
72
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
166
Input
653
Total output
630
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
156
Input
52
Total output
34
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
165
Input
77
Total output
57
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
167
Input
95
Total output
76
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
125
Input
124
Total output
98
Reasoning within output
tag_management f001
100%
Passed
Tokens
132
Input
110
Total output
89
Reasoning within output
tag_management f002
100%
Passed
Tokens
133
Input
127
Total output
91
Reasoning within output
tag_management f003
100%
Passed
Tokens
137
Input
134
Total output
110
Reasoning within output
tag_management f004
100%
Passed
Tokens
145
Input
133
Total output
116
Reasoning within output
tag_management f005
100%
Passed
Tokens
153
Input
88
Total output
65
Reasoning within output
tag_management f006
100%
Passed
Tokens
140
Input
97
Total output
71
Reasoning within output
tag_management f007
100%
Passed
Tokens
139
Input
196
Total output
171
Reasoning within output
tag_management f008
100%
Passed
Tokens
141
Input
154
Total output
118
Reasoning within output
tag_management f009
100%
Passed
Tokens
147
Input
151
Total output
121
Reasoning within output
tag_management f010
100%
Passed
Tokens
126
Input
75
Total output
53
Reasoning within output
tag_management f011
100%
Passed
Tokens
124
Input
91
Total output
71
Reasoning within output
tag_management f012
100%
Passed
Tokens
160
Input
226
Total output
202
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
200
Input
79
Total output
55
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
200
Input
120
Total output
84
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
250
Input
92
Total output
69
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
254
Input
50
Total output
31
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
191
Input
118
Total output
92
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
194
Input
117
Total output
88
Reasoning within output
worktree_usage f007
0%
Failed
Tokens
193
Input
449
Total output
411
Reasoning within output
worktree_usage f008
100%
Passed
Tokens
214
Input
1,577
Total output
1,513
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
281
Input
51
Total output
32
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
259
Input
97
Total output
67
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
249
Input
64
Total output
41
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
191
Input
125
Total output
98
Reasoning within output