Moonshotai / kimi-k3
low
90.7%
185 / 204 fixtures · 1 run(s)
50,081 input / 64,649 total output / 52,661 reasoning within output tokens $1.10068650
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
+0%
Text: 90.7% →
JSON: 90.7%
+21
Gained
JSON pass / text fail
−28
Lost
Text pass / JSON fail
1
Unchanged Pass
Both pass
3
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| blame_forensics | 100% | 83.3% | -16.7% |
| merge_conflicts | 83.3% | 91.7% | + 8.3% |
| commit_messages | 0% | 8.3% | + 8.3% |
| branch_cleanup | 100% | 100% | + 0% |
| cherry_pick | 83.3% | 83.3% | + 0% |
| commit_squash | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_clean | 100% | 100% | + 0% |
| git_grep | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 100% | 100% | + 0% |
| rebase | 91.7% | 91.7% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
| worktree_usage | 83.3% | 83.3% | + 0% |
Changed Fixtures (49)
f008 -loss f009 -loss f010 -loss f011 -loss f002 -loss f011 -loss f012 -loss f007 -loss f008 -loss f006 -loss f011 -loss f012 -loss f009 -loss f010 -loss f007 -loss f008 -loss f005 -loss f006 -loss f009 -loss f003 -loss f003 -loss f001 -loss f002 -loss f003 -loss f004 -loss f005 -loss f006 -loss f007 -loss f003 +gain f004 +gain f003 +gain f004 +gain f008 +gain f001 +gain f002 +gain f004 +gain f001 +gain f002 +gain f007 +gain f001 +gain f011 +gain f006 +gain f007 +gain f011 +gain f008 +gain f009 +gain f002 +gain f010 +gain f011 +gain
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
292
Input
239
Total output
219
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
279
Input
459
Total output
440
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
303
Input
72
Total output
51
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
245
Input
411
Total output
391
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
305
Input
1,477
Total output
1,459
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
279
Input
407
Total output
389
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
256
Input
90
Total output
71
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
282
Input
352
Total output
334
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
254
Input
177
Total output
158
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
446
Input
111
Total output
93
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
282
Input
121
Total output
103
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
207
Input
256
Total output
236
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
177
Input
98
Total output
79
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
188
Input
208
Total output
188
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
169
Input
134
Total output
118
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
201
Input
109
Total output
89
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
185
Input
160
Total output
142
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
198
Input
208
Total output
186
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
174
Input
94
Total output
74
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
197
Input
172
Total output
148
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
156
Input
169
Total output
153
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
187
Input
180
Total output
160
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
144
Input
113
Total output
97
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
227
Input
151
Total output
125
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
171
Input
260
Total output
241
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
191
Input
291
Total output
269
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
164
Input
264
Total output
246
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
222
Input
532
Total output
498
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
224
Input
138
Total output
102
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
207
Input
530
Total output
491
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
200
Input
95
Total output
72
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
201
Input
98
Total output
77
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
184
Input
81
Total output
61
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
282
Input
384
Total output
336
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
237
Input
191
Total output
151
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
334
Input
437
Total output
382
Reasoning within output
commit_messages f001
0%
Failed
Tokens
177
Input
113
Total output
90
Reasoning within output
commit_messages f002
0%
Failed
Tokens
274
Input
210
Total output
155
Reasoning within output
commit_messages f003
0%
Failed
Tokens
158
Input
97
Total output
74
Reasoning within output
commit_messages f004
0%
Failed
Tokens
181
Input
89
Total output
71
Reasoning within output
commit_messages f005
0%
Failed
Tokens
175
Input
72
Total output
53
Reasoning within output
commit_messages f006
0%
Failed
Tokens
210
Input
280
Total output
244
Reasoning within output
commit_messages f007
0%
Failed
Tokens
252
Input
152
Total output
130
Reasoning within output
commit_messages f008
0%
Failed
Tokens
147
Input
116
Total output
97
Reasoning within output
commit_messages f009
0%
Failed
Tokens
203
Input
172
Total output
104
Reasoning within output
commit_messages f010
0%
Failed
Tokens
335
Input
338
Total output
257
Reasoning within output
commit_messages f011
0%
Failed
Tokens
217
Input
326
Total output
268
Reasoning within output
commit_messages f012
0%
Failed
Tokens
196
Input
223
Total output
203
Reasoning within output
commit_squash f001
100%
Passed
Tokens
209
Input
1,164
Total output
1,137
Reasoning within output
commit_squash f002
100%
Passed
Tokens
190
Input
220
Total output
197
Reasoning within output
commit_squash f003
100%
Passed
Tokens
201
Input
735
Total output
708
Reasoning within output
commit_squash f004
100%
Passed
Tokens
190
Input
368
Total output
342
Reasoning within output
commit_squash f005
100%
Passed
Tokens
184
Input
219
Total output
197
Reasoning within output
commit_squash f006
100%
Passed
Tokens
171
Input
360
Total output
334
Reasoning within output
commit_squash f007
100%
Passed
Tokens
173
Input
1,064
Total output
1,037
Reasoning within output
commit_squash f008
100%
Passed
Tokens
188
Input
209
Total output
182
Reasoning within output
commit_squash f009
100%
Passed
Tokens
180
Input
1,615
Total output
1,589
Reasoning within output
commit_squash f010
100%
Passed
Tokens
196
Input
104
Total output
74
Reasoning within output
commit_squash f011
100%
Passed
Tokens
201
Input
836
Total output
806
Reasoning within output
commit_squash f012
100%
Passed
Tokens
200
Input
175
Total output
140
Reasoning within output
git_bisect f001
100%
Passed
Tokens
251
Input
160
Total output
84
Reasoning within output
git_bisect f002
100%
Passed
Tokens
266
Input
293
Total output
130
Reasoning within output
git_bisect f003
100%
Passed
Tokens
268
Input
277
Total output
90
Reasoning within output
git_bisect f004
100%
Passed
Tokens
270
Input
155
Total output
51
Reasoning within output
git_bisect f005
100%
Passed
Tokens
266
Input
312
Total output
103
Reasoning within output
git_bisect f006
100%
Passed
Tokens
295
Input
251
Total output
95
Reasoning within output
git_bisect f007
100%
Passed
Tokens
264
Input
302
Total output
86
Reasoning within output
git_bisect f008
100%
Passed
Tokens
266
Input
343
Total output
162
Reasoning within output
git_bisect f009
100%
Passed
Tokens
266
Input
244
Total output
66
Reasoning within output
git_bisect f010
100%
Passed
Tokens
270
Input
316
Total output
126
Reasoning within output
git_bisect f011
100%
Passed
Tokens
266
Input
224
Total output
73
Reasoning within output
git_bisect f012
100%
Passed
Tokens
289
Input
212
Total output
129
Reasoning within output
git_clean f001
100%
Passed
Tokens
128
Input
197
Total output
174
Reasoning within output
git_clean f002
100%
Passed
Tokens
138
Input
210
Total output
188
Reasoning within output
git_clean f003
100%
Passed
Tokens
135
Input
313
Total output
294
Reasoning within output
git_clean f004
100%
Passed
Tokens
136
Input
191
Total output
171
Reasoning within output
git_clean f005
100%
Passed
Tokens
127
Input
139
Total output
120
Reasoning within output
git_clean f006
100%
Passed
Tokens
154
Input
458
Total output
437
Reasoning within output
git_clean f007
100%
Passed
Tokens
142
Input
201
Total output
178
Reasoning within output
git_clean f008
100%
Passed
Tokens
149
Input
106
Total output
87
Reasoning within output
git_clean f009
100%
Passed
Tokens
143
Input
882
Total output
860
Reasoning within output
git_clean f010
100%
Passed
Tokens
138
Input
121
Total output
102
Reasoning within output
git_clean f011
100%
Passed
Tokens
140
Input
180
Total output
160
Reasoning within output
git_clean f012
100%
Passed
Tokens
141
Input
136
Total output
114
Reasoning within output
git_grep f001
100%
Passed
Tokens
129
Input
71
Total output
53
Reasoning within output
git_grep f002
100%
Passed
Tokens
140
Input
57
Total output
41
Reasoning within output
git_grep f003
100%
Passed
Tokens
164
Input
53
Total output
37
Reasoning within output
git_grep f004
100%
Passed
Tokens
153
Input
55
Total output
35
Reasoning within output
git_grep f005
100%
Passed
Tokens
184
Input
138
Total output
122
Reasoning within output
git_grep f006
100%
Passed
Tokens
118
Input
143
Total output
127
Reasoning within output
git_grep f007
100%
Passed
Tokens
233
Input
978
Total output
962
Reasoning within output
git_grep f008
100%
Passed
Tokens
137
Input
71
Total output
55
Reasoning within output
git_grep f009
100%
Passed
Tokens
131
Input
71
Total output
53
Reasoning within output
git_grep f010
100%
Passed
Tokens
140
Input
261
Total output
245
Reasoning within output
git_grep f011
100%
Passed
Tokens
185
Input
119
Total output
103
Reasoning within output
git_grep f012
100%
Passed
Tokens
142
Input
65
Total output
42
Reasoning within output
git_log_format f001
100%
Passed
Tokens
783
Input
108
Total output
92
Reasoning within output
git_log_format f002
100%
Passed
Tokens
753
Input
121
Total output
99
Reasoning within output
git_log_format f003
100%
Passed
Tokens
645
Input
111
Total output
87
Reasoning within output
git_log_format f004
100%
Passed
Tokens
761
Input
105
Total output
89
Reasoning within output
git_log_format f005
100%
Passed
Tokens
641
Input
144
Total output
124
Reasoning within output
git_log_format f006
100%
Passed
Tokens
775
Input
133
Total output
117
Reasoning within output
git_log_format f007
100%
Passed
Tokens
764
Input
108
Total output
90
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,007
Input
70
Total output
54
Reasoning within output
git_log_format f009
100%
Passed
Tokens
642
Input
59
Total output
43
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,088
Input
148
Total output
132
Reasoning within output
git_log_format f011
100%
Passed
Tokens
430
Input
76
Total output
59
Reasoning within output
git_log_format f012
100%
Passed
Tokens
391
Input
32
Total output
16
Reasoning within output
git_show f001
100%
Passed
Tokens
241
Input
96
Total output
77
Reasoning within output
git_show f002
100%
Passed
Tokens
240
Input
210
Total output
193
Reasoning within output
git_show f003
100%
Passed
Tokens
630
Input
115
Total output
94
Reasoning within output
git_show f004
100%
Passed
Tokens
466
Input
102
Total output
81
Reasoning within output
git_show f005
100%
Passed
Tokens
248
Input
83
Total output
66
Reasoning within output
git_show f006
100%
Passed
Tokens
257
Input
98
Total output
82
Reasoning within output
git_show f007
100%
Passed
Tokens
242
Input
121
Total output
102
Reasoning within output
git_show f008
100%
Passed
Tokens
255
Input
134
Total output
98
Reasoning within output
git_show f009
100%
Passed
Tokens
332
Input
75
Total output
59
Reasoning within output
git_show f010
100%
Passed
Tokens
247
Input
80
Total output
64
Reasoning within output
git_show f011
100%
Passed
Tokens
272
Input
61
Total output
44
Reasoning within output
git_show f012
100%
Passed
Tokens
366
Input
121
Total output
105
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
161
Input
247
Total output
228
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
181
Input
213
Total output
191
Reasoning within output
merge_conflicts f003
0%
Failed
Tokens
154
Input
1,875
Total output
1,701
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
211
Input
948
Total output
911
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
212
Input
212
Total output
181
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
196
Input
620
Total output
581
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
201
Input
130
Total output
107
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
183
Input
116
Total output
95
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
180
Input
265
Total output
245
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
251
Input
552
Total output
511
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
219
Input
207
Total output
167
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
301
Input
641
Total output
586
Reasoning within output
rebase f001
100%
Passed
Tokens
170
Input
703
Total output
684
Reasoning within output
rebase f002
100%
Passed
Tokens
200
Input
249
Total output
227
Reasoning within output
rebase f003
100%
Passed
Tokens
177
Input
147
Total output
129
Reasoning within output
rebase f004
100%
Passed
Tokens
224
Input
1,110
Total output
1,073
Reasoning within output
rebase f005
100%
Passed
Tokens
217
Input
518
Total output
485
Reasoning within output
rebase f006
100%
Passed
Tokens
209
Input
972
Total output
933
Reasoning within output
rebase f007
100%
Passed
Tokens
201
Input
495
Total output
472
Reasoning within output
rebase f008
100%
Passed
Tokens
194
Input
639
Total output
618
Reasoning within output
rebase f009
100%
Passed
Tokens
179
Input
155
Total output
135
Reasoning within output
rebase f010
100%
Passed
Tokens
278
Input
1,030
Total output
991
Reasoning within output
rebase f011
100%
Passed
Tokens
228
Input
537
Total output
501
Reasoning within output
rebase f012
0%
Failed
Tokens
330
Input
665
Total output
607
Reasoning within output
reflog f001
100%
Passed
Tokens
266
Input
205
Total output
168
Reasoning within output
reflog f002
100%
Passed
Tokens
264
Input
526
Total output
333
Reasoning within output
reflog f003
100%
Passed
Tokens
253
Input
846
Total output
466
Reasoning within output
reflog f004
100%
Passed
Tokens
364
Input
1,438
Total output
1,036
Reasoning within output
reflog f005
100%
Passed
Tokens
383
Input
539
Total output
250
Reasoning within output
reflog f006
100%
Passed
Tokens
280
Input
1,133
Total output
800
Reasoning within output
reflog f007
100%
Passed
Tokens
319
Input
806
Total output
505
Reasoning within output
reflog f008
100%
Passed
Tokens
378
Input
1,013
Total output
717
Reasoning within output
reflog f009
100%
Passed
Tokens
349
Input
1,052
Total output
711
Reasoning within output
reflog f010
100%
Passed
Tokens
307
Input
1,066
Total output
713
Reasoning within output
reflog f011
100%
Passed
Tokens
351
Input
1,447
Total output
1,145
Reasoning within output
reflog f012
100%
Passed
Tokens
353
Input
2,515
Total output
1,920
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
201
Input
155
Total output
50
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
336
Input
445
Total output
184
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
187
Input
209
Total output
80
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
187
Input
344
Total output
200
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
196
Input
274
Total output
59
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
243
Input
329
Total output
170
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
266
Input
262
Total output
140
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
239
Input
574
Total output
405
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
268
Input
377
Total output
229
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
194
Input
192
Total output
87
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
186
Input
510
Total output
284
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
197
Input
287
Total output
166
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
120
Input
80
Total output
57
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
163
Input
282
Total output
258
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
171
Input
385
Total output
339
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
157
Input
102
Total output
84
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
127
Input
303
Total output
263
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
152
Input
103
Total output
85
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
127
Input
142
Total output
110
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
161
Input
72
Total output
52
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
158
Input
88
Total output
70
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
163
Input
80
Total output
59
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
168
Input
90
Total output
71
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
125
Input
123
Total output
97
Reasoning within output
tag_management f001
100%
Passed
Tokens
134
Input
103
Total output
82
Reasoning within output
tag_management f002
100%
Passed
Tokens
132
Input
108
Total output
76
Reasoning within output
tag_management f003
100%
Passed
Tokens
137
Input
65
Total output
41
Reasoning within output
tag_management f004
100%
Passed
Tokens
143
Input
110
Total output
90
Reasoning within output
tag_management f005
100%
Passed
Tokens
157
Input
74
Total output
51
Reasoning within output
tag_management f006
100%
Passed
Tokens
142
Input
85
Total output
59
Reasoning within output
tag_management f007
100%
Passed
Tokens
139
Input
144
Total output
119
Reasoning within output
tag_management f008
100%
Passed
Tokens
142
Input
171
Total output
135
Reasoning within output
tag_management f009
100%
Passed
Tokens
147
Input
176
Total output
144
Reasoning within output
tag_management f010
100%
Passed
Tokens
125
Input
86
Total output
64
Reasoning within output
tag_management f011
100%
Passed
Tokens
123
Input
88
Total output
68
Reasoning within output
tag_management f012
100%
Passed
Tokens
157
Input
299
Total output
275
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
201
Input
55
Total output
31
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
203
Input
237
Total output
198
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
254
Input
79
Total output
56
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
249
Input
67
Total output
48
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
188
Input
178
Total output
152
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
190
Input
92
Total output
63
Reasoning within output
worktree_usage f007
0%
Failed
Tokens
193
Input
362
Total output
324
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
223
Input
785
Total output
719
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
291
Input
53
Total output
34
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
254
Input
83
Total output
53
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
254
Input
78
Total output
55
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
189
Input
89
Total output
62
Reasoning within output