Moonshotai / kimi-k3
high
90.7%
185 / 204 fixtures · 1 run(s)
50,163 input / 66,342 total output / 54,045 reasoning within output tokens $1.14393960
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-1.5%
Text: 90.7% →
JSON: 89.2%
+17
Gained
JSON pass / text fail
−15
Lost
Text pass / JSON fail
4
Unchanged Pass
Both pass
4
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| blame_forensics | 91.7% | 83.3% | -8.3% |
| worktree_usage | 91.7% | 83.3% | -8.3% |
| cherry_pick | 75% | 66.7% | -8.3% |
| commit_squash | 100% | 91.7% | -8.3% |
| commit_messages | 0% | 8.3% | + 8.3% |
| branch_cleanup | 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% |
| merge_conflicts | 91.7% | 91.7% | + 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% |
Changed Fixtures (32)
f007 -loss f008 -loss f012 -loss f012 -loss f005 -loss f003 -loss f004 -loss f008 -loss f008 -loss f009 -loss f005 -loss f001 -loss f001 -loss f002 -loss f004 -loss f009 +gain f010 +gain f011 +gain f001 +gain f008 +gain f010 +gain f008 +gain f009 +gain f011 +gain f012 +gain f010 +gain f004 +gain f002 +gain f003 +gain f005 +gain f002 +gain f006 +gain
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
288
Input
166
Total output
146
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
281
Input
189
Total output
170
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
301
Input
188
Total output
167
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
243
Input
152
Total output
132
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
306
Input
545
Total output
525
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
280
Input
531
Total output
513
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
256
Input
105
Total output
86
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
289
Input
87
Total output
69
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
250
Input
165
Total output
146
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
438
Input
337
Total output
319
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
282
Input
152
Total output
134
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
203
Input
293
Total output
273
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
173
Input
151
Total output
132
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
185
Input
182
Total output
162
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
169
Input
178
Total output
162
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
204
Input
150
Total output
130
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
179
Input
254
Total output
236
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
197
Input
215
Total output
193
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
177
Input
172
Total output
152
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
195
Input
177
Total output
153
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
156
Input
116
Total output
100
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
188
Input
159
Total output
139
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
145
Input
102
Total output
86
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
227
Input
218
Total output
192
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
171
Input
163
Total output
144
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
191
Input
463
Total output
441
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
163
Input
579
Total output
561
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
224
Input
680
Total output
646
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
224
Input
207
Total output
171
Reasoning within output
cherry_pick f006
0%
Failed
Tokens
208
Input
247
Total output
207
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
199
Input
90
Total output
67
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
200
Input
133
Total output
109
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
181
Input
88
Total output
68
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
284
Input
427
Total output
388
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
238
Input
279
Total output
243
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
334
Input
238
Total output
178
Reasoning within output
commit_messages f001
0%
Failed
Tokens
177
Input
77
Total output
55
Reasoning within output
commit_messages f002
0%
Failed
Tokens
274
Input
220
Total output
160
Reasoning within output
commit_messages f003
0%
Failed
Tokens
158
Input
169
Total output
146
Reasoning within output
commit_messages f004
0%
Failed
Tokens
181
Input
103
Total output
83
Reasoning within output
commit_messages f005
0%
Failed
Tokens
175
Input
133
Total output
114
Reasoning within output
commit_messages f006
0%
Failed
Tokens
210
Input
177
Total output
136
Reasoning within output
commit_messages f007
0%
Failed
Tokens
252
Input
160
Total output
111
Reasoning within output
commit_messages f008
0%
Failed
Tokens
147
Input
127
Total output
106
Reasoning within output
commit_messages f009
0%
Failed
Tokens
203
Input
213
Total output
158
Reasoning within output
commit_messages f010
0%
Failed
Tokens
335
Input
307
Total output
242
Reasoning within output
commit_messages f011
0%
Failed
Tokens
217
Input
265
Total output
177
Reasoning within output
commit_messages f012
0%
Failed
Tokens
196
Input
63
Total output
43
Reasoning within output
commit_squash f001
100%
Passed
Tokens
210
Input
1,297
Total output
1,270
Reasoning within output
commit_squash f002
100%
Passed
Tokens
188
Input
216
Total output
193
Reasoning within output
commit_squash f003
100%
Passed
Tokens
199
Input
366
Total output
339
Reasoning within output
commit_squash f004
100%
Passed
Tokens
189
Input
175
Total output
149
Reasoning within output
commit_squash f005
100%
Passed
Tokens
185
Input
237
Total output
215
Reasoning within output
commit_squash f006
100%
Passed
Tokens
170
Input
207
Total output
181
Reasoning within output
commit_squash f007
100%
Passed
Tokens
175
Input
258
Total output
231
Reasoning within output
commit_squash f008
100%
Passed
Tokens
188
Input
166
Total output
139
Reasoning within output
commit_squash f009
100%
Passed
Tokens
178
Input
435
Total output
409
Reasoning within output
commit_squash f010
100%
Passed
Tokens
193
Input
131
Total output
101
Reasoning within output
commit_squash f011
100%
Passed
Tokens
200
Input
126
Total output
96
Reasoning within output
commit_squash f012
100%
Passed
Tokens
200
Input
248
Total output
213
Reasoning within output
git_bisect f001
100%
Passed
Tokens
249
Input
377
Total output
142
Reasoning within output
git_bisect f002
100%
Passed
Tokens
270
Input
106
Total output
86
Reasoning within output
git_bisect f003
100%
Passed
Tokens
264
Input
208
Total output
33
Reasoning within output
git_bisect f004
100%
Passed
Tokens
274
Input
358
Total output
127
Reasoning within output
git_bisect f005
100%
Passed
Tokens
266
Input
197
Total output
111
Reasoning within output
git_bisect f006
100%
Passed
Tokens
293
Input
257
Total output
87
Reasoning within output
git_bisect f007
100%
Passed
Tokens
268
Input
258
Total output
81
Reasoning within output
git_bisect f008
100%
Passed
Tokens
276
Input
261
Total output
74
Reasoning within output
git_bisect f009
100%
Passed
Tokens
274
Input
335
Total output
108
Reasoning within output
git_bisect f010
100%
Passed
Tokens
266
Input
208
Total output
122
Reasoning within output
git_bisect f011
100%
Passed
Tokens
274
Input
294
Total output
110
Reasoning within output
git_bisect f012
100%
Passed
Tokens
289
Input
205
Total output
41
Reasoning within output
git_clean f001
100%
Passed
Tokens
128
Input
158
Total output
135
Reasoning within output
git_clean f002
100%
Passed
Tokens
138
Input
371
Total output
352
Reasoning within output
git_clean f003
100%
Passed
Tokens
135
Input
109
Total output
90
Reasoning within output
git_clean f004
100%
Passed
Tokens
136
Input
163
Total output
143
Reasoning within output
git_clean f005
100%
Passed
Tokens
127
Input
133
Total output
111
Reasoning within output
git_clean f006
100%
Passed
Tokens
154
Input
174
Total output
153
Reasoning within output
git_clean f007
100%
Passed
Tokens
142
Input
357
Total output
334
Reasoning within output
git_clean f008
100%
Passed
Tokens
149
Input
75
Total output
56
Reasoning within output
git_clean f009
100%
Passed
Tokens
143
Input
252
Total output
230
Reasoning within output
git_clean f010
100%
Passed
Tokens
138
Input
262
Total output
243
Reasoning within output
git_clean f011
100%
Passed
Tokens
140
Input
195
Total output
175
Reasoning within output
git_clean f012
100%
Passed
Tokens
141
Input
266
Total output
243
Reasoning within output
git_grep f001
100%
Passed
Tokens
129
Input
92
Total output
74
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
63
Total output
47
Reasoning within output
git_grep f004
100%
Passed
Tokens
153
Input
114
Total output
94
Reasoning within output
git_grep f005
100%
Passed
Tokens
184
Input
193
Total output
177
Reasoning within output
git_grep f006
100%
Passed
Tokens
118
Input
145
Total output
129
Reasoning within output
git_grep f007
100%
Passed
Tokens
233
Input
1,210
Total output
1,194
Reasoning within output
git_grep f008
100%
Passed
Tokens
137
Input
87
Total output
71
Reasoning within output
git_grep f009
100%
Passed
Tokens
131
Input
69
Total output
51
Reasoning within output
git_grep f010
100%
Passed
Tokens
140
Input
263
Total output
247
Reasoning within output
git_grep f011
100%
Passed
Tokens
185
Input
123
Total output
107
Reasoning within output
git_grep f012
100%
Passed
Tokens
142
Input
89
Total output
66
Reasoning within output
git_log_format f001
100%
Passed
Tokens
782
Input
113
Total output
97
Reasoning within output
git_log_format f002
100%
Passed
Tokens
751
Input
140
Total output
118
Reasoning within output
git_log_format f003
100%
Passed
Tokens
644
Input
108
Total output
84
Reasoning within output
git_log_format f004
100%
Passed
Tokens
787
Input
48
Total output
32
Reasoning within output
git_log_format f005
100%
Passed
Tokens
641
Input
163
Total output
143
Reasoning within output
git_log_format f006
100%
Passed
Tokens
775
Input
134
Total output
118
Reasoning within output
git_log_format f007
100%
Passed
Tokens
760
Input
70
Total output
52
Reasoning within output
git_log_format f008
100%
Passed
Tokens
988
Input
117
Total output
101
Reasoning within output
git_log_format f009
100%
Passed
Tokens
645
Input
60
Total output
44
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,105
Input
126
Total output
110
Reasoning within output
git_log_format f011
100%
Passed
Tokens
432
Input
112
Total output
95
Reasoning within output
git_log_format f012
100%
Passed
Tokens
400
Input
80
Total output
64
Reasoning within output
git_show f001
100%
Passed
Tokens
245
Input
67
Total output
48
Reasoning within output
git_show f002
100%
Passed
Tokens
244
Input
1,516
Total output
1,499
Reasoning within output
git_show f003
100%
Passed
Tokens
638
Input
118
Total output
97
Reasoning within output
git_show f004
100%
Passed
Tokens
468
Input
117
Total output
96
Reasoning within output
git_show f005
100%
Passed
Tokens
251
Input
129
Total output
112
Reasoning within output
git_show f006
100%
Passed
Tokens
253
Input
65
Total output
49
Reasoning within output
git_show f007
100%
Passed
Tokens
242
Input
114
Total output
95
Reasoning within output
git_show f008
100%
Passed
Tokens
256
Input
165
Total output
127
Reasoning within output
git_show f009
100%
Passed
Tokens
328
Input
176
Total output
160
Reasoning within output
git_show f010
100%
Passed
Tokens
245
Input
74
Total output
58
Reasoning within output
git_show f011
100%
Passed
Tokens
272
Input
87
Total output
70
Reasoning within output
git_show f012
100%
Passed
Tokens
365
Input
122
Total output
106
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
161
Input
204
Total output
185
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
181
Input
215
Total output
193
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
154
Input
362
Total output
344
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
211
Input
680
Total output
643
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
212
Input
359
Total output
328
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
196
Input
326
Total output
287
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
133
Total output
109
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
180
Input
369
Total output
349
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
251
Input
396
Total output
355
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
219
Input
223
Total output
183
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
301
Input
1,237
Total output
1,179
Reasoning within output
rebase f001
100%
Passed
Tokens
170
Input
602
Total output
583
Reasoning within output
rebase f002
100%
Passed
Tokens
200
Input
276
Total output
254
Reasoning within output
rebase f003
100%
Passed
Tokens
175
Input
126
Total output
108
Reasoning within output
rebase f004
100%
Passed
Tokens
222
Input
1,555
Total output
1,518
Reasoning within output
rebase f005
100%
Passed
Tokens
215
Input
562
Total output
534
Reasoning within output
rebase f006
100%
Passed
Tokens
208
Input
913
Total output
874
Reasoning within output
rebase f007
100%
Passed
Tokens
202
Input
614
Total output
591
Reasoning within output
rebase f008
100%
Passed
Tokens
196
Input
225
Total output
204
Reasoning within output
rebase f009
100%
Passed
Tokens
179
Input
114
Total output
94
Reasoning within output
rebase f010
100%
Passed
Tokens
276
Input
1,486
Total output
1,447
Reasoning within output
rebase f011
100%
Passed
Tokens
229
Input
200
Total output
160
Reasoning within output
rebase f012
0%
Failed
Tokens
332
Input
809
Total output
749
Reasoning within output
reflog f001
100%
Passed
Tokens
286
Input
317
Total output
276
Reasoning within output
reflog f002
100%
Passed
Tokens
266
Input
771
Total output
482
Reasoning within output
reflog f003
100%
Passed
Tokens
250
Input
766
Total output
405
Reasoning within output
reflog f004
100%
Passed
Tokens
356
Input
1,621
Total output
1,169
Reasoning within output
reflog f005
100%
Passed
Tokens
419
Input
1,135
Total output
741
Reasoning within output
reflog f006
100%
Passed
Tokens
290
Input
853
Total output
435
Reasoning within output
reflog f007
100%
Passed
Tokens
314
Input
1,305
Total output
996
Reasoning within output
reflog f008
100%
Passed
Tokens
373
Input
1,446
Total output
1,119
Reasoning within output
reflog f009
100%
Passed
Tokens
345
Input
689
Total output
360
Reasoning within output
reflog f010
100%
Passed
Tokens
315
Input
1,546
Total output
1,140
Reasoning within output
reflog f011
100%
Passed
Tokens
352
Input
1,729
Total output
1,357
Reasoning within output
reflog f012
100%
Passed
Tokens
345
Input
2,238
Total output
1,612
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
199
Input
112
Total output
58
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
345
Input
318
Total output
104
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
187
Input
291
Total output
101
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
187
Input
375
Total output
227
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
197
Input
368
Total output
217
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
243
Input
317
Total output
166
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
270
Input
216
Total output
112
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
239
Input
303
Total output
180
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
268
Input
360
Total output
163
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
194
Input
245
Total output
131
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
186
Input
628
Total output
412
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
197
Input
270
Total output
158
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
120
Input
76
Total output
53
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
164
Input
330
Total output
306
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
167
Input
1,156
Total output
1,110
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
156
Input
51
Total output
33
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
127
Input
497
Total output
457
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
154
Input
144
Total output
126
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
127
Input
657
Total output
625
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
160
Input
61
Total output
41
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
156
Input
64
Total output
46
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
166
Input
113
Total output
92
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
169
Input
67
Total output
48
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
125
Input
150
Total output
124
Reasoning within output
tag_management f001
100%
Passed
Tokens
134
Input
88
Total output
67
Reasoning within output
tag_management f002
100%
Passed
Tokens
132
Input
117
Total output
85
Reasoning within output
tag_management f003
100%
Passed
Tokens
137
Input
94
Total output
67
Reasoning within output
tag_management f004
100%
Passed
Tokens
141
Input
95
Total output
78
Reasoning within output
tag_management f005
100%
Passed
Tokens
151
Input
67
Total output
44
Reasoning within output
tag_management f006
100%
Passed
Tokens
141
Input
103
Total output
75
Reasoning within output
tag_management f007
100%
Passed
Tokens
139
Input
214
Total output
189
Reasoning within output
tag_management f008
100%
Passed
Tokens
144
Input
328
Total output
292
Reasoning within output
tag_management f009
100%
Passed
Tokens
146
Input
155
Total output
125
Reasoning within output
tag_management f010
100%
Passed
Tokens
125
Input
50
Total output
28
Reasoning within output
tag_management f011
100%
Passed
Tokens
123
Input
112
Total output
92
Reasoning within output
tag_management f012
100%
Passed
Tokens
158
Input
473
Total output
449
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
197
Input
79
Total output
55
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
200
Input
184
Total output
148
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
258
Input
117
Total output
94
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
256
Input
65
Total output
46
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
187
Input
85
Total output
59
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
189
Input
94
Total output
65
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
193
Input
2,187
Total output
2,153
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
214
Input
899
Total output
833
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
290
Input
59
Total output
40
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
260
Input
142
Total output
112
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
257
Input
113
Total output
90
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
188
Input
132
Total output
102
Reasoning within output