Moonshotai / kimi-k3
max
90.2%
184 / 204 fixtures · 1 run(s)
50,105 input / 68,633 total output / 56,667 reasoning within output tokens $1.17981000
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-1%
Text: 90.2% →
JSON: 89.2%
+17
Gained
JSON pass / text fail
−17
Lost
Text pass / JSON fail
1
Unchanged Pass
Both pass
6
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| git_clean | 100% | 83.3% | -16.7% |
| rebase | 91.7% | 83.3% | -8.3% |
| git_show | 100% | 91.7% | -8.3% |
| submodule_usage | 91.7% | 100% | + 8.3% |
| commit_messages | 0% | 8.3% | + 8.3% |
| blame_forensics | 91.7% | 91.7% | + 0% |
| branch_cleanup | 100% | 100% | + 0% |
| cherry_pick | 83.3% | 83.3% | + 0% |
| commit_squash | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_grep | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| merge_conflicts | 91.7% | 91.7% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
| worktree_usage | 83.3% | 83.3% | + 0% |
Changed Fixtures (34)
f004 -loss f007 -loss f008 -loss f009 -loss f010 -loss f011 -loss f008 -loss f009 -loss f002 -loss f003 -loss f001 -loss f002 -loss f005 -loss f007 -loss f011 -loss f012 -loss f012 -loss f007 +gain f008 +gain f007 +gain f009 +gain f008 +gain f008 +gain f009 +gain f003 +gain f004 +gain f004 +gain f007 +gain f009 +gain f010 +gain f003 +gain f008 +gain f003 +gain f004 +gain
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
291
Input
126
Total output
106
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
275
Input
248
Total output
229
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
307
Input
85
Total output
64
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
243
Input
63
Total output
43
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
306
Input
733
Total output
713
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
287
Input
264
Total output
246
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
261
Input
147
Total output
128
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
287
Input
286
Total output
268
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
252
Input
134
Total output
115
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
441
Input
215
Total output
197
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
289
Input
71
Total output
53
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
207
Input
436
Total output
416
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
176
Input
118
Total output
99
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
187
Input
114
Total output
94
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
167
Input
142
Total output
126
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
200
Input
130
Total output
110
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
178
Input
170
Total output
152
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
193
Input
192
Total output
170
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
177
Input
76
Total output
56
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
194
Input
172
Total output
148
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
155
Input
110
Total output
94
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
189
Input
145
Total output
125
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
144
Input
118
Total output
102
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
229
Input
134
Total output
108
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
171
Input
188
Total output
169
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
190
Input
294
Total output
272
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
162
Input
459
Total output
441
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
224
Input
2,983
Total output
2,946
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
224
Input
167
Total output
131
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
209
Input
280
Total output
246
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
199
Input
101
Total output
78
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
199
Input
111
Total output
90
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
183
Input
158
Total output
138
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
286
Input
1,284
Total output
1,245
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
236
Input
249
Total output
209
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
334
Input
281
Total output
226
Reasoning within output
commit_messages f001
0%
Failed
Tokens
177
Input
192
Total output
137
Reasoning within output
commit_messages f002
0%
Failed
Tokens
274
Input
174
Total output
137
Reasoning within output
commit_messages f003
0%
Failed
Tokens
158
Input
153
Total output
91
Reasoning within output
commit_messages f004
0%
Failed
Tokens
181
Input
67
Total output
49
Reasoning within output
commit_messages f005
0%
Failed
Tokens
175
Input
162
Total output
113
Reasoning within output
commit_messages f006
0%
Failed
Tokens
210
Input
178
Total output
138
Reasoning within output
commit_messages f007
0%
Failed
Tokens
252
Input
140
Total output
119
Reasoning within output
commit_messages f008
0%
Failed
Tokens
147
Input
105
Total output
86
Reasoning within output
commit_messages f009
0%
Failed
Tokens
203
Input
245
Total output
223
Reasoning within output
commit_messages f010
0%
Failed
Tokens
335
Input
293
Total output
232
Reasoning within output
commit_messages f011
35%
Failed
Tokens
217
Input
316
Total output
228
Reasoning within output
commit_messages f012
38.3%
Failed
Tokens
196
Input
306
Total output
258
Reasoning within output
commit_squash f001
100%
Passed
Tokens
212
Input
1,070
Total output
1,043
Reasoning within output
commit_squash f002
100%
Passed
Tokens
190
Input
159
Total output
136
Reasoning within output
commit_squash f003
100%
Passed
Tokens
198
Input
334
Total output
307
Reasoning within output
commit_squash f004
100%
Passed
Tokens
187
Input
198
Total output
172
Reasoning within output
commit_squash f005
100%
Passed
Tokens
186
Input
352
Total output
330
Reasoning within output
commit_squash f006
100%
Passed
Tokens
173
Input
293
Total output
267
Reasoning within output
commit_squash f007
100%
Passed
Tokens
178
Input
1,434
Total output
1,407
Reasoning within output
commit_squash f008
100%
Passed
Tokens
193
Input
388
Total output
361
Reasoning within output
commit_squash f009
100%
Passed
Tokens
174
Input
163
Total output
137
Reasoning within output
commit_squash f010
100%
Passed
Tokens
195
Input
185
Total output
155
Reasoning within output
commit_squash f011
100%
Passed
Tokens
202
Input
315
Total output
285
Reasoning within output
commit_squash f012
100%
Passed
Tokens
198
Input
1,132
Total output
1,097
Reasoning within output
git_bisect f001
100%
Passed
Tokens
243
Input
284
Total output
96
Reasoning within output
git_bisect f002
100%
Passed
Tokens
264
Input
182
Total output
78
Reasoning within output
git_bisect f003
100%
Passed
Tokens
266
Input
81
Total output
56
Reasoning within output
git_bisect f004
100%
Passed
Tokens
266
Input
133
Total output
30
Reasoning within output
git_bisect f005
100%
Passed
Tokens
266
Input
170
Total output
151
Reasoning within output
git_bisect f006
100%
Passed
Tokens
295
Input
268
Total output
67
Reasoning within output
git_bisect f007
100%
Passed
Tokens
272
Input
294
Total output
99
Reasoning within output
git_bisect f008
100%
Passed
Tokens
268
Input
216
Total output
50
Reasoning within output
git_bisect f009
100%
Passed
Tokens
270
Input
213
Total output
63
Reasoning within output
git_bisect f010
100%
Passed
Tokens
268
Input
387
Total output
172
Reasoning within output
git_bisect f011
100%
Passed
Tokens
272
Input
212
Total output
93
Reasoning within output
git_bisect f012
100%
Passed
Tokens
301
Input
275
Total output
103
Reasoning within output
git_clean f001
100%
Passed
Tokens
128
Input
201
Total output
178
Reasoning within output
git_clean f002
100%
Passed
Tokens
138
Input
81
Total output
62
Reasoning within output
git_clean f003
100%
Passed
Tokens
135
Input
89
Total output
70
Reasoning within output
git_clean f004
100%
Passed
Tokens
136
Input
179
Total output
159
Reasoning within output
git_clean f005
100%
Passed
Tokens
127
Input
165
Total output
146
Reasoning within output
git_clean f006
100%
Passed
Tokens
154
Input
194
Total output
172
Reasoning within output
git_clean f007
100%
Passed
Tokens
142
Input
141
Total output
118
Reasoning within output
git_clean f008
100%
Passed
Tokens
149
Input
119
Total output
100
Reasoning within output
git_clean f009
100%
Passed
Tokens
143
Input
248
Total output
226
Reasoning within output
git_clean f010
100%
Passed
Tokens
138
Input
206
Total output
187
Reasoning within output
git_clean f011
100%
Passed
Tokens
140
Input
149
Total output
129
Reasoning within output
git_clean f012
100%
Passed
Tokens
141
Input
157
Total output
135
Reasoning within output
git_grep f001
100%
Passed
Tokens
129
Input
70
Total output
52
Reasoning within output
git_grep f002
100%
Passed
Tokens
141
Input
89
Total output
73
Reasoning within output
git_grep f003
100%
Passed
Tokens
164
Input
99
Total output
83
Reasoning within output
git_grep f004
100%
Passed
Tokens
153
Input
83
Total output
63
Reasoning within output
git_grep f005
100%
Passed
Tokens
184
Input
144
Total output
128
Reasoning within output
git_grep f006
100%
Passed
Tokens
118
Input
134
Total output
118
Reasoning within output
git_grep f007
100%
Passed
Tokens
233
Input
3,070
Total output
3,054
Reasoning within output
git_grep f008
100%
Passed
Tokens
137
Input
92
Total output
76
Reasoning within output
git_grep f009
100%
Passed
Tokens
131
Input
66
Total output
48
Reasoning within output
git_grep f010
100%
Passed
Tokens
140
Input
241
Total output
225
Reasoning within output
git_grep f011
100%
Passed
Tokens
185
Input
141
Total output
125
Reasoning within output
git_grep f012
100%
Passed
Tokens
142
Input
69
Total output
46
Reasoning within output
git_log_format f001
100%
Passed
Tokens
769
Input
152
Total output
136
Reasoning within output
git_log_format f002
100%
Passed
Tokens
752
Input
91
Total output
69
Reasoning within output
git_log_format f003
100%
Passed
Tokens
638
Input
83
Total output
59
Reasoning within output
git_log_format f004
100%
Passed
Tokens
793
Input
59
Total output
43
Reasoning within output
git_log_format f005
100%
Passed
Tokens
641
Input
162
Total output
142
Reasoning within output
git_log_format f006
100%
Passed
Tokens
775
Input
187
Total output
171
Reasoning within output
git_log_format f007
100%
Passed
Tokens
772
Input
67
Total output
49
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,002
Input
93
Total output
77
Reasoning within output
git_log_format f009
100%
Passed
Tokens
647
Input
72
Total output
56
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,117
Input
51
Total output
35
Reasoning within output
git_log_format f011
100%
Passed
Tokens
437
Input
74
Total output
57
Reasoning within output
git_log_format f012
100%
Passed
Tokens
388
Input
74
Total output
58
Reasoning within output
git_show f001
100%
Passed
Tokens
238
Input
64
Total output
45
Reasoning within output
git_show f002
100%
Passed
Tokens
242
Input
1,345
Total output
1,328
Reasoning within output
git_show f003
100%
Passed
Tokens
642
Input
114
Total output
93
Reasoning within output
git_show f004
100%
Passed
Tokens
464
Input
73
Total output
52
Reasoning within output
git_show f005
100%
Passed
Tokens
243
Input
176
Total output
159
Reasoning within output
git_show f006
100%
Passed
Tokens
257
Input
61
Total output
45
Reasoning within output
git_show f007
100%
Passed
Tokens
242
Input
104
Total output
85
Reasoning within output
git_show f008
100%
Passed
Tokens
256
Input
163
Total output
126
Reasoning within output
git_show f009
100%
Passed
Tokens
335
Input
153
Total output
137
Reasoning within output
git_show f010
100%
Passed
Tokens
242
Input
79
Total output
63
Reasoning within output
git_show f011
100%
Passed
Tokens
274
Input
55
Total output
38
Reasoning within output
git_show f012
100%
Passed
Tokens
366
Input
77
Total output
61
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
161
Input
173
Total output
154
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
181
Input
341
Total output
319
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
154
Input
591
Total output
573
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
211
Input
442
Total output
405
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
212
Input
267
Total output
236
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
196
Input
260
Total output
226
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
201
Input
99
Total output
76
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
183
Input
141
Total output
120
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
180
Input
152
Total output
132
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
251
Input
597
Total output
558
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
219
Input
221
Total output
185
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
301
Input
672
Total output
612
Reasoning within output
rebase f001
100%
Passed
Tokens
169
Input
1,234
Total output
1,215
Reasoning within output
rebase f002
100%
Passed
Tokens
198
Input
121
Total output
99
Reasoning within output
rebase f003
100%
Passed
Tokens
176
Input
233
Total output
212
Reasoning within output
rebase f004
100%
Passed
Tokens
224
Input
1,183
Total output
1,143
Reasoning within output
rebase f005
100%
Passed
Tokens
214
Input
440
Total output
407
Reasoning within output
rebase f006
100%
Passed
Tokens
209
Input
749
Total output
710
Reasoning within output
rebase f007
100%
Passed
Tokens
204
Input
661
Total output
635
Reasoning within output
rebase f008
100%
Passed
Tokens
197
Input
739
Total output
718
Reasoning within output
rebase f009
100%
Passed
Tokens
180
Input
57
Total output
37
Reasoning within output
rebase f010
100%
Passed
Tokens
274
Input
2,085
Total output
2,044
Reasoning within output
rebase f011
100%
Passed
Tokens
228
Input
315
Total output
275
Reasoning within output
rebase f012
0%
Failed
Tokens
328
Input
690
Total output
630
Reasoning within output
reflog f001
100%
Passed
Tokens
272
Input
254
Total output
221
Reasoning within output
reflog f002
100%
Passed
Tokens
269
Input
583
Total output
316
Reasoning within output
reflog f003
100%
Passed
Tokens
242
Input
977
Total output
588
Reasoning within output
reflog f004
100%
Passed
Tokens
353
Input
1,629
Total output
1,182
Reasoning within output
reflog f005
100%
Passed
Tokens
386
Input
987
Total output
634
Reasoning within output
reflog f006
100%
Passed
Tokens
282
Input
1,258
Total output
904
Reasoning within output
reflog f007
100%
Passed
Tokens
314
Input
1,128
Total output
704
Reasoning within output
reflog f008
100%
Passed
Tokens
371
Input
1,468
Total output
1,079
Reasoning within output
reflog f009
100%
Passed
Tokens
329
Input
796
Total output
399
Reasoning within output
reflog f010
100%
Passed
Tokens
308
Input
1,456
Total output
993
Reasoning within output
reflog f011
100%
Passed
Tokens
359
Input
2,014
Total output
1,553
Reasoning within output
reflog f012
100%
Passed
Tokens
338
Input
2,250
Total output
1,798
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
200
Input
180
Total output
69
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
342
Input
298
Total output
89
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
187
Input
214
Total output
143
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
187
Input
390
Total output
250
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
196
Input
309
Total output
192
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
243
Input
270
Total output
92
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
268
Input
147
Total output
72
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
239
Input
618
Total output
426
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
268
Input
426
Total output
234
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
194
Input
249
Total output
185
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
187
Input
400
Total output
275
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
197
Input
325
Total output
212
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
120
Input
96
Total output
70
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
162
Input
183
Total output
159
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
168
Input
206
Total output
167
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
161
Input
55
Total output
37
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
127
Input
256
Total output
216
Reasoning within output
submodule_usage f006
0%
Failed
Tokens
157
Input
199
Total output
173
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
127
Input
127
Total output
92
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
162
Input
283
Total output
263
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
157
Input
60
Total output
42
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
167
Input
120
Total output
99
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
169
Input
64
Total output
45
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
125
Input
145
Total output
119
Reasoning within output
tag_management f001
100%
Passed
Tokens
133
Input
119
Total output
98
Reasoning within output
tag_management f002
100%
Passed
Tokens
131
Input
108
Total output
76
Reasoning within output
tag_management f003
100%
Passed
Tokens
137
Input
80
Total output
56
Reasoning within output
tag_management f004
100%
Passed
Tokens
141
Input
171
Total output
154
Reasoning within output
tag_management f005
100%
Passed
Tokens
156
Input
68
Total output
45
Reasoning within output
tag_management f006
100%
Passed
Tokens
138
Input
99
Total output
73
Reasoning within output
tag_management f007
100%
Passed
Tokens
139
Input
117
Total output
92
Reasoning within output
tag_management f008
100%
Passed
Tokens
142
Input
296
Total output
260
Reasoning within output
tag_management f009
100%
Passed
Tokens
147
Input
119
Total output
89
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
105
Total output
85
Reasoning within output
tag_management f012
100%
Passed
Tokens
154
Input
253
Total output
229
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
197
Input
80
Total output
56
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
205
Input
184
Total output
148
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
250
Input
113
Total output
90
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
247
Input
58
Total output
39
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
195
Input
173
Total output
147
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
189
Input
91
Total output
62
Reasoning within output
worktree_usage f007
0%
Failed
Tokens
199
Input
221
Total output
183
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
217
Input
1,063
Total output
997
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
284
Input
42
Total output
23
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
258
Input
78
Total output
48
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
250
Input
60
Total output
37
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
190
Input
93
Total output
63
Reasoning within output