Moonshotai / kimi-k3
medium
89.2%
182 / 204 fixtures · 1 run(s)
49,718 input / 64,249 total output / 52,834 reasoning within output tokens $1.10077950
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
+2.4%
Text: 89.2% →
JSON: 91.7%
+14
Gained
JSON pass / text fail
−14
Lost
Text pass / JSON fail
4
Unchanged Pass
Both pass
3
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| cherry_pick | 58.3% | 83.3% | + 25% |
| git_show | 91.7% | 100% | + 8.3% |
| commit_messages | 0% | 8.3% | + 8.3% |
| blame_forensics | 91.7% | 91.7% | + 0% |
| branch_cleanup | 100% | 100% | + 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% |
| 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% |
| worktree_usage | 91.7% | 91.7% | + 0% |
Changed Fixtures (28)
f001 -loss f005 -loss f006 -loss f010 -loss f009 -loss f001 -loss f004 -loss f003 -loss f008 -loss f009 -loss f003 -loss f011 -loss f012 -loss f012 -loss f012 +gain f008 +gain f005 +gain f006 +gain f005 +gain f002 +gain f009 +gain f005 +gain f006 +gain f011 +gain f012 +gain f006 +gain f009 +gain f010 +gain
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
298
Input
309
Total output
289
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
275
Input
209
Total output
190
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
308
Input
88
Total output
67
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
245
Input
303
Total output
283
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
305
Input
1,407
Total output
1,387
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
284
Input
740
Total output
722
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
256
Input
134
Total output
115
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
282
Input
245
Total output
227
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
249
Input
125
Total output
106
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
437
Input
339
Total output
321
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
283
Input
159
Total output
141
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
209
Input
226
Total output
206
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
175
Input
162
Total output
143
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
190
Input
236
Total output
216
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
166
Input
117
Total output
101
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
203
Input
283
Total output
263
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
176
Input
103
Total output
85
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
194
Input
219
Total output
197
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
174
Input
144
Total output
124
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
193
Input
153
Total output
129
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
155
Input
175
Total output
159
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
191
Input
165
Total output
145
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
145
Input
127
Total output
111
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
225
Input
120
Total output
94
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
170
Input
186
Total output
167
Reasoning within output
cherry_pick f002
0%
Failed
Tokens
190
Input
605
Total output
583
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
165
Input
533
Total output
515
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
223
Input
1,437
Total output
1,403
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
225
Input
214
Total output
180
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
208
Input
367
Total output
328
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
202
Input
189
Total output
166
Reasoning within output
cherry_pick f008
0%
Failed
cherry_pick f009
100%
Passed
Tokens
182
Input
82
Total output
62
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
284
Input
371
Total output
330
Reasoning within output
cherry_pick f011
0%
Failed
cherry_pick f012
0%
Failed
Tokens
334
Input
422
Total output
360
Reasoning within output
commit_messages f001
0%
Failed
Tokens
177
Input
113
Total output
91
Reasoning within output
commit_messages f002
0%
Failed
Tokens
274
Input
191
Total output
140
Reasoning within output
commit_messages f003
0%
Failed
Tokens
158
Input
90
Total output
67
Reasoning within output
commit_messages f004
0%
Failed
Tokens
181
Input
123
Total output
105
Reasoning within output
commit_messages f005
0%
Failed
Tokens
175
Input
129
Total output
69
Reasoning within output
commit_messages f006
0%
Failed
Tokens
210
Input
300
Total output
239
Reasoning within output
commit_messages f007
0%
Failed
Tokens
252
Input
176
Total output
154
Reasoning within output
commit_messages f008
0%
Failed
Tokens
147
Input
128
Total output
81
Reasoning within output
commit_messages f009
0%
Failed
Tokens
203
Input
392
Total output
314
Reasoning within output
commit_messages f010
0%
Failed
Tokens
335
Input
258
Total output
213
Reasoning within output
commit_messages f011
0%
Failed
Tokens
217
Input
427
Total output
372
Reasoning within output
commit_messages f012
0%
Failed
Tokens
196
Input
233
Total output
213
Reasoning within output
commit_squash f001
100%
Passed
Tokens
206
Input
433
Total output
406
Reasoning within output
commit_squash f002
100%
Passed
Tokens
194
Input
239
Total output
216
Reasoning within output
commit_squash f003
100%
Passed
Tokens
198
Input
318
Total output
291
Reasoning within output
commit_squash f004
100%
Passed
Tokens
187
Input
289
Total output
263
Reasoning within output
commit_squash f005
100%
Passed
Tokens
185
Input
275
Total output
253
Reasoning within output
commit_squash f006
100%
Passed
Tokens
171
Input
190
Total output
164
Reasoning within output
commit_squash f007
100%
Passed
Tokens
174
Input
385
Total output
358
Reasoning within output
commit_squash f008
100%
Passed
Tokens
188
Input
235
Total output
208
Reasoning within output
commit_squash f009
100%
Passed
Tokens
182
Input
318
Total output
292
Reasoning within output
commit_squash f010
100%
Passed
Tokens
194
Input
135
Total output
105
Reasoning within output
commit_squash f011
100%
Passed
Tokens
201
Input
130
Total output
100
Reasoning within output
commit_squash f012
100%
Passed
Tokens
202
Input
144
Total output
109
Reasoning within output
git_bisect f001
100%
Passed
Tokens
243
Input
246
Total output
133
Reasoning within output
git_bisect f002
100%
Passed
Tokens
274
Input
377
Total output
179
Reasoning within output
git_bisect f003
100%
Passed
Tokens
262
Input
318
Total output
160
Reasoning within output
git_bisect f004
100%
Passed
Tokens
268
Input
68
Total output
42
Reasoning within output
git_bisect f005
100%
Passed
Tokens
270
Input
319
Total output
120
Reasoning within output
git_bisect f006
100%
Passed
Tokens
295
Input
305
Total output
91
Reasoning within output
git_bisect f007
100%
Passed
Tokens
270
Input
204
Total output
125
Reasoning within output
git_bisect f008
100%
Passed
Tokens
274
Input
415
Total output
147
Reasoning within output
git_bisect f009
100%
Passed
Tokens
270
Input
405
Total output
177
Reasoning within output
git_bisect f010
100%
Passed
Tokens
272
Input
87
Total output
63
Reasoning within output
git_bisect f011
100%
Passed
Tokens
268
Input
193
Total output
118
Reasoning within output
git_bisect f012
100%
Passed
Tokens
297
Input
243
Total output
73
Reasoning within output
git_clean f001
100%
Passed
Tokens
128
Input
153
Total output
130
Reasoning within output
git_clean f002
100%
Passed
Tokens
138
Input
185
Total output
166
Reasoning within output
git_clean f003
100%
Passed
Tokens
135
Input
176
Total output
157
Reasoning within output
git_clean f004
100%
Passed
Tokens
136
Input
181
Total output
161
Reasoning within output
git_clean f005
100%
Passed
Tokens
127
Input
140
Total output
121
Reasoning within output
git_clean f006
100%
Passed
Tokens
154
Input
311
Total output
290
Reasoning within output
git_clean f007
100%
Passed
Tokens
142
Input
109
Total output
86
Reasoning within output
git_clean f008
100%
Passed
Tokens
149
Input
78
Total output
59
Reasoning within output
git_clean f009
100%
Passed
Tokens
143
Input
573
Total output
547
Reasoning within output
git_clean f010
100%
Passed
Tokens
138
Input
172
Total output
153
Reasoning within output
git_clean f011
100%
Passed
Tokens
140
Input
217
Total output
197
Reasoning within output
git_clean f012
100%
Passed
Tokens
141
Input
181
Total output
159
Reasoning within output
git_grep f001
100%
Passed
Tokens
129
Input
58
Total output
40
Reasoning within output
git_grep f002
100%
Passed
Tokens
143
Input
73
Total output
57
Reasoning within output
git_grep f003
100%
Passed
Tokens
164
Input
116
Total output
100
Reasoning within output
git_grep f004
100%
Passed
Tokens
153
Input
110
Total output
90
Reasoning within output
git_grep f005
100%
Passed
Tokens
184
Input
166
Total output
150
Reasoning within output
git_grep f006
100%
Passed
Tokens
118
Input
122
Total output
106
Reasoning within output
git_grep f007
100%
Passed
Tokens
233
Input
1,098
Total output
1,082
Reasoning within output
git_grep f008
100%
Passed
Tokens
137
Input
91
Total output
75
Reasoning within output
git_grep f009
100%
Passed
Tokens
131
Input
86
Total output
68
Reasoning within output
git_grep f010
100%
Passed
Tokens
140
Input
287
Total output
271
Reasoning within output
git_grep f011
100%
Passed
Tokens
185
Input
129
Total output
113
Reasoning within output
git_grep f012
100%
Passed
Tokens
142
Input
111
Total output
88
Reasoning within output
git_log_format f001
100%
Passed
Tokens
768
Input
143
Total output
127
Reasoning within output
git_log_format f002
100%
Passed
Tokens
761
Input
89
Total output
67
Reasoning within output
git_log_format f003
100%
Passed
Tokens
629
Input
136
Total output
112
Reasoning within output
git_log_format f004
100%
Passed
Tokens
774
Input
87
Total output
71
Reasoning within output
git_log_format f005
100%
Passed
Tokens
641
Input
167
Total output
147
Reasoning within output
git_log_format f006
100%
Passed
Tokens
775
Input
178
Total output
162
Reasoning within output
git_log_format f007
100%
Passed
Tokens
783
Input
68
Total output
48
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,024
Input
128
Total output
112
Reasoning within output
git_log_format f009
100%
Passed
Tokens
644
Input
124
Total output
108
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,090
Input
104
Total output
88
Reasoning within output
git_log_format f011
100%
Passed
Tokens
430
Input
105
Total output
88
Reasoning within output
git_log_format f012
100%
Passed
Tokens
398
Input
65
Total output
49
Reasoning within output
git_show f001
100%
Passed
Tokens
244
Input
89
Total output
70
Reasoning within output
git_show f002
0%
Failed
Tokens
244
Input
471
Total output
454
Reasoning within output
git_show f003
100%
Passed
Tokens
628
Input
103
Total output
82
Reasoning within output
git_show f004
100%
Passed
Tokens
474
Input
118
Total output
97
Reasoning within output
git_show f005
100%
Passed
Tokens
251
Input
146
Total output
129
Reasoning within output
git_show f006
100%
Passed
Tokens
253
Input
89
Total output
73
Reasoning within output
git_show f007
100%
Passed
Tokens
242
Input
127
Total output
108
Reasoning within output
git_show f008
100%
Passed
Tokens
256
Input
111
Total output
73
Reasoning within output
git_show f009
100%
Passed
Tokens
335
Input
140
Total output
124
Reasoning within output
git_show f010
100%
Passed
Tokens
244
Input
127
Total output
111
Reasoning within output
git_show f011
100%
Passed
Tokens
272
Input
63
Total output
46
Reasoning within output
git_show f012
100%
Passed
Tokens
364
Input
112
Total output
96
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
161
Input
325
Total output
306
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
181
Input
255
Total output
233
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
154
Input
923
Total output
905
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
211
Input
393
Total output
356
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
212
Input
179
Total output
143
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
196
Input
412
Total output
378
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
201
Input
184
Total output
161
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
183
Input
182
Total output
161
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
180
Input
203
Total output
183
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
251
Input
304
Total output
265
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
219
Input
262
Total output
222
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
301
Input
4,004
Total output
3,944
Reasoning within output
rebase f001
100%
Passed
Tokens
172
Input
374
Total output
355
Reasoning within output
rebase f002
100%
Passed
Tokens
198
Input
109
Total output
87
Reasoning within output
rebase f003
100%
Passed
Tokens
176
Input
195
Total output
177
Reasoning within output
rebase f004
100%
Passed
Tokens
223
Input
1,251
Total output
1,214
Reasoning within output
rebase f005
100%
Passed
Tokens
217
Input
338
Total output
305
Reasoning within output
rebase f006
100%
Passed
Tokens
208
Input
782
Total output
744
Reasoning within output
rebase f007
100%
Passed
Tokens
205
Input
381
Total output
358
Reasoning within output
rebase f008
100%
Passed
Tokens
193
Input
93
Total output
72
Reasoning within output
rebase f009
100%
Passed
Tokens
178
Input
145
Total output
125
Reasoning within output
rebase f010
100%
Passed
Tokens
274
Input
598
Total output
557
Reasoning within output
rebase f011
100%
Passed
Tokens
228
Input
551
Total output
515
Reasoning within output
rebase f012
0%
Failed
Tokens
330
Input
779
Total output
721
Reasoning within output
reflog f001
100%
Passed
Tokens
271
Input
256
Total output
221
Reasoning within output
reflog f002
100%
Passed
Tokens
268
Input
645
Total output
429
Reasoning within output
reflog f003
100%
Passed
Tokens
251
Input
757
Total output
398
Reasoning within output
reflog f004
100%
Passed
Tokens
362
Input
1,747
Total output
1,332
Reasoning within output
reflog f005
100%
Passed
Tokens
377
Input
528
Total output
243
Reasoning within output
reflog f006
100%
Passed
Tokens
295
Input
1,166
Total output
858
Reasoning within output
reflog f007
100%
Passed
Tokens
312
Input
801
Total output
445
Reasoning within output
reflog f008
100%
Passed
Tokens
387
Input
1,240
Total output
879
Reasoning within output
reflog f009
100%
Passed
Tokens
339
Input
1,231
Total output
882
Reasoning within output
reflog f010
100%
Passed
Tokens
299
Input
1,122
Total output
752
Reasoning within output
reflog f011
100%
Passed
Tokens
349
Input
1,463
Total output
1,115
Reasoning within output
reflog f012
100%
Passed
Tokens
359
Input
2,393
Total output
1,903
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
200
Input
202
Total output
111
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
336
Input
162
Total output
105
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
187
Input
276
Total output
144
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
187
Input
302
Total output
162
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
197
Input
468
Total output
318
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
243
Input
370
Total output
225
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
268
Input
205
Total output
109
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
239
Input
227
Total output
75
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
268
Input
495
Total output
338
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
194
Input
280
Total output
137
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
187
Input
282
Total output
148
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
197
Input
255
Total output
95
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
120
Input
172
Total output
149
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
163
Input
312
Total output
288
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
167
Input
1,257
Total output
1,209
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
158
Input
44
Total output
26
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
127
Input
193
Total output
153
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
156
Input
269
Total output
251
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
127
Input
126
Total output
91
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
164
Input
85
Total output
65
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
159
Input
77
Total output
59
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
166
Input
90
Total output
69
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
168
Input
70
Total output
51
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
125
Input
113
Total output
87
Reasoning within output
tag_management f001
100%
Passed
Tokens
137
Input
92
Total output
71
Reasoning within output
tag_management f002
100%
Passed
Tokens
133
Input
75
Total output
43
Reasoning within output
tag_management f003
100%
Passed
Tokens
137
Input
95
Total output
71
Reasoning within output
tag_management f004
100%
Passed
Tokens
142
Input
128
Total output
111
Reasoning within output
tag_management f005
100%
Passed
Tokens
154
Input
76
Total output
53
Reasoning within output
tag_management f006
100%
Passed
Tokens
140
Input
97
Total output
70
Reasoning within output
tag_management f007
100%
Passed
Tokens
138
Input
232
Total output
207
Reasoning within output
tag_management f008
100%
Passed
Tokens
141
Input
295
Total output
259
Reasoning within output
tag_management f009
100%
Passed
Tokens
146
Input
78
Total output
48
Reasoning within output
tag_management f010
100%
Passed
Tokens
125
Input
64
Total output
42
Reasoning within output
tag_management f011
100%
Passed
Tokens
123
Input
150
Total output
130
Reasoning within output
tag_management f012
100%
Passed
Tokens
159
Input
371
Total output
347
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
199
Input
80
Total output
56
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
204
Input
159
Total output
125
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
252
Input
148
Total output
125
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
247
Input
351
Total output
332
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
197
Input
110
Total output
84
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
195
Input
119
Total output
90
Reasoning within output
worktree_usage f007
0%
Failed
Tokens
197
Input
250
Total output
212
Reasoning within output
worktree_usage f008
100%
Passed
Tokens
215
Input
394
Total output
330
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
283
Input
111
Total output
92
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
261
Input
163
Total output
133
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
253
Input
82
Total output
59
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
191
Input
88
Total output
61
Reasoning within output