Anthropic / claude-haiku-4.5
medium
93.1%
190 / 204 fixtures · 1 run(s)
45,605 input / 113,136 total output / 67,371 reasoning within output tokens $0.61128500
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
+0.5%
Text: 93.1% →
JSON: 93.6%
+8
Gained
JSON pass / text fail
−7
Lost
Text pass / JSON fail
183
Unchanged Pass
Both pass
6
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|---|---|---|
| f010 | 0% (0/1) | 100% (1/1) | -100% |
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| branch_cleanup | 100% | 75% | -25% |
| rebase | 91.7% | 83.3% | -8.3% |
| commit_messages | 91.7% | 100% | + 8.3% |
| commit_squash | 91.7% | 100% | + 8.3% |
| git_clean | 91.7% | 100% | + 8.3% |
| merge_conflicts | 75% | 83.3% | + 8.3% |
| worktree_usage | 91.7% | 100% | + 8.3% |
| blame_forensics | 91.7% | 91.7% | + 0% |
| cherry_pick | 83.3% | 83.3% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_grep | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 91.7% | 91.7% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 83.3% | 83.3% | + 0% |
| tag_management | 100% | 100% | + 0% |
Changed Fixtures (15)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
280
Input
528
Total output
500
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
265
Input
581
Total output
467
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
294
Input
240
Total output
171
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
230
Input
420
Total output
374
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
270
Input
6,708
Total output
2,566
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
265
Input
1,041
Total output
765
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
233
Input
274
Total output
233
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
266
Input
347
Total output
326
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
225
Input
439
Total output
404
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
440
Input
362
Total output
340
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
269
Input
433
Total output
347
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
178
Input
371
Total output
350
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
137
Input
206
Total output
176
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
151
Input
214
Total output
176
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
129
Input
155
Total output
138
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
169
Input
169
Total output
159
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
142
Input
174
Total output
148
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
157
Input
223
Total output
192
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
139
Input
173
Total output
157
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
159
Input
148
Total output
126
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
114
Input
257
Total output
261
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
151
Input
191
Total output
156
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
102
Input
137
Total output
142
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
190
Input
243
Total output
173
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
137
Input
315
Total output
341
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
157
Input
515
Total output
450
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
130
Input
664
Total output
620
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
190
Input
655
Total output
537
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
199
Input
284
Total output
260
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
176
Input
398
Total output
361
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
174
Input
199
Total output
183
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
166
Input
130
Total output
109
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
150
Input
177
Total output
154
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
269
Input
522
Total output
517
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
210
Input
387
Total output
312
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
321
Input
656
Total output
520
Reasoning within output
commit_messages f001
95%
Passed
Tokens
147
Input
340
Total output
301
Reasoning within output
commit_messages f002
89.7%
Passed
Tokens
267
Input
403
Total output
376
Reasoning within output
commit_messages f003
94.3%
Passed
Tokens
123
Input
308
Total output
227
Reasoning within output
commit_messages f004
94.3%
Passed
Tokens
152
Input
226
Total output
188
Reasoning within output
commit_messages f005
91.7%
Passed
Tokens
146
Input
200
Total output
175
Reasoning within output
commit_messages f006
88.3%
Passed
Tokens
178
Input
425
Total output
422
Reasoning within output
commit_messages f007
92.7%
Passed
Tokens
240
Input
517
Total output
392
Reasoning within output
commit_messages f008
87.7%
Passed
Tokens
108
Input
469
Total output
325
Reasoning within output
commit_messages f009
50%
Passed
Tokens
171
Input
393
Total output
370
Reasoning within output
commit_messages f010
43.3%
Failed
Tokens
350
Input
985
Total output
512
Reasoning within output
commit_messages f011
63.3%
Passed
Tokens
194
Input
945
Total output
483
Reasoning within output
commit_messages f012
91.3%
Passed
Tokens
171
Input
318
Total output
274
Reasoning within output
commit_squash f001
100%
Passed
Tokens
168
Input
741
Total output
474
Reasoning within output
commit_squash f002
100%
Passed
Tokens
151
Input
286
Total output
256
Reasoning within output
commit_squash f003
0%
Failed
Tokens
160
Input
5,194
Total output
1,822
Reasoning within output
commit_squash f004
100%
Passed
Tokens
151
Input
368
Total output
313
Reasoning within output
commit_squash f005
100%
Passed
Tokens
147
Input
289
Total output
251
Reasoning within output
commit_squash f006
100%
Passed
Tokens
131
Input
256
Total output
223
Reasoning within output
commit_squash f007
100%
Passed
Tokens
135
Input
436
Total output
399
Reasoning within output
commit_squash f008
100%
Passed
Tokens
147
Input
303
Total output
286
Reasoning within output
commit_squash f009
100%
Passed
Tokens
139
Input
3,457
Total output
1,321
Reasoning within output
commit_squash f010
100%
Passed
Tokens
150
Input
350
Total output
317
Reasoning within output
commit_squash f011
100%
Passed
Tokens
162
Input
872
Total output
486
Reasoning within output
commit_squash f012
100%
Passed
Tokens
158
Input
290
Total output
222
Reasoning within output
git_bisect f001
100%
Passed
Tokens
217
Input
378
Total output
218
Reasoning within output
git_bisect f002
100%
Passed
Tokens
244
Input
472
Total output
218
Reasoning within output
git_bisect f003
100%
Passed
Tokens
236
Input
403
Total output
220
Reasoning within output
git_bisect f004
100%
Passed
Tokens
244
Input
405
Total output
210
Reasoning within output
git_bisect f005
100%
Passed
Tokens
242
Input
396
Total output
198
Reasoning within output
git_bisect f006
100%
Passed
Tokens
267
Input
408
Total output
202
Reasoning within output
git_bisect f007
100%
Passed
Tokens
240
Input
428
Total output
240
Reasoning within output
git_bisect f008
100%
Passed
Tokens
240
Input
455
Total output
286
Reasoning within output
git_bisect f009
100%
Passed
Tokens
240
Input
419
Total output
226
Reasoning within output
git_bisect f010
100%
Passed
Tokens
242
Input
376
Total output
191
Reasoning within output
git_bisect f011
100%
Passed
Tokens
242
Input
453
Total output
241
Reasoning within output
git_bisect f012
100%
Passed
Tokens
265
Input
407
Total output
196
Reasoning within output
git_clean f001
100%
Passed
Tokens
90
Input
344
Total output
317
Reasoning within output
git_clean f002
100%
Passed
Tokens
103
Input
125
Total output
109
Reasoning within output
git_clean f003
100%
Passed
Tokens
102
Input
147
Total output
137
Reasoning within output
git_clean f004
100%
Passed
Tokens
102
Input
193
Total output
167
Reasoning within output
git_clean f005
100%
Passed
Tokens
88
Input
4,694
Total output
1,764
Reasoning within output
git_clean f006
100%
Passed
Tokens
122
Input
541
Total output
501
Reasoning within output
git_clean f007
100%
Passed
Tokens
114
Input
309
Total output
270
Reasoning within output
git_clean f008
100%
Passed
Tokens
123
Input
268
Total output
246
Reasoning within output
git_clean f009
100%
Passed
Tokens
114
Input
1,897
Total output
878
Reasoning within output
git_clean f010
100%
Passed
Tokens
104
Input
401
Total output
386
Reasoning within output
git_clean f011
60%
Failed
Tokens
106
Input
253
Total output
215
Reasoning within output
git_clean f012
100%
Passed
Tokens
108
Input
437
Total output
380
Reasoning within output
git_grep f001
100%
Passed
Tokens
88
Input
122
Total output
109
Reasoning within output
git_grep f002
100%
Passed
Tokens
96
Input
112
Total output
95
Reasoning within output
git_grep f003
100%
Passed
Tokens
138
Input
132
Total output
99
Reasoning within output
git_grep f004
100%
Passed
Tokens
115
Input
138
Total output
105
Reasoning within output
git_grep f005
100%
Passed
Tokens
154
Input
185
Total output
143
Reasoning within output
git_grep f006
100%
Passed
Tokens
72
Input
269
Total output
294
Reasoning within output
git_grep f007
100%
Passed
Tokens
215
Input
786
Total output
549
Reasoning within output
git_grep f008
100%
Passed
Tokens
93
Input
92
Total output
80
Reasoning within output
git_grep f009
100%
Passed
Tokens
87
Input
119
Total output
99
Reasoning within output
git_grep f010
100%
Passed
Tokens
101
Input
106
Total output
83
Reasoning within output
git_grep f011
100%
Passed
Tokens
165
Input
159
Total output
115
Reasoning within output
git_grep f012
100%
Passed
Tokens
103
Input
140
Total output
102
Reasoning within output
git_log_format f001
100%
Passed
Tokens
824
Input
227
Total output
193
Reasoning within output
git_log_format f002
100%
Passed
Tokens
815
Input
162
Total output
141
Reasoning within output
git_log_format f003
100%
Passed
Tokens
696
Input
274
Total output
215
Reasoning within output
git_log_format f004
100%
Passed
Tokens
819
Input
306
Total output
190
Reasoning within output
git_log_format f005
100%
Passed
Tokens
676
Input
259
Total output
187
Reasoning within output
git_log_format f006
100%
Passed
Tokens
828
Input
335
Total output
186
Reasoning within output
git_log_format f007
100%
Passed
Tokens
833
Input
127
Total output
108
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,103
Input
209
Total output
158
Reasoning within output
git_log_format f009
100%
Passed
Tokens
686
Input
218
Total output
163
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,217
Input
277
Total output
178
Reasoning within output
git_log_format f011
100%
Passed
Tokens
454
Input
200
Total output
160
Reasoning within output
git_log_format f012
100%
Passed
Tokens
395
Input
171
Total output
119
Reasoning within output
git_show f001
100%
Passed
Tokens
221
Input
131
Total output
98
Reasoning within output
git_show f002
0%
Failed
Tokens
235
Input
626
Total output
539
Reasoning within output
git_show f003
100%
Passed
Tokens
697
Input
126
Total output
91
Reasoning within output
git_show f004
100%
Passed
Tokens
477
Input
149
Total output
110
Reasoning within output
git_show f005
100%
Passed
Tokens
239
Input
275
Total output
244
Reasoning within output
git_show f006
100%
Passed
Tokens
244
Input
222
Total output
157
Reasoning within output
git_show f007
100%
Passed
Tokens
220
Input
189
Total output
152
Reasoning within output
git_show f008
100%
Passed
Tokens
236
Input
132
Total output
90
Reasoning within output
git_show f009
100%
Passed
Tokens
326
Input
270
Total output
224
Reasoning within output
git_show f010
100%
Passed
Tokens
233
Input
150
Total output
131
Reasoning within output
git_show f011
100%
Passed
Tokens
257
Input
120
Total output
104
Reasoning within output
git_show f012
100%
Passed
Tokens
378
Input
177
Total output
132
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
127
Input
430
Total output
457
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
145
Input
704
Total output
595
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
120
Input
885
Total output
751
Reasoning within output
merge_conflicts f004
0%
Failed
Tokens
177
Input
788
Total output
509
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
185
Input
231
Total output
201
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
162
Input
1,975
Total output
880
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
175
Input
255
Total output
211
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
149
Input
135
Total output
120
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
149
Input
406
Total output
372
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
232
Input
422
Total output
377
Reasoning within output
merge_conflicts f011
0%
Failed
Tokens
188
Input
568
Total output
429
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
284
Input
972
Total output
562
Reasoning within output
rebase f001
100%
Passed
Tokens
138
Input
3,428
Total output
1,621
Reasoning within output
rebase f002
100%
Passed
Tokens
166
Input
235
Total output
209
Reasoning within output
rebase f003
100%
Passed
Tokens
146
Input
423
Total output
389
Reasoning within output
rebase f004
100%
Passed
Tokens
189
Input
365
Total output
294
Reasoning within output
rebase f005
100%
Passed
Tokens
190
Input
1,689
Total output
811
Reasoning within output
rebase f006
100%
Passed
Tokens
175
Input
2,068
Total output
932
Reasoning within output
rebase f007
100%
Passed
Tokens
174
Input
163
Total output
134
Reasoning within output
rebase f008
100%
Passed
Tokens
163
Input
202
Total output
187
Reasoning within output
rebase f009
100%
Passed
Tokens
148
Input
206
Total output
179
Reasoning within output
rebase f010
100%
Passed
Tokens
261
Input
325
Total output
277
Reasoning within output
rebase f011
100%
Passed
Tokens
198
Input
367
Total output
278
Reasoning within output
rebase f012
0%
Failed
Tokens
319
Input
5,675
Total output
2,262
Reasoning within output
reflog f001
100%
Passed
Tokens
247
Input
301
Total output
197
Reasoning within output
reflog f002
100%
Passed
Tokens
246
Input
569
Total output
251
Reasoning within output
reflog f003
100%
Passed
Tokens
210
Input
666
Total output
244
Reasoning within output
reflog f004
100%
Passed
Tokens
328
Input
1,669
Total output
590
Reasoning within output
reflog f005
100%
Passed
Tokens
364
Input
780
Total output
345
Reasoning within output
reflog f006
100%
Passed
Tokens
260
Input
559
Total output
225
Reasoning within output
reflog f007
100%
Passed
Tokens
285
Input
632
Total output
352
Reasoning within output
reflog f008
100%
Passed
Tokens
351
Input
983
Total output
466
Reasoning within output
reflog f009
100%
Passed
Tokens
326
Input
1,184
Total output
419
Reasoning within output
reflog f010
100%
Passed
Tokens
282
Input
902
Total output
370
Reasoning within output
reflog f011
100%
Passed
Tokens
339
Input
2,092
Total output
836
Reasoning within output
reflog f012
100%
Passed
Tokens
307
Input
2,330
Total output
819
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
188
Input
253
Total output
148
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
363
Input
394
Total output
159
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
169
Input
284
Total output
154
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
167
Input
233
Total output
135
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
183
Input
400
Total output
169
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
238
Input
303
Total output
141
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
273
Input
319
Total output
145
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
231
Input
327
Total output
169
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
273
Input
291
Total output
151
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
179
Input
268
Total output
120
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
165
Input
216
Total output
141
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
188
Input
255
Total output
150
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
77
Input
134
Total output
100
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
134
Input
762
Total output
717
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
141
Input
1,418
Total output
715
Reasoning within output
submodule_usage f004
0%
Failed
Tokens
124
Input
154
Total output
146
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
84
Input
326
Total output
255
Reasoning within output
submodule_usage f006
0%
Failed
Tokens
126
Input
749
Total output
598
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
87
Input
223
Total output
166
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
134
Input
612
Total output
516
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
129
Input
319
Total output
306
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
138
Input
560
Total output
550
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
139
Input
126
Total output
114
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
85
Input
124
Total output
91
Reasoning within output
tag_management f001
100%
Passed
Tokens
90
Input
124
Total output
106
Reasoning within output
tag_management f002
100%
Passed
Tokens
92
Input
172
Total output
122
Reasoning within output
tag_management f003
100%
Passed
Tokens
95
Input
222
Total output
206
Reasoning within output
tag_management f004
100%
Passed
Tokens
99
Input
91
Total output
77
Reasoning within output
tag_management f005
100%
Passed
Tokens
113
Input
185
Total output
138
Reasoning within output
tag_management f006
100%
Passed
Tokens
99
Input
159
Total output
107
Reasoning within output
tag_management f007
100%
Passed
Tokens
97
Input
613
Total output
464
Reasoning within output
tag_management f008
100%
Passed
Tokens
101
Input
3,547
Total output
1,360
Reasoning within output
tag_management f009
100%
Passed
Tokens
111
Input
278
Total output
212
Reasoning within output
tag_management f010
100%
Passed
Tokens
82
Input
150
Total output
122
Reasoning within output
tag_management f011
100%
Passed
Tokens
83
Input
106
Total output
96
Reasoning within output
tag_management f012
100%
Passed
Tokens
115
Input
317
Total output
282
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
173
Input
155
Total output
122
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
181
Input
469
Total output
386
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
242
Input
126
Total output
100
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
239
Input
97
Total output
85
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
167
Input
233
Total output
196
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
170
Input
173
Total output
117
Reasoning within output
worktree_usage f007
0%
Failed
Tokens
179
Input
453
Total output
356
Reasoning within output
worktree_usage f008
100%
Passed
Tokens
198
Input
572
Total output
403
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
282
Input
173
Total output
163
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
253
Input
168
Total output
126
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
249
Input
158
Total output
128
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
164
Input
153
Total output
105
Reasoning within output