Anthropic / claude-haiku-4.5
xhigh
91.7%
187 / 204 fixtures · 1 run(s)
45,521 input / 151,184 total output / 80,115 reasoning within output tokens $0.80144100
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
+1.5%
Text: 91.7% →
JSON: 93.1%
+11
Gained
JSON pass / text fail
−8
Lost
Text pass / JSON fail
179
Unchanged Pass
Both pass
6
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|---|---|---|
| f002 | 0% (0/1) | 100% (1/1) | -100% |
| f006 | 0% (0/1) | 100% (1/1) | -100% |
| f010 | 0% (0/1) | 100% (1/1) | -100% |
| f011 | 0% (0/1) | 100% (1/1) | -100% |
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| commit_messages | 66.7% | 100% | + 33.3% |
| branch_cleanup | 100% | 75% | -25% |
| submodule_usage | 66.7% | 83.3% | + 16.7% |
| commit_squash | 100% | 91.7% | -8.3% |
| worktree_usage | 91.7% | 100% | + 8.3% |
| blame_forensics | 100% | 100% | + 0% |
| cherry_pick | 75% | 75% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_clean | 100% | 100% | + 0% |
| git_grep | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 91.7% | 91.7% | + 0% |
| merge_conflicts | 83.3% | 83.3% | + 0% |
| rebase | 83.3% | 83.3% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
Changed Fixtures (19)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
277
Input
807
Total output
554
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
259
Input
790
Total output
495
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
295
Input
236
Total output
171
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
228
Input
1,296
Total output
667
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
272
Input
9,900
Total output
4,151
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
261
Input
418
Total output
367
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
233
Input
268
Total output
204
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
271
Input
408
Total output
397
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
224
Input
324
Total output
305
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
437
Input
3,297
Total output
1,023
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
266
Input
369
Total output
303
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
175
Input
418
Total output
356
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
139
Input
157
Total output
134
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
150
Input
269
Total output
229
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
128
Input
181
Total output
177
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
166
Input
244
Total output
191
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
139
Input
191
Total output
170
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
153
Input
203
Total output
181
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
141
Input
131
Total output
128
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
150
Input
189
Total output
152
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
114
Input
180
Total output
180
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
146
Input
191
Total output
153
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
103
Input
116
Total output
116
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
192
Input
214
Total output
155
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
137
Input
324
Total output
340
Reasoning within output
cherry_pick f002
0%
Failed
Tokens
159
Input
1,200
Total output
685
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
130
Input
608
Total output
588
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
191
Input
1,617
Total output
777
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
198
Input
256
Total output
222
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
176
Input
338
Total output
288
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
172
Input
295
Total output
270
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
167
Input
288
Total output
266
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
150
Input
172
Total output
160
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
269
Input
1,095
Total output
692
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
209
Input
263
Total output
186
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
327
Input
7,176
Total output
2,901
Reasoning within output
commit_messages f001
95%
Passed
Tokens
147
Input
211
Total output
172
Reasoning within output
commit_messages f002
6.7%
Failed
Tokens
267
Input
594
Total output
397
Reasoning within output
commit_messages f003
94.7%
Passed
Tokens
123
Input
310
Total output
219
Reasoning within output
commit_messages f004
95%
Passed
Tokens
152
Input
285
Total output
230
Reasoning within output
commit_messages f005
91%
Passed
Tokens
146
Input
524
Total output
478
Reasoning within output
commit_messages f006
5%
Failed
Tokens
178
Input
757
Total output
515
Reasoning within output
commit_messages f007
53.7%
Passed
Tokens
240
Input
431
Total output
289
Reasoning within output
commit_messages f008
91%
Passed
Tokens
108
Input
405
Total output
244
Reasoning within output
commit_messages f009
53.7%
Passed
Tokens
171
Input
3,050
Total output
957
Reasoning within output
commit_messages f010
36.7%
Failed
Tokens
350
Input
412
Total output
324
Reasoning within output
commit_messages f011
38.3%
Failed
Tokens
194
Input
568
Total output
516
Reasoning within output
commit_messages f012
89.3%
Passed
Tokens
171
Input
418
Total output
359
Reasoning within output
commit_squash f001
100%
Passed
Tokens
169
Input
428
Total output
392
Reasoning within output
commit_squash f002
100%
Passed
Tokens
148
Input
312
Total output
275
Reasoning within output
commit_squash f003
100%
Passed
Tokens
164
Input
708
Total output
570
Reasoning within output
commit_squash f004
100%
Passed
Tokens
150
Input
627
Total output
428
Reasoning within output
commit_squash f005
100%
Passed
Tokens
150
Input
392
Total output
385
Reasoning within output
commit_squash f006
100%
Passed
Tokens
132
Input
281
Total output
240
Reasoning within output
commit_squash f007
100%
Passed
Tokens
134
Input
1,144
Total output
850
Reasoning within output
commit_squash f008
100%
Passed
Tokens
146
Input
1,212
Total output
714
Reasoning within output
commit_squash f009
100%
Passed
Tokens
138
Input
921
Total output
605
Reasoning within output
commit_squash f010
100%
Passed
Tokens
154
Input
346
Total output
293
Reasoning within output
commit_squash f011
100%
Passed
Tokens
164
Input
7,527
Total output
2,392
Reasoning within output
commit_squash f012
100%
Passed
Tokens
159
Input
425
Total output
338
Reasoning within output
git_bisect f001
100%
Passed
Tokens
211
Input
386
Total output
239
Reasoning within output
git_bisect f002
100%
Passed
Tokens
240
Input
367
Total output
192
Reasoning within output
git_bisect f003
100%
Passed
Tokens
240
Input
389
Total output
184
Reasoning within output
git_bisect f004
100%
Passed
Tokens
232
Input
468
Total output
277
Reasoning within output
git_bisect f005
100%
Passed
Tokens
246
Input
424
Total output
204
Reasoning within output
git_bisect f006
100%
Passed
Tokens
269
Input
544
Total output
281
Reasoning within output
git_bisect f007
100%
Passed
Tokens
250
Input
523
Total output
262
Reasoning within output
git_bisect f008
100%
Passed
Tokens
236
Input
488
Total output
281
Reasoning within output
git_bisect f009
100%
Passed
Tokens
242
Input
436
Total output
232
Reasoning within output
git_bisect f010
100%
Passed
Tokens
238
Input
472
Total output
276
Reasoning within output
git_bisect f011
100%
Passed
Tokens
236
Input
464
Total output
259
Reasoning within output
git_bisect f012
100%
Passed
Tokens
267
Input
353
Total output
153
Reasoning within output
git_clean f001
100%
Passed
Tokens
90
Input
1,201
Total output
769
Reasoning within output
git_clean f002
100%
Passed
Tokens
103
Input
120
Total output
104
Reasoning within output
git_clean f003
100%
Passed
Tokens
102
Input
141
Total output
128
Reasoning within output
git_clean f004
100%
Passed
Tokens
102
Input
466
Total output
418
Reasoning within output
git_clean f005
100%
Passed
Tokens
88
Input
609
Total output
522
Reasoning within output
git_clean f006
100%
Passed
Tokens
122
Input
238
Total output
205
Reasoning within output
git_clean f007
100%
Passed
Tokens
114
Input
293
Total output
251
Reasoning within output
git_clean f008
100%
Passed
Tokens
123
Input
173
Total output
157
Reasoning within output
git_clean f009
100%
Passed
Tokens
114
Input
377
Total output
367
Reasoning within output
git_clean f010
100%
Passed
Tokens
104
Input
165
Total output
148
Reasoning within output
git_clean f011
100%
Passed
Tokens
106
Input
289
Total output
248
Reasoning within output
git_clean f012
100%
Passed
Tokens
108
Input
378
Total output
333
Reasoning within output
git_grep f001
100%
Passed
Tokens
88
Input
120
Total output
107
Reasoning within output
git_grep f002
100%
Passed
Tokens
94
Input
94
Total output
78
Reasoning within output
git_grep f003
100%
Passed
Tokens
138
Input
129
Total output
95
Reasoning within output
git_grep f004
100%
Passed
Tokens
115
Input
125
Total output
98
Reasoning within output
git_grep f005
100%
Passed
Tokens
154
Input
192
Total output
150
Reasoning within output
git_grep f006
100%
Passed
Tokens
72
Input
233
Total output
245
Reasoning within output
git_grep f007
100%
Passed
Tokens
215
Input
386
Total output
287
Reasoning within output
git_grep f008
100%
Passed
Tokens
93
Input
99
Total output
86
Reasoning within output
git_grep f009
100%
Passed
Tokens
87
Input
75
Total output
62
Reasoning within output
git_grep f010
100%
Passed
Tokens
101
Input
98
Total output
79
Reasoning within output
git_grep f011
100%
Passed
Tokens
165
Input
143
Total output
101
Reasoning within output
git_grep f012
100%
Passed
Tokens
103
Input
130
Total output
92
Reasoning within output
git_log_format f001
100%
Passed
Tokens
840
Input
103
Total output
82
Reasoning within output
git_log_format f002
100%
Passed
Tokens
830
Input
197
Total output
147
Reasoning within output
git_log_format f003
100%
Passed
Tokens
677
Input
400
Total output
265
Reasoning within output
git_log_format f004
100%
Passed
Tokens
804
Input
596
Total output
387
Reasoning within output
git_log_format f005
100%
Passed
Tokens
676
Input
266
Total output
175
Reasoning within output
git_log_format f006
100%
Passed
Tokens
828
Input
277
Total output
158
Reasoning within output
git_log_format f007
100%
Passed
Tokens
846
Input
142
Total output
121
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,099
Input
143
Total output
109
Reasoning within output
git_log_format f009
100%
Passed
Tokens
672
Input
204
Total output
170
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,236
Input
292
Total output
191
Reasoning within output
git_log_format f011
100%
Passed
Tokens
445
Input
193
Total output
153
Reasoning within output
git_log_format f012
100%
Passed
Tokens
392
Input
199
Total output
126
Reasoning within output
git_show f001
100%
Passed
Tokens
221
Input
130
Total output
97
Reasoning within output
git_show f002
0%
Failed
Tokens
228
Input
470
Total output
423
Reasoning within output
git_show f003
100%
Passed
Tokens
695
Input
137
Total output
103
Reasoning within output
git_show f004
100%
Passed
Tokens
477
Input
159
Total output
119
Reasoning within output
git_show f005
100%
Passed
Tokens
236
Input
260
Total output
220
Reasoning within output
git_show f006
100%
Passed
Tokens
243
Input
113
Total output
92
Reasoning within output
git_show f007
100%
Passed
Tokens
220
Input
188
Total output
150
Reasoning within output
git_show f008
100%
Passed
Tokens
240
Input
185
Total output
106
Reasoning within output
git_show f009
100%
Passed
Tokens
330
Input
216
Total output
162
Reasoning within output
git_show f010
100%
Passed
Tokens
231
Input
127
Total output
117
Reasoning within output
git_show f011
100%
Passed
Tokens
252
Input
133
Total output
114
Reasoning within output
git_show f012
100%
Passed
Tokens
382
Input
168
Total output
135
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
127
Input
456
Total output
487
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
145
Input
705
Total output
506
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
120
Input
613
Total output
570
Reasoning within output
merge_conflicts f004
0%
Failed
Tokens
177
Input
1,077
Total output
771
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
185
Input
278
Total output
240
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
162
Input
393
Total output
335
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
175
Input
257
Total output
222
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
149
Input
269
Total output
251
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
149
Input
178
Total output
152
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
232
Input
565
Total output
491
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
188
Input
375
Total output
295
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
284
Input
7,831
Total output
2,887
Reasoning within output
rebase f001
100%
Passed
Tokens
138
Input
6,358
Total output
2,589
Reasoning within output
rebase f002
100%
Passed
Tokens
167
Input
218
Total output
175
Reasoning within output
rebase f003
100%
Passed
Tokens
144
Input
442
Total output
427
Reasoning within output
rebase f004
0%
Failed
Tokens
190
Input
402
Total output
333
Reasoning within output
rebase f005
100%
Passed
Tokens
189
Input
720
Total output
543
Reasoning within output
rebase f006
100%
Passed
Tokens
177
Input
459
Total output
378
Reasoning within output
rebase f007
100%
Passed
Tokens
176
Input
199
Total output
168
Reasoning within output
rebase f008
100%
Passed
Tokens
161
Input
257
Total output
261
Reasoning within output
rebase f009
100%
Passed
Tokens
148
Input
777
Total output
647
Reasoning within output
rebase f010
100%
Passed
Tokens
261
Input
666
Total output
576
Reasoning within output
rebase f011
100%
Passed
Tokens
199
Input
352
Total output
246
Reasoning within output
rebase f012
0%
Failed
Tokens
321
Input
1,961
Total output
853
Reasoning within output
reflog f001
100%
Passed
Tokens
240
Input
328
Total output
263
Reasoning within output
reflog f002
100%
Passed
Tokens
244
Input
584
Total output
236
Reasoning within output
reflog f003
100%
Passed
Tokens
211
Input
693
Total output
282
Reasoning within output
reflog f004
100%
Passed
Tokens
335
Input
2,164
Total output
728
Reasoning within output
reflog f005
100%
Passed
Tokens
364
Input
1,788
Total output
657
Reasoning within output
reflog f006
100%
Passed
Tokens
253
Input
702
Total output
269
Reasoning within output
reflog f007
100%
Passed
Tokens
281
Input
610
Total output
224
Reasoning within output
reflog f008
100%
Passed
Tokens
360
Input
1,145
Total output
449
Reasoning within output
reflog f009
100%
Passed
Tokens
338
Input
918
Total output
461
Reasoning within output
reflog f010
100%
Passed
Tokens
286
Input
759
Total output
336
Reasoning within output
reflog f011
100%
Passed
Tokens
308
Input
1,188
Total output
572
Reasoning within output
reflog f012
100%
Passed
Tokens
312
Input
1,543
Total output
777
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
188
Input
237
Total output
148
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
357
Input
470
Total output
227
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
169
Input
307
Total output
145
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
167
Input
395
Total output
183
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
181
Input
323
Total output
166
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
238
Input
266
Total output
143
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
273
Input
374
Total output
180
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
231
Input
294
Total output
139
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
273
Input
326
Total output
186
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
179
Input
207
Total output
112
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
165
Input
283
Total output
167
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
188
Input
402
Total output
243
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
77
Input
140
Total output
108
Reasoning within output
submodule_usage f002
0%
Failed
Tokens
133
Input
4,162
Total output
1,500
Reasoning within output
submodule_usage f003
75%
Failed
Tokens
140
Input
7,210
Total output
2,702
Reasoning within output
submodule_usage f004
0%
Failed
Tokens
125
Input
130
Total output
128
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
84
Input
325
Total output
246
Reasoning within output
submodule_usage f006
0%
Failed
Tokens
121
Input
6,694
Total output
2,518
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
87
Input
163
Total output
108
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
128
Input
547
Total output
526
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
129
Input
244
Total output
205
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
139
Input
397
Total output
398
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
139
Input
99
Total output
91
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
85
Input
176
Total output
135
Reasoning within output
tag_management f001
100%
Passed
Tokens
92
Input
141
Total output
119
Reasoning within output
tag_management f002
100%
Passed
Tokens
91
Input
178
Total output
138
Reasoning within output
tag_management f003
100%
Passed
Tokens
96
Input
299
Total output
267
Reasoning within output
tag_management f004
100%
Passed
Tokens
96
Input
155
Total output
139
Reasoning within output
tag_management f005
100%
Passed
Tokens
112
Input
202
Total output
157
Reasoning within output
tag_management f006
100%
Passed
Tokens
100
Input
179
Total output
119
Reasoning within output
tag_management f007
100%
Passed
Tokens
95
Input
356
Total output
286
Reasoning within output
tag_management f008
100%
Passed
Tokens
101
Input
832
Total output
471
Reasoning within output
tag_management f009
100%
Passed
Tokens
111
Input
212
Total output
163
Reasoning within output
tag_management f010
100%
Passed
Tokens
81
Input
139
Total output
114
Reasoning within output
tag_management f011
100%
Passed
Tokens
81
Input
119
Total output
101
Reasoning within output
tag_management f012
100%
Passed
Tokens
112
Input
448
Total output
363
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
173
Input
147
Total output
115
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
179
Input
253
Total output
179
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
236
Input
291
Total output
202
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
251
Input
151
Total output
144
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
164
Input
172
Total output
129
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
172
Input
148
Total output
99
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
174
Input
174
Total output
104
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
197
Input
9,852
Total output
3,397
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
286
Input
215
Total output
171
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
255
Input
150
Total output
110
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
243
Input
185
Total output
127
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
164
Input
182
Total output
132
Reasoning within output