Anthropic / claude-fable-5
max
84.8%
173 / 204 fixtures · 1 run(s)
49,672 input / 90,834 total output / 15,381 reasoning within output tokens $4.97474000
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
+3.4%
Text: 84.8% →
JSON: 88.2%
+18
Gained
JSON pass / text fail
−11
Lost
Text pass / JSON fail
162
Unchanged Pass
Both pass
13
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|---|---|---|
| f012 | 0% (0/1) | 100% (1/1) | -100% |
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| blame_forensics | 41.7% | 66.7% | + 25% |
| branch_cleanup | 91.7% | 75% | -16.7% |
| git_log_format | 83.3% | 100% | + 16.7% |
| rebase | 75% | 58.3% | -16.7% |
| submodule_usage | 83.3% | 100% | + 16.7% |
| git_grep | 66.7% | 83.3% | + 16.7% |
| git_show | 91.7% | 83.3% | -8.3% |
| cherry_pick | 66.7% | 75% | + 8.3% |
| commit_messages | 91.7% | 100% | + 8.3% |
| git_bisect | 91.7% | 100% | + 8.3% |
| merge_conflicts | 75% | 66.7% | -8.3% |
| worktree_usage | 91.7% | 100% | + 8.3% |
| commit_squash | 100% | 100% | + 0% |
| git_clean | 100% | 100% | + 0% |
| reflog | 91.7% | 91.7% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
Changed Fixtures (29)
f001 -loss f002 +gain f004 +gain f010 +gain f011 +gain f003 -loss f011 -loss f003 +gain f012 +gain f009 +gain f003 +gain f004 -loss f007 +gain f008 +gain f003 +gain f007 +gain f007 -loss f003 +gain f004 -loss f010 -loss f003 +gain f006 -loss f010 -loss f011 -loss f011 +gain f012 -loss f008 +gain f009 +gain f008 +gain
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
313
Input
502
Total output
173
Reasoning within output
blame_forensics f002
0%
Failed
Tokens
275
Input
4
Total output
0
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
315
Input
157
Total output
64
Reasoning within output
blame_forensics f004
0%
Failed
Tokens
246
Input
7
Total output
0
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
306
Input
1,650
Total output
286
Reasoning within output
blame_forensics f006
0%
Failed
Tokens
271
Input
102
Total output
51
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
258
Input
336
Total output
58
Reasoning within output
blame_forensics f008
0%
Failed
Tokens
284
Input
10
Total output
0
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
226
Input
406
Total output
159
Reasoning within output
blame_forensics f010
0%
Failed
Tokens
504
Input
5
Total output
0
Reasoning within output
blame_forensics f011
0%
Failed
Tokens
276
Input
4
Total output
0
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
178
Input
357
Total output
78
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
132
Input
305
Total output
69
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
157
Input
180
Total output
43
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
127
Input
272
Total output
58
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
170
Input
327
Total output
69
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
137
Input
298
Total output
71
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
160
Input
232
Total output
63
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
141
Input
257
Total output
117
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
166
Input
285
Total output
72
Reasoning within output
branch_cleanup f009
100%
Failed
Tokens
110
Input
325
Total output
84
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
138
Input
941
Total output
149
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
92
Input
177
Total output
42
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
202
Input
436
Total output
192
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
173
Input
239
Total output
80
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
180
Input
407
Total output
92
Reasoning within output
cherry_pick f003
0%
Failed
Tokens
154
Input
115
Total output
38
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
214
Input
881
Total output
186
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
234
Input
387
Total output
59
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
202
Input
412
Total output
76
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
225
Input
498
Total output
89
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
192
Input
296
Total output
50
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
175
Input
90
Total output
38
Reasoning within output
cherry_pick f010
0%
Failed
Tokens
355
Input
1,435
Total output
176
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
229
Input
351
Total output
69
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
413
Input
9
Total output
0
Reasoning within output
commit_messages f001
58.3%
Passed
Tokens
148
Input
479
Total output
71
Reasoning within output
commit_messages f002
91.7%
Passed
Tokens
276
Input
385
Total output
80
Reasoning within output
commit_messages f003
58.3%
Passed
Tokens
121
Input
282
Total output
54
Reasoning within output
commit_messages f004
95%
Passed
Tokens
156
Input
219
Total output
60
Reasoning within output
commit_messages f005
91%
Passed
Tokens
138
Input
369
Total output
72
Reasoning within output
commit_messages f006
88.3%
Passed
Tokens
188
Input
456
Total output
60
Reasoning within output
commit_messages f007
95%
Passed
Tokens
256
Input
492
Total output
67
Reasoning within output
commit_messages f008
91.7%
Passed
Tokens
99
Input
482
Total output
96
Reasoning within output
commit_messages f009
78.3%
Passed
Tokens
170
Input
336
Total output
65
Reasoning within output
commit_messages f010
55%
Passed
Tokens
385
Input
674
Total output
83
Reasoning within output
commit_messages f011
75%
Passed
Tokens
188
Input
936
Total output
99
Reasoning within output
commit_messages f012
34%
Failed
Tokens
170
Input
357
Total output
68
Reasoning within output
commit_squash f001
100%
Passed
Tokens
196
Input
1,264
Total output
225
Reasoning within output
commit_squash f002
100%
Passed
Tokens
156
Input
228
Total output
58
Reasoning within output
commit_squash f003
100%
Passed
Tokens
176
Input
279
Total output
80
Reasoning within output
commit_squash f004
100%
Passed
Tokens
156
Input
523
Total output
104
Reasoning within output
commit_squash f005
100%
Passed
Tokens
159
Input
604
Total output
85
Reasoning within output
commit_squash f006
100%
Passed
Tokens
141
Input
274
Total output
84
Reasoning within output
commit_squash f007
100%
Passed
Tokens
140
Input
430
Total output
54
Reasoning within output
commit_squash f008
100%
Passed
Tokens
160
Input
402
Total output
70
Reasoning within output
commit_squash f009
100%
Passed
Tokens
145
Input
360
Total output
80
Reasoning within output
commit_squash f010
100%
Passed
Tokens
173
Input
335
Total output
70
Reasoning within output
commit_squash f011
100%
Passed
Tokens
179
Input
275
Total output
65
Reasoning within output
commit_squash f012
100%
Passed
Tokens
171
Input
303
Total output
129
Reasoning within output
git_bisect f001
100%
Passed
Tokens
235
Input
369
Total output
58
Reasoning within output
git_bisect f002
100%
Passed
Tokens
279
Input
440
Total output
74
Reasoning within output
git_bisect f003
100%
Passed
Tokens
277
Input
368
Total output
51
Reasoning within output
git_bisect f004
100%
Passed
Tokens
272
Input
381
Total output
66
Reasoning within output
git_bisect f005
100%
Passed
Tokens
272
Input
474
Total output
65
Reasoning within output
git_bisect f006
100%
Passed
Tokens
303
Input
425
Total output
42
Reasoning within output
git_bisect f007
100%
Passed
Tokens
279
Input
423
Total output
61
Reasoning within output
git_bisect f008
100%
Passed
Tokens
275
Input
478
Total output
74
Reasoning within output
git_bisect f009
0%
Failed
Tokens
271
Input
3
Total output
0
Reasoning within output
git_bisect f010
100%
Passed
Tokens
281
Input
449
Total output
68
Reasoning within output
git_bisect f011
100%
Passed
Tokens
269
Input
392
Total output
66
Reasoning within output
git_bisect f012
100%
Passed
Tokens
305
Input
411
Total output
39
Reasoning within output
git_clean f001
100%
Passed
Tokens
73
Input
493
Total output
56
Reasoning within output
git_clean f002
100%
Passed
Tokens
90
Input
170
Total output
39
Reasoning within output
git_clean f003
100%
Passed
Tokens
91
Input
169
Total output
61
Reasoning within output
git_clean f004
100%
Passed
Tokens
92
Input
177
Total output
60
Reasoning within output
git_clean f005
100%
Passed
Tokens
76
Input
212
Total output
74
Reasoning within output
git_clean f006
100%
Passed
Tokens
112
Input
261
Total output
47
Reasoning within output
git_clean f007
100%
Passed
Tokens
106
Input
313
Total output
45
Reasoning within output
git_clean f008
100%
Passed
Tokens
111
Input
123
Total output
56
Reasoning within output
git_clean f009
100%
Passed
Tokens
115
Input
1,326
Total output
157
Reasoning within output
git_clean f010
100%
Passed
Tokens
101
Input
217
Total output
67
Reasoning within output
git_clean f011
100%
Passed
Tokens
94
Input
236
Total output
74
Reasoning within output
git_clean f012
100%
Passed
Tokens
96
Input
262
Total output
74
Reasoning within output
git_grep f001
0%
Failed
Tokens
76
Input
4
Total output
0
Reasoning within output
git_grep f002
100%
Passed
Tokens
88
Input
88
Total output
47
Reasoning within output
git_grep f003
0%
Failed
Tokens
125
Input
3
Total output
0
Reasoning within output
git_grep f004
100%
Passed
Tokens
103
Input
129
Total output
34
Reasoning within output
git_grep f005
100%
Passed
Tokens
155
Input
185
Total output
63
Reasoning within output
git_grep f006
100%
Passed
Tokens
53
Input
102
Total output
33
Reasoning within output
git_grep f007
0%
Failed
Tokens
221
Input
10
Total output
0
Reasoning within output
git_grep f008
0%
Failed
Tokens
82
Input
4
Total output
0
Reasoning within output
git_grep f009
100%
Passed
Tokens
68
Input
119
Total output
34
Reasoning within output
git_grep f010
100%
Passed
Tokens
89
Input
90
Total output
32
Reasoning within output
git_grep f011
100%
Passed
Tokens
166
Input
140
Total output
40
Reasoning within output
git_grep f012
100%
Passed
Tokens
89
Input
102
Total output
58
Reasoning within output
git_log_format f001
100%
Passed
Tokens
1,005
Input
130
Total output
37
Reasoning within output
git_log_format f002
100%
Passed
Tokens
959
Input
95
Total output
32
Reasoning within output
git_log_format f003
0%
Failed
Tokens
825
Input
6
Total output
0
Reasoning within output
git_log_format f004
100%
Passed
Tokens
965
Input
69
Total output
25
Reasoning within output
git_log_format f005
100%
Passed
Tokens
760
Input
189
Total output
58
Reasoning within output
git_log_format f006
100%
Passed
Tokens
978
Input
143
Total output
45
Reasoning within output
git_log_format f007
0%
Failed
Tokens
956
Input
3
Total output
0
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,293
Input
126
Total output
32
Reasoning within output
git_log_format f009
100%
Passed
Tokens
776
Input
44
Total output
23
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,452
Input
67
Total output
26
Reasoning within output
git_log_format f011
100%
Passed
Tokens
478
Input
88
Total output
51
Reasoning within output
git_log_format f012
100%
Passed
Tokens
436
Input
44
Total output
29
Reasoning within output
git_show f001
100%
Passed
Tokens
233
Input
99
Total output
37
Reasoning within output
git_show f002
100%
Passed
Tokens
245
Input
207
Total output
62
Reasoning within output
git_show f003
100%
Passed
Tokens
760
Input
75
Total output
34
Reasoning within output
git_show f004
100%
Passed
Tokens
514
Input
56
Total output
27
Reasoning within output
git_show f005
0%
Failed
Tokens
251
Input
4
Total output
0
Reasoning within output
git_show f006
100%
Passed
Tokens
255
Input
52
Total output
23
Reasoning within output
git_show f007
100%
Passed
Tokens
232
Input
114
Total output
64
Reasoning within output
git_show f008
100%
Passed
Tokens
252
Input
92
Total output
36
Reasoning within output
git_show f009
100%
Passed
Tokens
360
Input
165
Total output
36
Reasoning within output
git_show f010
100%
Passed
Tokens
238
Input
94
Total output
58
Reasoning within output
git_show f011
100%
Passed
Tokens
265
Input
110
Total output
27
Reasoning within output
git_show f012
100%
Passed
Tokens
400
Input
46
Total output
24
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
158
Input
218
Total output
53
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
166
Input
261
Total output
76
Reasoning within output
merge_conflicts f003
0%
Failed
Tokens
141
Input
4
Total output
0
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
197
Input
4,710
Total output
612
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
219
Input
420
Total output
154
Reasoning within output
merge_conflicts f006
0%
Failed
Tokens
180
Input
10
Total output
0
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
230
Input
376
Total output
66
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
173
Input
232
Total output
57
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
169
Input
215
Total output
62
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
306
Input
903
Total output
173
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
202
Input
303
Total output
87
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
362
Input
1,385
Total output
221
Reasoning within output
rebase f001
100%
Passed
Tokens
175
Input
692
Total output
181
Reasoning within output
rebase f002
100%
Passed
Tokens
190
Input
440
Total output
81
Reasoning within output
rebase f003
0%
Failed
Tokens
172
Input
10
Total output
0
Reasoning within output
rebase f004
0%
Failed
Tokens
212
Input
9
Total output
0
Reasoning within output
rebase f005
100%
Passed
Tokens
225
Input
623
Total output
169
Reasoning within output
rebase f006
100%
Passed
Tokens
199
Input
946
Total output
164
Reasoning within output
rebase f007
100%
Passed
Tokens
229
Input
710
Total output
86
Reasoning within output
rebase f008
100%
Passed
Tokens
187
Input
540
Total output
182
Reasoning within output
rebase f009
100%
Passed
Tokens
170
Input
419
Total output
144
Reasoning within output
rebase f010
100%
Passed
Tokens
337
Input
2,074
Total output
277
Reasoning within output
rebase f011
100%
Passed
Tokens
217
Input
646
Total output
79
Reasoning within output
rebase f012
0%
Failed
Tokens
409
Input
4,655
Total output
431
Reasoning within output
reflog f001
100%
Passed
Tokens
287
Input
345
Total output
67
Reasoning within output
reflog f002
100%
Passed
Tokens
281
Input
828
Total output
90
Reasoning within output
reflog f003
100%
Passed
Tokens
236
Input
904
Total output
44
Reasoning within output
reflog f004
100%
Passed
Tokens
378
Input
2,757
Total output
289
Reasoning within output
reflog f005
100%
Passed
Tokens
437
Input
2,078
Total output
189
Reasoning within output
reflog f006
100%
Passed
Tokens
302
Input
1,552
Total output
152
Reasoning within output
reflog f007
100%
Passed
Tokens
326
Input
2,249
Total output
255
Reasoning within output
reflog f008
100%
Passed
Tokens
431
Input
1,861
Total output
139
Reasoning within output
reflog f009
100%
Passed
Tokens
373
Input
2,033
Total output
190
Reasoning within output
reflog f010
100%
Passed
Tokens
315
Input
1,373
Total output
128
Reasoning within output
reflog f011
0%
Failed
Tokens
359
Input
465
Total output
123
Reasoning within output
reflog f012
100%
Passed
Tokens
350
Input
2,905
Total output
239
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
185
Input
371
Total output
55
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
392
Input
585
Total output
52
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
167
Input
433
Total output
44
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
160
Input
576
Total output
51
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
182
Input
512
Total output
86
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
245
Input
451
Total output
56
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
280
Input
487
Total output
43
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
238
Input
767
Total output
54
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
286
Input
525
Total output
82
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
175
Input
477
Total output
49
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
162
Input
658
Total output
90
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
192
Input
395
Total output
78
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
61
Input
96
Total output
27
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
128
Input
573
Total output
72
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
138
Input
780
Total output
86
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
115
Input
49
Total output
18
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
68
Input
444
Total output
92
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
109
Input
429
Total output
79
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
74
Input
123
Total output
30
Reasoning within output
submodule_usage f008
33.3%
Failed
Tokens
128
Input
6
Total output
0
Reasoning within output
submodule_usage f009
0%
Failed
Tokens
125
Input
6
Total output
0
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
128
Input
275
Total output
54
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
138
Input
66
Total output
19
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
72
Input
174
Total output
51
Reasoning within output
tag_management f001
100%
Passed
Tokens
81
Input
122
Total output
39
Reasoning within output
tag_management f002
100%
Passed
Tokens
80
Input
138
Total output
45
Reasoning within output
tag_management f003
100%
Passed
Tokens
83
Input
79
Total output
18
Reasoning within output
tag_management f004
100%
Passed
Tokens
79
Input
51
Total output
24
Reasoning within output
tag_management f005
100%
Passed
Tokens
103
Input
82
Total output
36
Reasoning within output
tag_management f006
100%
Passed
Tokens
90
Input
91
Total output
34
Reasoning within output
tag_management f007
100%
Passed
Tokens
82
Input
321
Total output
110
Reasoning within output
tag_management f008
100%
Passed
Tokens
90
Input
366
Total output
61
Reasoning within output
tag_management f009
100%
Passed
Tokens
103
Input
184
Total output
65
Reasoning within output
tag_management f010
100%
Passed
Tokens
67
Input
67
Total output
18
Reasoning within output
tag_management f011
100%
Passed
Tokens
71
Input
122
Total output
24
Reasoning within output
tag_management f012
100%
Passed
Tokens
99
Input
225
Total output
70
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
169
Input
96
Total output
28
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
182
Input
371
Total output
72
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
245
Input
63
Total output
24
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
248
Input
200
Total output
47
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
162
Input
269
Total output
50
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
164
Input
208
Total output
55
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
170
Input
2,083
Total output
287
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
201
Input
683
Total output
154
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
305
Input
80
Total output
37
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
271
Input
181
Total output
45
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
258
Input
69
Total output
35
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
166
Input
169
Total output
44
Reasoning within output