Anthropic / claude-fable-5
high
81.4%
166 / 204 fixtures · 1 run(s)
49,588 input / 22,587 total output / 4,933 reasoning within output tokens $1.58234000
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
+9.8%
Text: 81.4% →
JSON: 91.2%
+25
Gained
JSON pass / text fail
−5
Lost
Text pass / JSON fail
161
Unchanged Pass
Both pass
13
Unchanged Fail
Both fail
Fixture Reliability Delta
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| blame_forensics | 33.3% | 75% | + 41.7% |
| git_grep | 50% | 83.3% | + 33.3% |
| branch_cleanup | 41.7% | 75% | + 33.3% |
| commit_messages | 83.3% | 100% | + 16.7% |
| worktree_usage | 83.3% | 100% | + 16.7% |
| cherry_pick | 66.7% | 58.3% | -8.3% |
| git_log_format | 91.7% | 100% | + 8.3% |
| git_show | 91.7% | 100% | + 8.3% |
| merge_conflicts | 75% | 83.3% | + 8.3% |
| rebase | 66.7% | 75% | + 8.3% |
| commit_squash | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_clean | 100% | 100% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
Changed Fixtures (30)
f002 +gain f004 +gain f006 +gain f011 +gain f012 +gain f002 +gain f007 +gain f008 +gain f010 +gain f006 -loss f008 +gain f009 -loss f010 -loss f011 +gain f002 +gain f011 +gain f001 +gain f003 +gain f008 +gain f012 +gain f003 +gain f004 +gain f006 +gain f010 -loss f011 +gain f006 +gain f010 -loss f011 +gain f007 +gain f008 +gain
Fixture Gallery (204)
blame_forensics f001
0%
Failed
Tokens
307
Input
2
Total output
0
Reasoning within output
blame_forensics f002
0%
Failed
Tokens
276
Input
10
Total output
0
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
320
Input
10
Total output
0
Reasoning within output
blame_forensics f004
0%
Failed
Tokens
238
Input
2
Total output
0
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
304
Input
533
Total output
95
Reasoning within output
blame_forensics f006
0%
Failed
Tokens
266
Input
3
Total output
0
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
250
Input
45
Total output
37
Reasoning within output
blame_forensics f008
0%
Failed
Tokens
282
Input
3
Total output
0
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
237
Input
38
Total output
38
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
505
Input
46
Total output
34
Reasoning within output
blame_forensics f011
0%
Failed
Tokens
274
Input
2
Total output
0
Reasoning within output
blame_forensics f012
0%
Failed
Tokens
178
Input
2
Total output
0
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
131
Input
68
Total output
45
Reasoning within output
branch_cleanup f002
100%
Failed
Tokens
156
Input
267
Total output
40
Reasoning within output
branch_cleanup f003
100%
Failed
Tokens
124
Input
113
Total output
25
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
166
Input
52
Total output
43
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
137
Input
47
Total output
40
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
164
Input
63
Total output
45
Reasoning within output
branch_cleanup f007
100%
Failed
Tokens
143
Input
108
Total output
22
Reasoning within output
branch_cleanup f008
100%
Failed
Tokens
164
Input
208
Total output
51
Reasoning within output
branch_cleanup f009
100%
Failed
Tokens
109
Input
116
Total output
40
Reasoning within output
branch_cleanup f010
100%
Failed
Tokens
136
Input
156
Total output
47
Reasoning within output
branch_cleanup f011
100%
Failed
Tokens
93
Input
71
Total output
21
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
200
Input
48
Total output
39
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
172
Input
77
Total output
63
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
180
Input
62
Total output
33
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
153
Input
53
Total output
26
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
213
Input
244
Total output
76
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
236
Input
45
Total output
19
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
200
Input
53
Total output
42
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
226
Input
52
Total output
23
Reasoning within output
cherry_pick f008
0%
Failed
Tokens
194
Input
109
Total output
6
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
177
Input
10
Total output
0
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
357
Input
143
Total output
65
Reasoning within output
cherry_pick f011
0%
Failed
Tokens
228
Input
149
Total output
17
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
413
Input
323
Total output
93
Reasoning within output
commit_messages f001
91.7%
Passed
Tokens
148
Input
14
Total output
0
Reasoning within output
commit_messages f002
5%
Failed
Tokens
276
Input
90
Total output
0
Reasoning within output
commit_messages f003
93.7%
Passed
Tokens
121
Input
17
Total output
0
Reasoning within output
commit_messages f004
90%
Passed
Tokens
156
Input
12
Total output
0
Reasoning within output
commit_messages f005
88.7%
Passed
Tokens
138
Input
38
Total output
20
Reasoning within output
commit_messages f006
67%
Passed
Tokens
188
Input
86
Total output
16
Reasoning within output
commit_messages f007
93.3%
Passed
Tokens
256
Input
93
Total output
0
Reasoning within output
commit_messages f008
92.7%
Passed
Tokens
99
Input
25
Total output
17
Reasoning within output
commit_messages f009
78.3%
Passed
Tokens
170
Input
46
Total output
28
Reasoning within output
commit_messages f010
89.3%
Passed
Tokens
385
Input
13
Total output
0
Reasoning within output
commit_messages f011
31.7%
Failed
Tokens
188
Input
110
Total output
0
Reasoning within output
commit_messages f012
88.3%
Passed
Tokens
170
Input
9
Total output
0
Reasoning within output
commit_squash f001
100%
Passed
Tokens
195
Input
521
Total output
75
Reasoning within output
commit_squash f002
100%
Passed
Tokens
160
Input
41
Total output
17
Reasoning within output
commit_squash f003
100%
Passed
Tokens
178
Input
50
Total output
27
Reasoning within output
commit_squash f004
100%
Passed
Tokens
155
Input
135
Total output
82
Reasoning within output
commit_squash f005
100%
Passed
Tokens
164
Input
53
Total output
22
Reasoning within output
commit_squash f006
100%
Passed
Tokens
141
Input
60
Total output
39
Reasoning within output
commit_squash f007
100%
Passed
Tokens
139
Input
30
Total output
19
Reasoning within output
commit_squash f008
100%
Passed
Tokens
156
Input
38
Total output
15
Reasoning within output
commit_squash f009
100%
Passed
Tokens
141
Input
86
Total output
27
Reasoning within output
commit_squash f010
100%
Passed
Tokens
167
Input
37
Total output
11
Reasoning within output
commit_squash f011
100%
Passed
Tokens
173
Input
60
Total output
36
Reasoning within output
commit_squash f012
100%
Passed
Tokens
173
Input
37
Total output
10
Reasoning within output
git_bisect f001
100%
Passed
Tokens
233
Input
166
Total output
9
Reasoning within output
git_bisect f002
100%
Passed
Tokens
275
Input
206
Total output
17
Reasoning within output
git_bisect f003
100%
Passed
Tokens
277
Input
212
Total output
23
Reasoning within output
git_bisect f004
100%
Passed
Tokens
276
Input
160
Total output
9
Reasoning within output
git_bisect f005
100%
Passed
Tokens
272
Input
189
Total output
9
Reasoning within output
git_bisect f006
100%
Passed
Tokens
295
Input
193
Total output
15
Reasoning within output
git_bisect f007
100%
Passed
Tokens
271
Input
190
Total output
15
Reasoning within output
git_bisect f008
100%
Passed
Tokens
275
Input
202
Total output
22
Reasoning within output
git_bisect f009
100%
Passed
Tokens
267
Input
120
Total output
9
Reasoning within output
git_bisect f010
100%
Passed
Tokens
283
Input
235
Total output
16
Reasoning within output
git_bisect f011
100%
Passed
Tokens
271
Input
215
Total output
16
Reasoning within output
git_bisect f012
100%
Passed
Tokens
299
Input
222
Total output
20
Reasoning within output
git_clean f001
100%
Passed
Tokens
73
Input
30
Total output
21
Reasoning within output
git_clean f002
100%
Passed
Tokens
90
Input
19
Total output
18
Reasoning within output
git_clean f003
100%
Passed
Tokens
91
Input
20
Total output
23
Reasoning within output
git_clean f004
100%
Passed
Tokens
92
Input
18
Total output
30
Reasoning within output
git_clean f005
100%
Passed
Tokens
76
Input
49
Total output
32
Reasoning within output
git_clean f006
100%
Passed
Tokens
112
Input
18
Total output
16
Reasoning within output
git_clean f007
100%
Passed
Tokens
106
Input
54
Total output
35
Reasoning within output
git_clean f008
100%
Passed
Tokens
111
Input
16
Total output
23
Reasoning within output
git_clean f009
100%
Passed
Tokens
115
Input
17
Total output
0
Reasoning within output
git_clean f010
100%
Passed
Tokens
101
Input
18
Total output
23
Reasoning within output
git_clean f011
100%
Passed
Tokens
94
Input
49
Total output
42
Reasoning within output
git_clean f012
100%
Passed
Tokens
96
Input
22
Total output
29
Reasoning within output
git_grep f001
0%
Failed
Tokens
76
Input
4
Total output
0
Reasoning within output
git_grep f002
100%
Passed
Tokens
89
Input
18
Total output
18
Reasoning within output
git_grep f003
0%
Failed
Tokens
125
Input
1
Total output
0
Reasoning within output
git_grep f004
0%
Failed
Tokens
103
Input
23
Total output
13
Reasoning within output
git_grep f005
100%
Passed
Tokens
155
Input
10
Total output
16
Reasoning within output
git_grep f006
100%
Passed
Tokens
53
Input
26
Total output
13
Reasoning within output
git_grep f007
0%
Failed
Tokens
221
Input
3
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
16
Total output
5
Reasoning within output
git_grep f010
100%
Passed
Tokens
89
Input
10
Total output
14
Reasoning within output
git_grep f011
100%
Passed
Tokens
166
Input
3
Total output
0
Reasoning within output
git_grep f012
0%
Failed
Tokens
89
Input
40
Total output
6
Reasoning within output
git_log_format f001
100%
Passed
Tokens
997
Input
3
Total output
0
Reasoning within output
git_log_format f002
100%
Passed
Tokens
960
Input
16
Total output
0
Reasoning within output
git_log_format f003
0%
Failed
Tokens
808
Input
3
Total output
0
Reasoning within output
git_log_format f004
100%
Passed
Tokens
965
Input
3
Total output
0
Reasoning within output
git_log_format f005
100%
Passed
Tokens
760
Input
9
Total output
0
Reasoning within output
git_log_format f006
100%
Passed
Tokens
978
Input
3
Total output
0
Reasoning within output
git_log_format f007
100%
Passed
Tokens
975
Input
7
Total output
0
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,275
Input
3
Total output
0
Reasoning within output
git_log_format f009
100%
Passed
Tokens
764
Input
3
Total output
0
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,425
Input
3
Total output
0
Reasoning within output
git_log_format f011
100%
Passed
Tokens
488
Input
6
Total output
0
Reasoning within output
git_log_format f012
100%
Passed
Tokens
419
Input
3
Total output
0
Reasoning within output
git_show f001
100%
Passed
Tokens
226
Input
22
Total output
14
Reasoning within output
git_show f002
100%
Passed
Tokens
239
Input
6
Total output
0
Reasoning within output
git_show f003
100%
Passed
Tokens
774
Input
9
Total output
0
Reasoning within output
git_show f004
0%
Failed
Tokens
524
Input
1
Total output
0
Reasoning within output
git_show f005
100%
Passed
Tokens
254
Input
16
Total output
11
Reasoning within output
git_show f006
100%
Passed
Tokens
254
Input
3
Total output
0
Reasoning within output
git_show f007
100%
Passed
Tokens
232
Input
28
Total output
19
Reasoning within output
git_show f008
100%
Passed
Tokens
251
Input
26
Total output
0
Reasoning within output
git_show f009
100%
Passed
Tokens
370
Input
29
Total output
17
Reasoning within output
git_show f010
100%
Passed
Tokens
235
Input
50
Total output
39
Reasoning within output
git_show f011
100%
Passed
Tokens
271
Input
5
Total output
0
Reasoning within output
git_show f012
100%
Passed
Tokens
400
Input
3
Total output
0
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
158
Input
74
Total output
53
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
166
Input
65
Total output
32
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
141
Input
222
Total output
83
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
197
Input
329
Total output
93
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
219
Input
50
Total output
17
Reasoning within output
merge_conflicts f006
0%
Failed
Tokens
180
Input
5
Total output
0
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
230
Input
52
Total output
23
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
173
Input
20
Total output
6
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
169
Input
37
Total output
23
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
306
Input
115
Total output
49
Reasoning within output
merge_conflicts f011
0%
Failed
Tokens
202
Input
117
Total output
17
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
362
Input
289
Total output
129
Reasoning within output
rebase f001
100%
Passed
Tokens
171
Input
112
Total output
65
Reasoning within output
rebase f002
100%
Passed
Tokens
190
Input
69
Total output
34
Reasoning within output
rebase f003
100%
Passed
Tokens
171
Input
63
Total output
52
Reasoning within output
rebase f004
0%
Failed
Tokens
212
Input
3
Total output
0
Reasoning within output
rebase f005
100%
Passed
Tokens
224
Input
57
Total output
26
Reasoning within output
rebase f006
0%
Failed
Tokens
201
Input
128
Total output
28
Reasoning within output
rebase f007
100%
Passed
Tokens
230
Input
52
Total output
23
Reasoning within output
rebase f008
100%
Passed
Tokens
185
Input
166
Total output
42
Reasoning within output
rebase f009
100%
Passed
Tokens
170
Input
59
Total output
52
Reasoning within output
rebase f010
100%
Passed
Tokens
341
Input
151
Total output
62
Reasoning within output
rebase f011
0%
Failed
Tokens
218
Input
115
Total output
22
Reasoning within output
rebase f012
0%
Failed
Tokens
405
Input
472
Total output
119
Reasoning within output
reflog f001
100%
Passed
Tokens
280
Input
79
Total output
14
Reasoning within output
reflog f002
100%
Passed
Tokens
263
Input
405
Total output
21
Reasoning within output
reflog f003
100%
Passed
Tokens
240
Input
486
Total output
18
Reasoning within output
reflog f004
100%
Passed
Tokens
376
Input
800
Total output
121
Reasoning within output
reflog f005
100%
Passed
Tokens
433
Input
582
Total output
13
Reasoning within output
reflog f006
100%
Passed
Tokens
305
Input
363
Total output
14
Reasoning within output
reflog f007
100%
Passed
Tokens
337
Input
513
Total output
65
Reasoning within output
reflog f008
100%
Passed
Tokens
414
Input
466
Total output
25
Reasoning within output
reflog f009
100%
Passed
Tokens
387
Input
626
Total output
47
Reasoning within output
reflog f010
100%
Passed
Tokens
326
Input
606
Total output
30
Reasoning within output
reflog f011
100%
Passed
Tokens
367
Input
763
Total output
64
Reasoning within output
reflog f012
100%
Passed
Tokens
355
Input
979
Total output
63
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
184
Input
148
Total output
14
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
398
Input
200
Total output
0
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
167
Input
223
Total output
17
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
160
Input
258
Total output
17
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
183
Input
302
Total output
53
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
245
Input
261
Total output
14
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
284
Input
219
Total output
6
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
238
Input
338
Total output
45
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
286
Input
241
Total output
36
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
175
Input
171
Total output
17
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
161
Input
296
Total output
42
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
192
Input
275
Total output
17
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
61
Input
39
Total output
31
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
126
Input
82
Total output
31
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
137
Input
118
Total output
62
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
114
Input
17
Total output
19
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
68
Input
82
Total output
28
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
113
Input
120
Total output
83
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
74
Input
48
Total output
13
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
123
Input
166
Total output
63
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
118
Input
12
Total output
0
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
128
Input
16
Total output
0
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
139
Input
10
Total output
0
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
72
Input
47
Total output
31
Reasoning within output
tag_management f001
100%
Passed
Tokens
85
Input
15
Total output
4
Reasoning within output
tag_management f002
100%
Passed
Tokens
78
Input
30
Total output
20
Reasoning within output
tag_management f003
100%
Passed
Tokens
85
Input
18
Total output
0
Reasoning within output
tag_management f004
100%
Passed
Tokens
83
Input
5
Total output
0
Reasoning within output
tag_management f005
100%
Passed
Tokens
101
Input
15
Total output
0
Reasoning within output
tag_management f006
100%
Passed
Tokens
87
Input
30
Total output
16
Reasoning within output
tag_management f007
100%
Passed
Tokens
83
Input
254
Total output
83
Reasoning within output
tag_management f008
100%
Passed
Tokens
89
Input
147
Total output
73
Reasoning within output
tag_management f009
100%
Passed
Tokens
105
Input
35
Total output
20
Reasoning within output
tag_management f010
100%
Passed
Tokens
68
Input
20
Total output
4
Reasoning within output
tag_management f011
100%
Passed
Tokens
69
Input
33
Total output
26
Reasoning within output
tag_management f012
100%
Passed
Tokens
100
Input
30
Total output
21
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
173
Input
39
Total output
21
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
184
Input
78
Total output
32
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
256
Input
15
Total output
0
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
246
Input
38
Total output
20
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
158
Input
23
Total output
0
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
172
Input
53
Total output
45
Reasoning within output
worktree_usage f007
0%
Failed
Tokens
170
Input
239
Total output
76
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
193
Input
109
Total output
31
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
305
Input
8
Total output
0
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
267
Input
24
Total output
0
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
259
Input
20
Total output
0
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
165
Input
38
Total output
14
Reasoning within output