Sakana / fugu-max
high
96.1%
196 / 204 fixtures · 1 run(s)
53,138 input / 69,732 total output / 65,734 reasoning within output tokens $0.51775550
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-2.9%
Text: 96.1% →
JSON: 93.1%
+2
Gained
JSON pass / text fail
−8
Lost
Text pass / JSON fail
188
Unchanged Pass
Both pass
6
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| branch_cleanup | 100% | 75% | -25% |
| merge_conflicts | 91.7% | 83.3% | -8.3% |
| rebase | 91.7% | 83.3% | -8.3% |
| cherry_pick | 83.3% | 75% | -8.3% |
| git_grep | 91.7% | 100% | + 8.3% |
| git_show | 100% | 91.7% | -8.3% |
| submodule_usage | 100% | 91.7% | -8.3% |
| tag_management | 91.7% | 100% | + 8.3% |
| blame_forensics | 91.7% | 91.7% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| commit_squash | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_clean | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| worktree_usage | 91.7% | 91.7% | + 0% |
Changed Fixtures (10)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
338
Input
306
Total output
302
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
332
Input
184
Total output
180
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
308
Input
21
Total output
13
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
287
Input
111
Total output
106
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
351
Input
771
Total output
766
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
326
Input
198
Total output
195
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
300
Input
359
Total output
355
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
340
Input
200
Total output
197
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
289
Input
178
Total output
175
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
539
Input
158
Total output
155
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
283
Input
45
Total output
36
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
231
Input
216
Total output
212
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
176
Input
38
Total output
28
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
184
Input
134
Total output
123
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
170
Input
253
Total output
252
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
192
Input
57
Total output
46
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
183
Input
286
Total output
282
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
206
Input
279
Total output
269
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
181
Input
130
Total output
123
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
194
Input
144
Total output
135
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
156
Input
204
Total output
203
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
190
Input
9
Total output
0
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
142
Input
38
Total output
31
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
232
Input
304
Total output
292
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
171
Input
36
Total output
30
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
222
Input
2,476
Total output
2,466
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
190
Input
1,130
Total output
1,124
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
247
Input
112
Total output
91
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
235
Input
196
Total output
176
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
216
Input
54
Total output
27
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
230
Input
51
Total output
40
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
221
Input
44
Total output
36
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
206
Input
34
Total output
27
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
307
Input
304
Total output
274
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
262
Input
47
Total output
24
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
337
Input
176
Total output
133
Reasoning within output
commit_messages f001
82.5%
Passed
Tokens
201
Input
214
Total output
204
Reasoning within output
commit_messages f002
87.5%
Passed
Tokens
280
Input
15
Total output
5
Reasoning within output
commit_messages f003
92.5%
Passed
Tokens
182
Input
152
Total output
141
Reasoning within output
commit_messages f004
91.5%
Passed
Tokens
185
Input
7
Total output
0
Reasoning within output
commit_messages f005
94%
Passed
Tokens
197
Input
85
Total output
79
Reasoning within output
commit_messages f006
91.5%
Passed
Tokens
232
Input
521
Total output
513
Reasoning within output
commit_messages f007
92.5%
Passed
Tokens
256
Input
12
Total output
4
Reasoning within output
commit_messages f008
92.5%
Passed
Tokens
156
Input
292
Total output
287
Reasoning within output
commit_messages f009
90%
Passed
Tokens
220
Input
179
Total output
169
Reasoning within output
commit_messages f010
89%
Passed
Tokens
367
Input
200
Total output
192
Reasoning within output
commit_messages f011
87.5%
Passed
Tokens
238
Input
478
Total output
464
Reasoning within output
commit_messages f012
94%
Passed
Tokens
221
Input
414
Total output
406
Reasoning within output
commit_squash f001
100%
Passed
Tokens
214
Input
67
Total output
53
Reasoning within output
commit_squash f002
100%
Passed
Tokens
216
Input
134
Total output
123
Reasoning within output
commit_squash f003
100%
Passed
Tokens
206
Input
116
Total output
102
Reasoning within output
commit_squash f004
100%
Passed
Tokens
194
Input
391
Total output
380
Reasoning within output
commit_squash f005
100%
Passed
Tokens
190
Input
2,516
Total output
2,509
Reasoning within output
commit_squash f006
100%
Passed
Tokens
193
Input
172
Total output
158
Reasoning within output
commit_squash f007
100%
Passed
Tokens
179
Input
460
Total output
448
Reasoning within output
commit_squash f008
100%
Passed
Tokens
191
Input
265
Total output
253
Reasoning within output
commit_squash f009
100%
Passed
Tokens
180
Input
633
Total output
622
Reasoning within output
commit_squash f010
100%
Passed
Tokens
196
Input
349
Total output
334
Reasoning within output
commit_squash f011
100%
Passed
Tokens
222
Input
210
Total output
193
Reasoning within output
commit_squash f012
100%
Passed
Tokens
204
Input
367
Total output
347
Reasoning within output
git_bisect f001
100%
Passed
Tokens
245
Input
9
Total output
0
Reasoning within output
git_bisect f002
100%
Passed
Tokens
268
Input
9
Total output
0
Reasoning within output
git_bisect f003
100%
Passed
Tokens
266
Input
9
Total output
0
Reasoning within output
git_bisect f004
100%
Passed
Tokens
272
Input
9
Total output
0
Reasoning within output
git_bisect f005
100%
Passed
Tokens
270
Input
9
Total output
0
Reasoning within output
git_bisect f006
100%
Passed
Tokens
291
Input
8
Total output
0
Reasoning within output
git_bisect f007
100%
Passed
Tokens
284
Input
124
Total output
119
Reasoning within output
git_bisect f008
100%
Passed
Tokens
270
Input
8
Total output
0
Reasoning within output
git_bisect f009
100%
Passed
Tokens
284
Input
87
Total output
81
Reasoning within output
git_bisect f010
100%
Passed
Tokens
268
Input
9
Total output
0
Reasoning within output
git_bisect f011
100%
Passed
Tokens
292
Input
110
Total output
104
Reasoning within output
git_bisect f012
100%
Passed
Tokens
291
Input
9
Total output
0
Reasoning within output
git_clean f001
100%
Passed
Tokens
150
Input
238
Total output
228
Reasoning within output
git_clean f002
100%
Passed
Tokens
134
Input
53
Total output
43
Reasoning within output
git_clean f003
100%
Passed
Tokens
158
Input
117
Total output
111
Reasoning within output
git_clean f004
100%
Passed
Tokens
158
Input
95
Total output
88
Reasoning within output
git_clean f005
100%
Passed
Tokens
123
Input
76
Total output
64
Reasoning within output
git_clean f006
100%
Passed
Tokens
175
Input
201
Total output
192
Reasoning within output
git_clean f007
100%
Passed
Tokens
138
Input
57
Total output
43
Reasoning within output
git_clean f008
100%
Passed
Tokens
145
Input
43
Total output
33
Reasoning within output
git_clean f009
100%
Passed
Tokens
139
Input
96
Total output
83
Reasoning within output
git_clean f010
100%
Passed
Tokens
136
Input
91
Total output
81
Reasoning within output
git_clean f011
100%
Passed
Tokens
135
Input
51
Total output
40
Reasoning within output
git_clean f012
100%
Passed
Tokens
149
Input
325
Total output
318
Reasoning within output
git_grep f001
100%
Passed
Tokens
128
Input
155
Total output
150
Reasoning within output
git_grep f002
100%
Passed
Tokens
139
Input
5
Total output
0
Reasoning within output
git_grep f003
100%
Passed
Tokens
159
Input
5
Total output
0
Reasoning within output
git_grep f004
0%
Failed
Tokens
156
Input
19
Total output
10
Reasoning within output
git_grep f005
100%
Passed
Tokens
194
Input
149
Total output
148
Reasoning within output
git_grep f006
100%
Passed
Tokens
121
Input
82
Total output
79
Reasoning within output
git_grep f007
100%
Passed
Tokens
256
Input
1,926
Total output
1,924
Reasoning within output
git_grep f008
100%
Passed
Tokens
133
Input
19
Total output
12
Reasoning within output
git_grep f009
100%
Passed
Tokens
129
Input
7
Total output
0
Reasoning within output
git_grep f010
100%
Passed
Tokens
138
Input
5
Total output
0
Reasoning within output
git_grep f011
100%
Passed
Tokens
183
Input
5
Total output
0
Reasoning within output
git_grep f012
100%
Passed
Tokens
140
Input
12
Total output
0
Reasoning within output
git_log_format f001
100%
Passed
Tokens
802
Input
34
Total output
31
Reasoning within output
git_log_format f002
100%
Passed
Tokens
761
Input
29
Total output
16
Reasoning within output
git_log_format f003
100%
Passed
Tokens
670
Input
62
Total output
51
Reasoning within output
git_log_format f004
100%
Passed
Tokens
795
Input
25
Total output
22
Reasoning within output
git_log_format f005
100%
Passed
Tokens
674
Input
187
Total output
180
Reasoning within output
git_log_format f006
100%
Passed
Tokens
804
Input
56
Total output
53
Reasoning within output
git_log_format f007
100%
Passed
Tokens
824
Input
55
Total output
48
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,061
Input
26
Total output
23
Reasoning within output
git_log_format f009
100%
Passed
Tokens
684
Input
47
Total output
44
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,164
Input
40
Total output
37
Reasoning within output
git_log_format f011
100%
Passed
Tokens
529
Input
132
Total output
129
Reasoning within output
git_log_format f012
100%
Passed
Tokens
400
Input
5
Total output
0
Reasoning within output
git_show f001
100%
Passed
Tokens
243
Input
7
Total output
0
Reasoning within output
git_show f002
100%
Passed
Tokens
243
Input
107
Total output
99
Reasoning within output
git_show f003
100%
Passed
Tokens
656
Input
64
Total output
56
Reasoning within output
git_show f004
100%
Passed
Tokens
491
Input
40
Total output
32
Reasoning within output
git_show f005
100%
Passed
Tokens
278
Input
85
Total output
81
Reasoning within output
git_show f006
100%
Passed
Tokens
280
Input
68
Total output
65
Reasoning within output
git_show f007
100%
Passed
Tokens
240
Input
8
Total output
0
Reasoning within output
git_show f008
100%
Passed
Tokens
281
Input
104
Total output
78
Reasoning within output
git_show f009
100%
Passed
Tokens
335
Input
5
Total output
0
Reasoning within output
git_show f010
100%
Passed
Tokens
245
Input
5
Total output
0
Reasoning within output
git_show f011
100%
Passed
Tokens
295
Input
63
Total output
59
Reasoning within output
git_show f012
100%
Passed
Tokens
398
Input
118
Total output
115
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
162
Input
241
Total output
237
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
210
Input
605
Total output
595
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
180
Input
305
Total output
299
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
235
Input
384
Total output
360
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
220
Input
259
Total output
239
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
224
Input
518
Total output
497
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
231
Input
98
Total output
87
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
207
Input
56
Total output
48
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
205
Input
117
Total output
110
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
270
Input
824
Total output
794
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
243
Input
48
Total output
25
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
302
Input
378
Total output
335
Reasoning within output
rebase f001
100%
Passed
Tokens
173
Input
66
Total output
60
Reasoning within output
rebase f002
100%
Passed
Tokens
201
Input
47
Total output
38
Reasoning within output
rebase f003
100%
Passed
Tokens
204
Input
395
Total output
390
Reasoning within output
rebase f004
100%
Passed
Tokens
246
Input
8,455
Total output
8,431
Reasoning within output
rebase f005
100%
Passed
Tokens
225
Input
438
Total output
422
Reasoning within output
rebase f006
100%
Passed
Tokens
236
Input
110
Total output
83
Reasoning within output
rebase f007
100%
Passed
Tokens
232
Input
89
Total output
75
Reasoning within output
rebase f008
100%
Passed
Tokens
219
Input
656
Total output
648
Reasoning within output
rebase f009
100%
Passed
Tokens
205
Input
179
Total output
172
Reasoning within output
rebase f010
100%
Passed
Tokens
303
Input
540
Total output
510
Reasoning within output
rebase f011
100%
Passed
Tokens
227
Input
44
Total output
17
Reasoning within output
rebase f012
0%
Failed
Tokens
331
Input
3,308
Total output
3,267
Reasoning within output
reflog f001
100%
Passed
Tokens
332
Input
369
Total output
331
Reasoning within output
reflog f002
100%
Passed
Tokens
290
Input
228
Total output
115
Reasoning within output
reflog f003
100%
Passed
Tokens
251
Input
87
Total output
27
Reasoning within output
reflog f004
100%
Passed
Tokens
378
Input
3,237
Total output
2,942
Reasoning within output
reflog f005
100%
Passed
Tokens
421
Input
1,826
Total output
1,734
Reasoning within output
reflog f006
100%
Passed
Tokens
328
Input
698
Total output
488
Reasoning within output
reflog f007
100%
Passed
Tokens
317
Input
152
Total output
59
Reasoning within output
reflog f008
100%
Passed
Tokens
392
Input
198
Total output
106
Reasoning within output
reflog f009
100%
Passed
Tokens
381
Input
1,575
Total output
1,412
Reasoning within output
reflog f010
100%
Passed
Tokens
331
Input
605
Total output
430
Reasoning within output
reflog f011
100%
Passed
Tokens
373
Input
2,341
Total output
2,134
Reasoning within output
reflog f012
100%
Passed
Tokens
366
Input
3,516
Total output
3,237
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
199
Input
9
Total output
0
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
347
Input
9
Total output
0
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
189
Input
9
Total output
0
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
187
Input
9
Total output
0
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
210
Input
122
Total output
117
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
276
Input
78
Total output
73
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
272
Input
9
Total output
0
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
238
Input
9
Total output
0
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
270
Input
30
Total output
0
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
196
Input
9
Total output
0
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
185
Input
40
Total output
21
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
201
Input
9
Total output
0
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
115
Input
204
Total output
196
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
181
Input
4,147
Total output
4,138
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
178
Input
59
Total output
26
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
171
Input
141
Total output
138
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
122
Input
2,562
Total output
2,535
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
174
Input
402
Total output
399
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
122
Input
185
Total output
168
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
178
Input
913
Total output
908
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
175
Input
212
Total output
209
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
162
Input
46
Total output
33
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
173
Input
25
Total output
15
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
120
Input
257
Total output
246
Reasoning within output
tag_management f001
100%
Passed
Tokens
133
Input
31
Total output
19
Reasoning within output
tag_management f002
100%
Passed
Tokens
132
Input
54
Total output
30
Reasoning within output
tag_management f003
100%
Passed
Tokens
135
Input
42
Total output
27
Reasoning within output
tag_management f004
100%
Passed
Tokens
139
Input
32
Total output
24
Reasoning within output
tag_management f005
100%
Passed
Tokens
151
Input
62
Total output
48
Reasoning within output
tag_management f006
100%
Passed
Tokens
143
Input
264
Total output
252
Reasoning within output
tag_management f007
66.7%
Failed
Tokens
140
Input
566
Total output
516
Reasoning within output
tag_management f008
100%
Passed
Tokens
142
Input
165
Total output
136
Reasoning within output
tag_management f009
100%
Passed
Tokens
144
Input
76
Total output
53
Reasoning within output
tag_management f010
100%
Passed
Tokens
123
Input
32
Total output
19
Reasoning within output
tag_management f011
100%
Passed
Tokens
125
Input
39
Total output
28
Reasoning within output
tag_management f012
100%
Passed
Tokens
154
Input
64
Total output
49
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
233
Input
137
Total output
128
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
232
Input
348
Total output
325
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
279
Input
15
Total output
5
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
287
Input
69
Total output
63
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
192
Input
61
Total output
44
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
224
Input
194
Total output
181
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
229
Input
1,064
Total output
1,041
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
215
Input
195
Total output
137
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
325
Input
79
Total output
73
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
296
Input
144
Total output
127
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
292
Input
99
Total output
89
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
217
Input
277
Total output
264
Reasoning within output