Sakana / fugu-max
max
95.6%
195 / 204 fixtures · 1 run(s)
53,328 input / 158,353 total output / 154,152 reasoning within output tokens $1.05122125
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-2.4%
Text: 95.6% →
JSON: 93.1%
+4
Gained
JSON pass / text fail
−9
Lost
Text pass / JSON fail
186
Unchanged Pass
Both pass
5
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|---|---|---|
| f001 | 0% (0/1) | 100% (1/1) | -100% |
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| branch_cleanup | 100% | 75% | -25% |
| git_grep | 100% | 83.3% | -16.7% |
| merge_conflicts | 91.7% | 83.3% | -8.3% |
| commit_messages | 91.7% | 100% | + 8.3% |
| commit_squash | 100% | 91.7% | -8.3% |
| git_show | 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_clean | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| rebase | 83.3% | 83.3% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 100% | 100% | + 0% |
| tag_management | 100% | 100% | + 0% |
| worktree_usage | 91.7% | 91.7% | + 0% |
Changed Fixtures (13)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
341
Input
682
Total output
678
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
335
Input
533
Total output
529
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
331
Input
46
Total output
38
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
286
Input
344
Total output
339
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
344
Input
1,547
Total output
1,542
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
326
Input
534
Total output
531
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
298
Input
390
Total output
386
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
337
Input
375
Total output
372
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
291
Input
404
Total output
401
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
529
Input
534
Total output
531
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
340
Input
336
Total output
333
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
235
Input
439
Total output
435
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
181
Input
298
Total output
294
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
188
Input
86
Total output
75
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
171
Input
252
Total output
251
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
209
Input
413
Total output
406
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
179
Input
273
Total output
269
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
206
Input
383
Total output
373
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
185
Input
341
Total output
334
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
199
Input
343
Total output
334
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
158
Input
246
Total output
245
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
183
Input
87
Total output
76
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
144
Input
59
Total output
52
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
233
Input
289
Total output
277
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
172
Input
188
Total output
182
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
220
Input
190
Total output
180
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
190
Input
368
Total output
362
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
248
Input
323
Total output
302
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
234
Input
4,336
Total output
4,316
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
214
Input
174
Total output
152
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
231
Input
149
Total output
138
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
223
Input
53
Total output
45
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
206
Input
36
Total output
29
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
309
Input
1,641
Total output
1,611
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
263
Input
119
Total output
92
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
335
Input
683
Total output
634
Reasoning within output
commit_messages f001
15%
Failed
Tokens
201
Input
202
Total output
172
Reasoning within output
commit_messages f002
67.5%
Passed
Tokens
280
Input
494
Total output
478
Reasoning within output
commit_messages f003
62.5%
Passed
Tokens
182
Input
120
Total output
103
Reasoning within output
commit_messages f004
91.5%
Passed
Tokens
185
Input
7
Total output
0
Reasoning within output
commit_messages f005
92.5%
Passed
Tokens
197
Input
76
Total output
69
Reasoning within output
commit_messages f006
91.5%
Passed
Tokens
232
Input
60
Total output
51
Reasoning within output
commit_messages f007
92.5%
Passed
Tokens
256
Input
231
Total output
222
Reasoning within output
commit_messages f008
96.5%
Passed
Tokens
156
Input
362
Total output
357
Reasoning within output
commit_messages f009
82.5%
Passed
Tokens
220
Input
82
Total output
70
Reasoning within output
commit_messages f010
91.5%
Passed
Tokens
367
Input
165
Total output
148
Reasoning within output
commit_messages f011
87.5%
Passed
Tokens
238
Input
371
Total output
359
Reasoning within output
commit_messages f012
84%
Passed
Tokens
221
Input
163
Total output
152
Reasoning within output
commit_squash f001
100%
Passed
Tokens
217
Input
3,657
Total output
3,643
Reasoning within output
commit_squash f002
100%
Passed
Tokens
215
Input
135
Total output
124
Reasoning within output
commit_squash f003
100%
Passed
Tokens
202
Input
3,670
Total output
3,657
Reasoning within output
commit_squash f004
100%
Passed
Tokens
210
Input
26,874
Total output
26,861
Reasoning within output
commit_squash f005
100%
Passed
Tokens
193
Input
2,805
Total output
2,798
Reasoning within output
commit_squash f006
100%
Passed
Tokens
193
Input
76
Total output
62
Reasoning within output
commit_squash f007
100%
Passed
Tokens
183
Input
125
Total output
111
Reasoning within output
commit_squash f008
100%
Passed
Tokens
209
Input
68
Total output
54
Reasoning within output
commit_squash f009
100%
Passed
Tokens
187
Input
236
Total output
223
Reasoning within output
commit_squash f010
100%
Passed
Tokens
195
Input
418
Total output
403
Reasoning within output
commit_squash f011
100%
Passed
Tokens
209
Input
233
Total output
216
Reasoning within output
commit_squash f012
100%
Passed
Tokens
219
Input
140
Total output
118
Reasoning within output
git_bisect f001
100%
Passed
Tokens
245
Input
8
Total output
0
Reasoning within output
git_bisect f002
100%
Passed
Tokens
266
Input
50
Total output
41
Reasoning within output
git_bisect f003
100%
Passed
Tokens
268
Input
9
Total output
0
Reasoning within output
git_bisect f004
100%
Passed
Tokens
286
Input
158
Total output
152
Reasoning within output
git_bisect f005
100%
Passed
Tokens
272
Input
61
Total output
50
Reasoning within output
git_bisect f006
100%
Passed
Tokens
289
Input
8
Total output
0
Reasoning within output
git_bisect f007
100%
Passed
Tokens
260
Input
7
Total output
0
Reasoning within output
git_bisect f008
100%
Passed
Tokens
268
Input
40
Total output
31
Reasoning within output
git_bisect f009
100%
Passed
Tokens
266
Input
8
Total output
0
Reasoning within output
git_bisect f010
100%
Passed
Tokens
266
Input
8
Total output
0
Reasoning within output
git_bisect f011
100%
Passed
Tokens
268
Input
7
Total output
0
Reasoning within output
git_bisect f012
100%
Passed
Tokens
318
Input
179
Total output
173
Reasoning within output
git_clean f001
100%
Passed
Tokens
150
Input
170
Total output
160
Reasoning within output
git_clean f002
100%
Passed
Tokens
134
Input
83
Total output
73
Reasoning within output
git_clean f003
100%
Passed
Tokens
158
Input
62
Total output
56
Reasoning within output
git_clean f004
100%
Passed
Tokens
158
Input
40
Total output
33
Reasoning within output
git_clean f005
100%
Passed
Tokens
123
Input
262
Total output
250
Reasoning within output
git_clean f006
100%
Passed
Tokens
175
Input
98
Total output
89
Reasoning within output
git_clean f007
100%
Passed
Tokens
138
Input
224
Total output
209
Reasoning within output
git_clean f008
100%
Passed
Tokens
145
Input
79
Total output
69
Reasoning within output
git_clean f009
100%
Passed
Tokens
139
Input
170
Total output
156
Reasoning within output
git_clean f010
100%
Passed
Tokens
136
Input
118
Total output
108
Reasoning within output
git_clean f011
100%
Passed
Tokens
135
Input
102
Total output
91
Reasoning within output
git_clean f012
100%
Passed
Tokens
149
Input
299
Total output
292
Reasoning within output
git_grep f001
100%
Passed
Tokens
128
Input
165
Total output
160
Reasoning within output
git_grep f002
100%
Passed
Tokens
139
Input
195
Total output
194
Reasoning within output
git_grep f003
100%
Passed
Tokens
159
Input
25
Total output
18
Reasoning within output
git_grep f004
100%
Passed
Tokens
156
Input
93
Total output
86
Reasoning within output
git_grep f005
100%
Passed
Tokens
194
Input
255
Total output
254
Reasoning within output
git_grep f006
100%
Passed
Tokens
121
Input
149
Total output
146
Reasoning within output
git_grep f007
100%
Passed
Tokens
256
Input
9,532
Total output
9,530
Reasoning within output
git_grep f008
100%
Passed
Tokens
133
Input
32
Total output
25
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
58
Total output
51
Reasoning within output
git_grep f012
100%
Passed
Tokens
140
Input
46
Total output
32
Reasoning within output
git_log_format f001
100%
Passed
Tokens
814
Input
47
Total output
44
Reasoning within output
git_log_format f002
100%
Passed
Tokens
794
Input
54
Total output
45
Reasoning within output
git_log_format f003
100%
Passed
Tokens
673
Input
96
Total output
85
Reasoning within output
git_log_format f004
100%
Passed
Tokens
839
Input
32
Total output
29
Reasoning within output
git_log_format f005
100%
Passed
Tokens
674
Input
29
Total output
22
Reasoning within output
git_log_format f006
100%
Passed
Tokens
804
Input
94
Total output
91
Reasoning within output
git_log_format f007
100%
Passed
Tokens
835
Input
6
Total output
0
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,048
Input
20
Total output
17
Reasoning within output
git_log_format f009
100%
Passed
Tokens
666
Input
71
Total output
68
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,165
Input
80
Total output
77
Reasoning within output
git_log_format f011
100%
Passed
Tokens
525
Input
243
Total output
240
Reasoning within output
git_log_format f012
100%
Passed
Tokens
425
Input
48
Total output
45
Reasoning within output
git_show f001
100%
Passed
Tokens
241
Input
36
Total output
27
Reasoning within output
git_show f002
0%
Failed
Tokens
241
Input
524
Total output
516
Reasoning within output
git_show f003
100%
Passed
Tokens
664
Input
83
Total output
75
Reasoning within output
git_show f004
100%
Passed
Tokens
566
Input
161
Total output
154
Reasoning within output
git_show f005
100%
Passed
Tokens
273
Input
82
Total output
78
Reasoning within output
git_show f006
100%
Passed
Tokens
280
Input
41
Total output
38
Reasoning within output
git_show f007
100%
Passed
Tokens
240
Input
52
Total output
42
Reasoning within output
git_show f008
100%
Passed
Tokens
283
Input
77
Total output
48
Reasoning within output
git_show f009
100%
Passed
Tokens
335
Input
58
Total output
51
Reasoning within output
git_show f010
100%
Passed
Tokens
243
Input
35
Total output
28
Reasoning within output
git_show f011
100%
Passed
Tokens
273
Input
6
Total output
0
Reasoning within output
git_show f012
100%
Passed
Tokens
392
Input
33
Total output
30
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
162
Input
657
Total output
653
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
210
Input
350
Total output
340
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
180
Input
673
Total output
667
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
235
Input
9,998
Total output
9,974
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
220
Input
368
Total output
347
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
206
Input
1,258
Total output
1,231
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
231
Input
51
Total output
40
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
207
Input
31
Total output
23
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
205
Input
104
Total output
97
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
270
Input
1,189
Total output
1,159
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
243
Input
137
Total output
110
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
302
Input
1,273
Total output
1,222
Reasoning within output
rebase f001
100%
Passed
Tokens
173
Input
4,653
Total output
4,647
Reasoning within output
rebase f002
100%
Passed
Tokens
202
Input
424
Total output
415
Reasoning within output
rebase f003
100%
Passed
Tokens
180
Input
280
Total output
271
Reasoning within output
rebase f004
0%
Failed
Tokens
244
Input
3,514
Total output
3,493
Reasoning within output
rebase f005
100%
Passed
Tokens
227
Input
423
Total output
407
Reasoning within output
rebase f006
100%
Passed
Tokens
235
Input
477
Total output
450
Reasoning within output
rebase f007
100%
Passed
Tokens
231
Input
696
Total output
685
Reasoning within output
rebase f008
100%
Passed
Tokens
219
Input
85
Total output
77
Reasoning within output
rebase f009
100%
Passed
Tokens
204
Input
111
Total output
104
Reasoning within output
rebase f010
100%
Passed
Tokens
301
Input
2,405
Total output
2,375
Reasoning within output
rebase f011
100%
Passed
Tokens
253
Input
200
Total output
177
Reasoning within output
rebase f012
0%
Failed
Tokens
331
Input
9,015
Total output
8,974
Reasoning within output
reflog f001
100%
Passed
Tokens
331
Input
639
Total output
605
Reasoning within output
reflog f002
100%
Passed
Tokens
298
Input
232
Total output
56
Reasoning within output
reflog f003
100%
Passed
Tokens
286
Input
530
Total output
406
Reasoning within output
reflog f004
100%
Passed
Tokens
373
Input
3,979
Total output
3,735
Reasoning within output
reflog f005
100%
Passed
Tokens
407
Input
358
Total output
306
Reasoning within output
reflog f006
100%
Passed
Tokens
302
Input
345
Total output
219
Reasoning within output
reflog f007
100%
Passed
Tokens
361
Input
801
Total output
545
Reasoning within output
reflog f008
100%
Passed
Tokens
381
Input
328
Total output
239
Reasoning within output
reflog f009
100%
Passed
Tokens
348
Input
623
Total output
516
Reasoning within output
reflog f010
100%
Passed
Tokens
327
Input
1,269
Total output
889
Reasoning within output
reflog f011
100%
Passed
Tokens
346
Input
604
Total output
516
Reasoning within output
reflog f012
100%
Passed
Tokens
339
Input
1,141
Total output
1,026
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
202
Input
9
Total output
0
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
370
Input
245
Total output
80
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
78
Total output
66
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
196
Input
52
Total output
40
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
276
Input
181
Total output
167
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
268
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
100
Total output
57
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
196
Input
9
Total output
0
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
186
Input
114
Total output
96
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
155
Total output
147
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
178
Input
11,890
Total output
11,881
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
175
Input
4,044
Total output
4,008
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
174
Input
186
Total output
183
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
122
Input
10,320
Total output
10,298
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
155
Input
526
Total output
516
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
122
Input
316
Total output
299
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
186
Input
50
Total output
42
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
179
Input
194
Total output
191
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
163
Input
53
Total output
40
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
188
Input
266
Total output
262
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
120
Input
239
Total output
228
Reasoning within output
tag_management f001
100%
Passed
Tokens
131
Input
43
Total output
31
Reasoning within output
tag_management f002
100%
Passed
Tokens
130
Input
79
Total output
55
Reasoning within output
tag_management f003
100%
Passed
Tokens
136
Input
95
Total output
80
Reasoning within output
tag_management f004
100%
Passed
Tokens
140
Input
44
Total output
36
Reasoning within output
tag_management f005
100%
Passed
Tokens
154
Input
70
Total output
56
Reasoning within output
tag_management f006
100%
Passed
Tokens
145
Input
288
Total output
274
Reasoning within output
tag_management f007
100%
Passed
Tokens
138
Input
418
Total output
401
Reasoning within output
tag_management f008
100%
Passed
Tokens
143
Input
545
Total output
516
Reasoning within output
tag_management f009
100%
Passed
Tokens
146
Input
90
Total output
67
Reasoning within output
tag_management f010
100%
Passed
Tokens
125
Input
37
Total output
24
Reasoning within output
tag_management f011
100%
Passed
Tokens
123
Input
57
Total output
46
Reasoning within output
tag_management f012
100%
Passed
Tokens
155
Input
136
Total output
121
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
227
Input
227
Total output
218
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
232
Input
610
Total output
587
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
274
Input
52
Total output
42
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
292
Input
127
Total output
121
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
194
Input
65
Total output
48
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
222
Input
69
Total output
52
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
232
Input
3,052
Total output
3,029
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
218
Input
458
Total output
400
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
318
Input
47
Total output
41
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
300
Input
75
Total output
58
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
287
Input
43
Total output
33
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
218
Input
258
Total output
245
Reasoning within output